​

Claude Code Documentation Map

This is a comprehensive map of all Claude Code documentation pages with their headings, designed for easy navigation by LLMs.

Note: This file is auto-generated by GitHub Actions. Do not edit manually. Last updated: 2026-09-30 17:33:07 UTC

​

Document Structure

This map uses a hierarchical structure:

• ## marks documentation groups (e.g., ‘Getting started’)
• ### marks individual documentation pages
• ### Parent > Child marks a nested group; #### marks its pages
• Nested bullets show the heading structure within each page
• Each page title links to the full documentation

​

Getting started

​

overview

• Get started
• What you can do
• Use Claude Code everywhere
• Next steps

​

quickstart

• Before you begin
• Step 1: Install Claude Code
• Step 2: Log in to your account
• Step 3: Start your first session
• Step 4: Ask your first question
• Step 5: Make your first code change
• Step 6: Use Git with Claude Code
• Step 7: Fix a bug or add a feature
• Step 8: Test out other common workflows
• Essential commands
• Pro tips for beginners
• What’s next?
• Getting help

​

changelog

• (No headings found)

​

Core concepts

​

how-claude-code-works

• The agentic loop
  • Models
  • Tools
• What Claude can access
• Environments and interfaces
  • Execution environments
  • Interfaces
• Work with sessions
  • Work across branches
  • Resume or fork sessions
  • The context window
    • Context Claude Code adds on its own
    • When context fills up
    • Manage context with skills and subagents
• Stay safe with checkpoints and permissions
  • Undo changes with checkpoints
  • Control what Claude can do
• Work effectively with Claude Code
  • Ask Claude Code for help
  • It’s a conversation
    • Interrupt and steer
  • Delegate, don’t dictate
• What’s next

​

features-overview

• Overview
• Match features to your goal
  • Build your setup over time
  • Compare similar features
  • Understand how features layer
  • Combine features
• Understand context costs
  • Context cost by feature
  • Understand how features load
• Learn more

​

claude-directory

• Explore the directory
• What’s not shown
• Choose the right file
• File reference
• Frontmatter fields by file
• Troubleshoot configuration
• Application data
  • Cleaned up automatically
  • Session scratchpad directory
  • Kept until you delete them
  • Plaintext storage
  • Clear local data
• Related resources

​

context-window

• What the timeline shows
• What survives compaction
• When your context fills up
• Check your own session
• Related resources

​

prompt-caching

• How the cache is organized
  • Where the cache lives
• Actions that invalidate the cache
  • Switching models
  • Changing effort level
  • Turning on fast mode
  • Connecting or removing an MCP server
  • Enabling or disabling a plugin
    • Plugin components that keep the cache
    • Plugins that provide MCP servers
    • Code intelligence plugins
    • When plugin changes apply
    • Plugins you enable and then disable in one session
  • Denying an entire tool
  • Compacting the conversation
  • Accumulating many images
  • Upgrading Claude Code
• Actions that keep the cache
  • Editing files in your repository
  • Editing CLAUDE.md mid-session
  • Changing permission mode
  • Changing output style
  • Invoking skills and commands
  • Running /recap
  • Rewinding the conversation
• Resuming a session
• Cache lifetime
  • Which TTL each request gets
  • Choose the TTL yourself
• Cache scope
• Check cache performance
• Subagents and the cache
• Disable prompt caching
• Related resources

​

Use Claude Code

​

memory

• CLAUDE.md vs auto memory
• CLAUDE.md files
  • When to add to CLAUDE.md
  • Choose where to put CLAUDE.md files
  • Set up a project CLAUDE.md
  • Write effective instructions
    • Audit your instruction files
  • Import additional files
  • How CLAUDE.md files load
    • Load from additional directories
  • Organize rules with .claude/rules/
    • Set up rules
    • Path-specific rules
    • Rule frontmatter reference
    • Share rules across projects with symlinks
    • User-level rules
  • Manage CLAUDE.md for large teams
    • Deploy organization-wide CLAUDE.md
    • Exclude specific CLAUDE.md files
• AGENTS.md
  • When Claude Code reads AGENTS.md
  • Choose which instruction files load
  • When AGENTS.md support is unavailable
  • Where AGENTS.md differs from CLAUDE.md
  • Remove an earlier AGENTS.md workaround
  • Share one file with other coding tools
  • Migrate instructions from other tools
• Auto memory
  • Enable or disable auto memory
  • Storage location
  • How it works
  • Audit and edit your memory
• View and edit with /memory
• Troubleshoot memory issues
  • Claude isn’t following my CLAUDE.md
  • My AGENTS.md isn’t loading
  • I don’t know what auto memory saved
  • My CLAUDE.md is too large
  • Instructions seem lost after /compact
• Related resources

​

sessions

• Resume a session
  • What a resumed session restores
    • Permission mode on resume
      • Resume in plan mode with -p
  • Resume from a summary
  • Where the session picker looks
• Name your sessions
• Use the session picker
• Branch a session
• Manage context within a session
• Export and locate session data
  • Access conversations from scripts
  • Where transcripts are stored
  • Delete session data
  • Name the project directory yourself
• See also

​

common-workflows

• Prompt recipes
  • Understand new codebases
    • Get a quick codebase overview
    • Find relevant code
  • Fix bugs efficiently
  • Refactor code
  • Work with tests
  • Create pull requests
  • Handle documentation
  • Work in notes and non-code folders
  • Work with images
  • Reference files and directories
  • Run Claude on a schedule
  • Ask Claude about its capabilities
    • Example questions
• Resume previous conversations
• Run parallel sessions with worktrees
• Plan before editing
• Delegate research to subagents
• Pipe Claude into scripts
• Next steps

​

prompt-library

• What makes these prompts work
• Where these come from
• Related resources

​

best-practices

• Give Claude a way to verify its work
• Explore first, then plan, then code
• Provide specific context in your prompts
  • Provide rich content
• Configure your environment
  • Write an effective CLAUDE.md
  • Configure permissions
  • Use CLI tools
  • Connect MCP servers
  • Set up hooks
  • Create skills
  • Create custom subagents
  • Install plugins
• Communicate effectively
  • Ask codebase questions
  • Let Claude interview you
• Manage your session
  • Course-correct early and often
  • Manage context aggressively
  • Use subagents for investigation
  • Rewind with checkpoints
  • Resume conversations
• Automate and scale
  • Run non-interactive mode
  • Run multiple Claude sessions
  • Fan out across files
  • Run autonomously with auto mode
  • Add an adversarial review step
• Avoid common failure patterns
• Develop your intuition
• Related resources

​

Platforms and integrations

​

platforms

• Where to run Claude Code
• Connect your tools
• Work when you are away from your terminal
• Related resources
  • Platforms
  • Integrations
  • Remote access

​

remote-control

• Requirements
• Start a Remote Control session
  • Check connection status
  • Connect from another device
  • What connected devices see
  • Enable Remote Control for all sessions
  • Resume sessions after stopping the server
• Connection and security
• Trusted Devices
  • Enable Trusted Devices for a Team or Enterprise organization
  • What members see
  • Manage enrolled devices
• Remote Control vs cloud sessions
• Mobile push notifications
• Limitations
• Troubleshooting
  • “Remote Control requires a claude.ai subscription”
  • “Remote Control requires a full-scope login token”
  • “Unable to determine your organization for Remote Control eligibility”
  • “Remote Control isn’t enabled for this account”
  • “Couldn’t verify Remote Control eligibility”
  • “Remote Control requires feature-flag evaluation”
  • “Remote Control is only available when using Claude via api.anthropic.com”
  • “Remote Control is disabled by your organization’s policy”
  • “Couldn’t verify your organization’s policy for remote control”
  • “Remote credentials fetch failed”
  • “Couldn’t reconnect to your Remote Control session”
  • “Previous session is unavailable — run /remote-control to start a new one”
  • “Remote Control got an unexpected server response”
  • “Your organization requires Trusted Devices for Remote Control, but this device is not enrolled”
  • “session expired for trusted-device check”
• Related resources

​

claude-projects

• When to use a project
  • When something else fits better
• How a project is organized
• Create a project
  • Check the prerequisites
  • Start a new project from scratch
  • Start from an existing cloud session
  • Set up GitHub access
• Work in a project
  • Your first batch
  • Send work and read results
  • Review a thread’s pull request
  • See what needs you in Overview
  • Open a thread when you need control
  • Choose models and let Claude manage context
  • Tune how Claude runs a project
  • Unblock a thread waiting on approval
  • Run a thread on your own computer
• Give a project standing context
  • Write project instructions
  • Decide which repositories to add
  • Add files and folders
  • What threads pick up from your repositories
  • Choose an environment for threads
  • Get skills, plugins, connectors, and tools into threads
• Project settings reference
  • Pause, archive, or delete a project
• Usage and cost
  • What draws on your plan
  • See and reduce a project’s usage
• How projects relate to other Claude Code features
• Limitations
• Troubleshooting
  • A thread looks stuck
  • Threads guessed or stalled instead of asking
  • Claude hasn’t responded
  • Repository access errors
  • A thread hit the usage limit
  • Additional usage credits are required
  • Lost contact with your folder
  • Other messages
• Related resources

​

mobile

• Get the app
• Work from your phone
  • Start and monitor cloud sessions
  • Continue a local session with Remote Control
  • Get push notifications
• Limitations
• Related resources

​

chrome

• Capabilities
• Prerequisites
• Get started in the CLI
  • Install the extension when Claude asks
  • Enable Chrome by default
  • Manage site permissions
  • Browser tools in plan mode
• Example workflows
  • Test a local web application
  • Debug with console logs
  • Automate form filling
  • Upload files to web pages
  • Draft content in Google Docs
  • Extract data from web pages
  • Run multi-site workflows
  • Record a demo GIF
  • Save screenshots to disk
• Troubleshooting
  • Extension not detected
  • Browser not responding
  • Connection drops during long sessions
  • Windows-specific issues
  • Common error messages
• See also

​

computer-use

• What you can do with computer use
• When computer use applies
• Enable computer use
• Approve apps per session
• How Claude works on your screen
  • One session at a time
  • Apps are hidden while Claude works
  • Screenshots are downscaled automatically
  • Stop at any time
• Safety and the trust boundary
• Example workflows
  • Validate a native build
  • Reproduce a layout bug
  • Test a simulator flow
• Differences from the Desktop app
• Troubleshooting
  • “Computer use is in use by another Claude session”
  • macOS permissions prompt keeps reappearing
  • computer-use doesn’t appear in /mcp
• See also

​

vs-code

• Prerequisites
• Install the extension
• Get started
• Use the prompt box
  • Reference files and folders
  • Paste text
  • Resume past conversations
  • Resume cloud sessions from Claude.ai
  • Check account and usage
• Customize your workflow
  • Choose where Claude lives
  • Run multiple conversations
  • Organize sessions into groups
  • Filter the sessions list
  • Switch to terminal mode
• Manage plugins
  • Install plugins
  • Share a plugin install link
  • Manage marketplaces
• Automate browser tasks with Chrome
• VS Code commands and shortcuts
  • Launch a VS Code tab from other tools
• Configure settings
  • Extension settings
• Use a screen reader
  • Use the chat panel from the keyboard
• VS Code extension vs. Claude Code CLI
  • Rewind with checkpoints
  • Run CLI in VS Code
  • Switch between extension and CLI
  • Include terminal output in prompts
  • Monitor background processes
  • Connect to external tools with MCP
• Work with git
  • Create commits and pull requests
• Use third-party providers
• Security and privacy
  • The built-in IDE MCP server
• Fix common issues
  • Extension won’t install
  • Spark icon not visible
  • Cmd+Esc does nothing on macOS
  • Claude Code never responds
• Uninstall the extension
• Next steps

​

jetbrains

• Supported IDEs
• Features
• Installation
• Usage
  • From your IDE
  • From external terminals
• Configuration
  • Claude Code settings
  • Plugin settings
    • General settings
    • ESC key configuration
• Special configurations
  • Remote development
  • WSL configuration
    • Allow WSL2 traffic through Windows Firewall
    • Switch WSL2 to mirrored networking
• Troubleshooting
  • Plugin not working
  • IDE not detected
  • Command not found
• Security considerations
  • The built-in IDE MCP server

​

slack

• Use cases
• Prerequisites
• Setting up Claude Code in Slack
• How it works
  • Automatic detection
  • Context gathering
  • Session flow
• User interface elements
  • Message actions
  • Repository selection
• Access and permissions
  • User-level access
  • Workspace-level access
  • Channel-based access control
• What’s accessible where
• Best practices
  • Writing effective requests
  • When to use Slack vs. web
• Troubleshooting
  • “Claude Code is not enabled for your account”
  • Sessions not starting
  • Sessions from a Claude Tag channel fail to start
  • Repository not showing
  • Wrong repository selected
  • Authentication errors
• Current limitations
• Related resources

​

claude-tag

• (No headings found)

​

Platforms and integrations > Claude Code in the cloud

​

web-quickstart

• How sessions run
• Compare ways to run Claude Code
• Connect GitHub
  • Connect from your terminal
    • Remove the /web-setup token
• Start a task
• Pre-fill sessions
• Review and iterate
• Troubleshoot setup
  • No repositories appear after connecting GitHub
  • The page only shows a GitHub login button
  • “Claude Code isn’t available on your account”
  • /web-setup says “Not signed in to Claude”
  • /web-setup warns that your token doesn’t have the workflow scope
  • /web-setup shows “No commands match” or “Unknown command”
  • “Could not create a cloud environment” or “No cloud environment available” when using --cloud
  • Setup script failed
  • New sessions hang or time out during setup
  • Session keeps running after closing the tab
• Next steps

​

claude-code-on-the-web

• Cloud environments
• GitHub authentication options
• Move tasks between terminal and cloud
  • From terminal to cloud
    • Tips for cloud tasks
    • Send local repositories without GitHub
  • Send follow-ups from the CLI
    • Output and errors
  • From cloud to terminal
    • Teleport requirements
    • --teleport is unavailable
• Work with sessions
  • Take back a queued message
  • Manage context
  • Permission modes in cloud sessions
  • Review changes
  • Share sessions
    • Share from an Enterprise or Team account
    • Share from a Max or Pro account
  • Archive sessions
  • Delete sessions
• Auto-fix pull requests
  • How Claude responds to PR activity
• Security and isolation
• Troubleshooting
  • Session creation failed
  • Unable to get organization UUID
  • Remote Control session expired or access denied
  • Environment expired
• Limitations
• Related resources

​

routines

• Example use cases
• Create a routine
  • Create from the web
  • Create from the CLI
• Configure triggers
  • Add a schedule trigger
    • Schedule a one-off run
  • Add an API trigger
    • Trigger a routine
    • API reference
  • Add a GitHub trigger
    • Supported events
    • Filter pull requests
• Manage routines
  • View and interact with runs
  • Edit and control routines
  • Manage routines from the CLI
  • Repositories and branch permissions
  • Connectors
  • Environments and network access
• Usage and limits
• Troubleshooting
  • /schedule returns “Unknown command”
  • “Routines are disabled by your organization’s policy”
• Related resources

​

ultrareview

• Run ultrareview from the CLI
  • Review against a different base
  • Review a pull request
  • Post findings to the pull request
  • Pass a request in plain words
  • Diff limits and fallbacks
• Pricing and free runs
• Track a running review
• Run ultrareview non-interactively
• How ultrareview compares to /code-review
• Related resources

​

Platforms and integrations > Claude Code on desktop

​

desktop-quickstart

• Install
• Start your first session
• Now what?
• What’s next

​

desktop

• Start a session
• Work with code
  • Use the prompt box
  • Add files and context to prompts
  • Choose a permission mode
  • Preview your app
  • Browse external sites
    • Approve Claude’s actions on a site
    • Choose between the Browser and the Chrome extension
    • Restrict external browsing for your organization
  • Review changes with diff view
  • Review your code
  • Monitor pull request status
• Arrange your workspace
  • Run commands in the terminal
  • Open and edit files
  • Open files in other apps
  • Switch view modes
  • Keyboard shortcuts
  • Check usage
• Let Claude use your computer
  • When computer use applies
  • Enable computer use
  • App permissions
• Manage sessions
  • Work in parallel with sessions
  • Ask a side question without derailing the session
  • Watch background tasks
  • Work across sessions
  • Run long-running tasks in the cloud
  • Continue in another surface
  • Sessions from Dispatch
• Extend Claude Code
  • Connect external tools
  • Use skills
  • Install plugins
  • Configure preview servers
    • Auto-verify changes
    • Configuration fields
      • When to use program vs runtimeExecutable
      • Open the preview at a specific URL
    • Port conflicts
    • Examples
• Environment configuration
  • Local sessions
    • Local sessions on managed devices
  • Cloud sessions
  • SSH sessions
    • Pre-configure SSH connections for your team
    • Restrict which SSH hosts users can connect to
• Enterprise configuration
  • Admin console controls
  • Managed settings
  • Device management policies
  • Network access requirements
  • Authentication and SSO
  • Data handling
  • Deployment
• Coming from the CLI?
  • CLI flag equivalents
  • Shared configuration
    • MCP servers from the Claude Desktop chat app
  • Feature comparison
  • What’s not available in Desktop
• Troubleshooting
  • Check your version
  • 403 or authentication errors in the Code tab
  • Blank or stuck screen on launch
  • “Failed to load session”
  • Session not finding installed tools
  • Git and Git LFS errors
  • MCP servers not working on Windows
  • App won’t quit
  • Windows-specific issues
  • “Branch doesn’t exist yet” when opening in CLI
  • Still stuck?

​

desktop-linux

• Requirements
  • Cowork requirements
• Install
  • Install from a downloaded file
• Update
• Uninstall
• Troubleshoot
  • Unable to locate package claude-desktop
  • Unmet dependencies
  • Running as root without --no-sandbox is not supported
  • Cowork isn’t available
• What’s not in the Linux beta yet

​

desktop-wsl

• Requirements
• Start a WSL session
• What works in a WSL session
• Managed devices

​

desktop-scheduled-tasks

• Compare scheduling options
• Create a scheduled task
• Schedule options
• How scheduled tasks run
• Missed runs
• Permissions for scheduled tasks
• Manage scheduled tasks
• Related resources

​

desktop-ios-simulator

• Requirements
  • Choose which Xcode the simulator pane uses
• Run your app in the simulator
• Control the simulator yourself
• How sessions manage devices
• Grant Claude access to a device
  • Allow a device the first time
  • Actions that follow your permission mode
  • Turn off simulator access
• Limitations
• Troubleshooting
  • The simulator pane doesn’t open when Claude runs the app
  • The simulator pane says no simulators were found
• See also

​

Platforms and integrations > Code review & CI/CD

​

security-guidance

• Prerequisites
• Install the plugin
  • Enable for your team in local sessions
• What the plugin checks
  • On each file edit
  • At the end of each turn
  • On each commit or push Claude makes
  • Review independence and limits
• Add your own rules
  • Add guidance for the model-backed reviews
  • Add custom per-edit patterns
  • Rule file lookup locations
• Usage cost
• Disable or uninstall
• How the plugin integrates with Claude Code
• How this fits with other security tools
• Troubleshooting
• Related resources

​

claude-security

• Prerequisites
• Models and providers
• Install the plugin
  • Uninstall the plugin
• Scan and fix your codebase
  • Scan only your changes
  • Scope large repositories
  • Read the scan results
• Fix findings
  • Patches are never applied automatically
• How the plugin fits with other security tools
• Troubleshooting
• Related resources

​

code-review

• How reviews work
  • Severity levels
  • Rate and reply to findings
  • Check run output
  • What Code Review checks
• Set up Code Review
• Manually trigger reviews
  • Review pull requests from forks
• Customize reviews
  • CLAUDE.md
  • REVIEW.md
    • What you can tune
    • Example
    • Keep it focused
• View usage
• Pricing
• Troubleshooting
  • Retrigger a failed or timed-out review
  • Review didn’t run and the PR shows a spend-cap message
  • Find issues that aren’t showing as inline comments
• Review a diff locally
  • What the review reads and edits
  • Tune effort and arguments
  • Run in the foreground
  • Let Claude start the review
  • Escalate to ultrareview
• Related resources

​

github-actions

• Setup
  • Quick setup
  • Manual setup
  • Set up for an organization
  • Uninstall
  • GitHub App permissions
• Interactive and automation modes
  • Who can trigger runs
• Example use cases
  • Respond to @claude mentions
  • Run a skill
  • Run on a schedule
• Best practices
  • Define project standards in CLAUDE.md
  • Protect your credentials
  • Manage costs
• Use a cloud provider
• Troubleshooting
  • Claude not responding to @claude commands
  • CI not running on Claude’s commits
  • Authentication errors
• Advanced configuration
  • Action parameters
  • Pass CLI arguments
• Upgrade from beta
• What’s next

​

github-actions-cloud-providers

• Choose your provider
• Prerequisites
• Set up the integration
• Troubleshooting
• What’s next

​

github-enterprise-server

• What works with GitHub Enterprise Server
• Admin setup
  • GitHub App permissions
  • Manual setup
  • Network requirements
• Developer workflow
  • Teleport sessions to your terminal
• Plugin marketplaces on GHES
  • Add a GHES marketplace
  • Pre-register GHES marketplaces with managed settings
  • Allowlist GHES marketplaces in managed settings
• Limitations
• Troubleshooting
  • Cloud session fails to clone repository
  • Marketplace add fails with a policy error
  • Marketplace add on claude.ai fails with a GitHub access error
  • GHES instance not reachable
  • Session start fails with Unable to get organization UUID
• Related resources

​

gitlab-ci-cd

• Why use Claude Code with GitLab?
• How it works
• What can Claude do?
• Setup
  • Quick setup
  • Manual setup (recommended for production)
• Example use cases
  • Turn issues into MRs
  • Get implementation help
  • Fix bugs quickly
• Using with Amazon Bedrock and Google Cloud
• Configuration examples
  • Amazon Bedrock job example (OIDC)
  • Agent Platform job example (Workload Identity Federation)
• Best practices
  • CLAUDE.md configuration
  • Security considerations
  • Optimizing performance
  • CI costs
• Troubleshooting
  • Claude not responding to @claude commands
  • Job can’t write comments or open MRs
  • Authentication errors
• Advanced configuration
  • Common parameters and variables
  • Customizing Claude’s behavior

​

Agents and parallel work

​

agents

• Choose an approach
• Check on running work
• Learn more

​

sub-agents

• Built-in subagents
• Quickstart: create your first subagent
• Configure subagents
  • Choose the subagent scope
  • Write subagent files
  • Frontmatter reference
    • Subagent files Claude Code skips
      • Check an agents directory before a session
  • Choose a model
    • Run every subagent on one model
  • Control subagent capabilities
    • Available tools
    • Restrict which subagents can be spawned
    • Scope MCP servers to a subagent
    • Permission modes
    • Preload skills into subagents
    • Enable persistent memory
      • Persistent memory tips
    • Conditional rules with hooks
    • Disable specific subagents
  • Define hooks for subagents
    • Hooks in subagent frontmatter
    • Project-level hooks for subagent events
• Work with subagents
  • Understand automatic delegation
  • Invoke subagents explicitly
  • Run subagents in foreground or background
  • Subagent names
  • API errors in subagents
  • Subagent output scanning
  • Common patterns
    • Isolate high-volume operations
    • Run parallel research
    • Chain subagents
  • Choose between subagents and main conversation
  • Let subagents spawn their own subagents
  • Concurrent subagent limit
  • Manage subagent context
    • What loads at startup
    • Resume subagents
    • Auto-compaction
• Fork the current conversation
  • Observe and steer running forks
  • How forks differ from other subagents
  • Turn fork mode on or off
• Example subagents
  • Code reviewer
  • Debugger
  • Data scientist
  • Database query validator
• Next steps

​

agent-view

• Quick start
  • Open agent view by default
• Monitor sessions with agent view
  • Read session state
  • Row summaries
  • Pull request status
  • Peek and reply
  • Attach to a session
    • Switch sessions without leaving the terminal
  • Organize the list
  • Filter sessions
  • Keyboard shortcuts
• Dispatch new agents
  • From agent view
    • Dispatch to a specific directory
  • From inside a session
    • Send the session to the background
    • Copy the session with /fork
    • What carries over when you background
  • From your shell
    • Run a shell command
  • How file edits are isolated
    • What deleting a session removes
  • Set the model
  • Permission mode, model, and effort
    • Settings and provider
    • LLM gateway
    • Permission mode
    • Dispatch defaults
    • What persists across restarts
  • Settings, plugins, and MCP servers
• Manage sessions from the shell
  • List sessions as JSON
  • Read session state from a script
• How background sessions are hosted
  • The supervisor process
  • Where state is stored
  • Turn off agent view
• Troubleshooting
  • claude agents lists subagents instead of opening agent view
  • Agent view opens with no sessions
  • Backgrounding shows a Background this session? dialog
  • Prompt rejected as too short
  • Sessions show as failed or stopped after shutdown
  • Opening a session says the conversation is already open
  • Opening a session says it has no saved transcript
  • The terminal host died or the session stopped responding
    • Terminal host died
    • Session isn’t responding
  • A session fails before starting with a possibly low memory note
  • Agent view says the background service did not respond
  • Dispatch fails with Could not resolve authentication method
  • Background sessions can’t read Desktop, Documents, or Downloads on macOS
  • Background sessions can’t reach local-network hosts on macOS
  • A session is slow to respond after attaching
  • .claude/worktrees/ is filling up
• Limitations
• Related resources
• Version history

​

agent-teams

• When to use agent teams
  • Compare with subagents
• Enable agent teams
• Start your first agent team
• Control your agent team
  • Choose a display mode
  • Specify teammates and models
  • Have teammates plan before implementing
  • Talk to teammates directly
  • Assign and claim tasks
  • Shut down teammates
  • Enforce quality gates with hooks
• How agent teams work
  • How Claude starts agent teams
  • Architecture
  • Use subagent definitions for teammates
  • Permissions
    • Messages between agents
  • Context and communication
  • Token usage
• Use case examples
  • Run a parallel code review
  • Investigate with competing hypotheses
• Best practices
  • Give teammates enough context
  • Choose an appropriate team size
  • Size tasks appropriately
  • Wait for teammates to finish
  • Start with research and review
  • Avoid file conflicts
  • Monitor and steer
• Troubleshooting
  • Teammates not appearing
  • Claude spawns teammates instead of subagents
  • Too many permission prompts
  • Agents stopping early
  • Orphaned tmux sessions
• Limitations
• Next steps

​

cross-session-messaging

• When to use cross-session messaging
• Message another session
  • Message delivery
  • Get a notice when another session goes idle
    • Ask for a notice
    • What each session shows
    • Limits
  • See which sessions Claude can reach
  • Message sessions on other machines
• How a session treats an incoming message
  • What a message looks like
  • Control inbound messages
  • Non-interactive sessions
  • The session’s inbox socket
• Restrict cross-session messaging
  • Require approval for cross-machine messages
  • Turn off cross-session messaging
• Availability
• Limitations
• Related resources

​

workflows

• When to use a workflow
• Run a bundled workflow
  • Bundled workflows
  • Watch the run
• Have Claude write a workflow
  • Ask for a workflow in your prompt
    • Dismiss or turn off the keyword
    • Where the keyword works
  • Let Claude decide with ultracode
  • Approve the plan before it runs
  • Save the workflow for reuse
  • Distribute a workflow in a plugin
  • Pass input to a saved workflow
• Example workflow prompts
  • Audit many files for the same issue
  • Keep fixing until a check passes
  • Migrate many files in parallel
  • Review every changed file and write one summary
  • Research a topic across many sources
  • Find issues until the list stops growing
  • What the saved script looks like
  • Edit a saved script
• How a workflow runs
  • Prompt caching in a fan-out
  • Behavior and limits
• Manage runs
  • Resume after a pause
  • When a run hits your usage limit
  • Cost
  • Set a size guideline
  • Turn workflows off
• Related resources

​

worktrees

• Start Claude in a worktree
  • Set up the worktree environment
  • Ask Claude to create a worktree
• Clean up worktrees
• Resume a worktree session
• How Claude Code enforces isolation
• Isolate subagents with worktrees
  • Clean up subagent and background-session worktrees
• Customize worktree creation
  • Choose the base branch
  • Branch from a pull request
  • Copy gitignored files into worktrees
  • Reuse a worktree name
  • Replace worktree creation with a hook
• What worktrees share with the main checkout
• Manage worktrees manually
• Non-git version control
• Troubleshooting
  • Claude Code can’t enter the worktree at startup
  • Worktree creation fails on a symlinked path
  • Git LFS files are pointer files in a worktree Claude Code created
  • Claude Code refuses to use a worktree
  • The session resumes outside its worktree
• See also

​

MCP

​

mcp-quickstart

• Before you begin
• Add and verify a server
• Where servers are saved
  • Find your configuration on disk
• Change server scope
  • Use a server in all your projects
  • Share a server with your team
• Additional MCP server examples
  • Add a local server
  • Connect a server that requires sign-in
• Edit .mcp.json directly
• Connect from other surfaces
• Troubleshooting
• Next steps

​

mcp

• What you can do with MCP
• Find and build MCP servers
• Installing MCP servers
  • Option 1: Add a remote HTTP server
  • Option 2: Add a remote SSE server
  • Option 3: Add a local stdio server
  • Option 4: Add a remote WebSocket server
  • Add a server from setup instructions written for another client
    • From a URL
    • From an npx, uvx, or binary command
    • From an mcpServers JSON block
  • Managing your servers
    • Server status
    • Project server approvals and workspace trust
    • Server status detail
    • Configuration warnings
    • Tool availability
  • Disable a server without removing it
  • MCP client runtimes
  • Dynamic tool updates
    • Notification streams on the v2 runtime
  • Automatic reconnection
    • Mid-session drops of a remote server
    • Failed first connections
    • Failed discovery requests
    • How Claude learns that a server failed
  • Push messages with channels
  • Automatic backgrounding of long tool calls
  • Plugin-provided MCP servers
• MCP installation scopes
  • Local scope
  • Project scope
  • User scope
  • Scope hierarchy and precedence
  • Environment variable expansion in .mcp.json
    • Supported syntax
    • Expansion locations
    • Example with variable expansion
    • Unset variables without a default
    • Credential variables that read as empty
    • How references appear in /mcp and CLI output
• Practical examples
  • Example: Connect to GitHub for code reviews
  • Example: Query your PostgreSQL database
• Authenticate with remote MCP servers
  • Authenticate from the command line
  • Use a fixed OAuth callback port
  • Use pre-configured OAuth credentials
  • Override OAuth metadata discovery
  • Restrict OAuth scopes
  • Use dynamic headers for custom authentication
    • Where the helper runs
    • Which variables a helper can read
    • Trust a folder before its headersHelper runs
• Add MCP servers from JSON configuration
• Import MCP servers from Claude Desktop
• Use MCP servers from claude.ai
  • How connectors reach Claude Code
  • Organization controls on connector tools
  • Disable claude.ai connectors
• Use Claude Code as an MCP server
• MCP output limits and warnings
  • Raise the limit for a specific tool
  • Images in tool results
• Tool input schemas with a root-level combinator
• Tools with invalid input schemas
• Require approval for a specific tool
• Respond to MCP elicitation requests
• Use MCP resources
  • Reference MCP resources
• Scale with MCP tool search
  • For MCP server authors
  • Configure tool search
  • Exempt a server from deferral
• Use MCP prompts as commands
  • Execute MCP prompts
• Managed MCP configuration

​

Skills

​

skills

• Bundled skills
  • Run and verify your app
  • Work on Claude API projects
• Getting started
  • Create your first skill
• Choose where skills load
  • Load skills in monorepos and subdirectories
  • Load skills from a directory outside the project
  • Resolve skills that share a name
  • Use skills in Cowork and cloud sessions
  • Skills synced from claude.ai
    • Where synced skills load
    • When a synced skill name matches another command
    • Names reserved for synced skills
    • How Claude Code handles the frontmatter of a synced skill
    • How Claude Code handles the body of a synced skill
  • Edit a skill during a session
  • Remove a skill
• Configure skills
  • Types of skill content
  • Frontmatter reference
    • Using skill frontmatter outside Claude Code
    • How a skill gets its command name
    • Available string substitutions
  • Add supporting files
  • Control who invokes a skill
  • Skill content lifecycle
  • Pre-approve tools for a skill
  • Pass arguments to skills
• Advanced patterns
  • Inject dynamic context
    • How injected commands run
    • When an injected command fails
    • Permission checks on injected commands
  • Run skills in a subagent
    • Example: Research skill using Explore agent
  • Restrict Claude’s skill access
  • Override skill visibility from settings
  • Find unused skills
• Evaluate and iterate on a skill
  • Run evals with skill-creator
• Share skills
  • Generate visual output
• Troubleshooting
  • Skill not triggering
  • Skill triggers too often
  • Skill descriptions are cut short
  • Personal skills disappeared
• Related resources

​

Artifacts

​

artifacts

• When to use an artifact
  • What an artifact is not
• Create an artifact
• Update an artifact
• Find an artifact again
• Share an artifact
  • Let someone edit with you
• Read an artifact shared with you
• Collect comments on an artifact
  • Let Claude reply to comments on its own
• Pull live data with MCP connectors
  • How connector calls work for viewers
  • The page shows no live data for a viewer
• Offer a file download
• What you can build
  • Walk through a change
  • Compare alternatives
  • Tune with interactive controls
  • Bring the result back to your session
  • Track work in progress
• Improve the visual design
• Start from a Slides, Design, or Docs template
  • Make a slide deck
  • Draft a design canvas
  • Write a document with Claude Docs
• Page constraints
• Availability
• Disable artifacts
• Manage artifacts for your organization
  • Enable or disable artifacts
  • Control connector calls from artifacts
  • Control public sharing
  • Set a retention policy
  • Review the audit log
  • Allowlist the viewer domain
  • List and delete artifacts with the Compliance API
• Related resources

​

Automation

​

hooks-guide

• Set up your first hook
• What you can automate
  • Get notified when Claude needs input
  • Auto-format code after edits
  • Block edits to protected files
  • Re-inject context after compaction
  • Audit configuration changes
  • Reload environment when directory or files change
  • Auto-approve specific permission prompts
• How hooks work
  • Combine results from multiple hooks
  • Read input and return output
    • Hook input
    • Hook output
    • Structured JSON output
  • Filter hooks with matchers
    • Filter by tool name and arguments with the if field
  • Configure hook location
• Prompt-based hooks
• Agent-based hooks
• HTTP hooks
• Limitations and troubleshooting
  • Limitations
  • Hooks and permission modes
  • Hook not firing
  • Hook error in output
  • /hooks shows no hooks configured
  • Stop hook hits the block cap
  • Hook JSON has no effect
  • Debug techniques
• Learn more

​

channels

• Supported channels
• Quickstart
• Security
• Enterprise controls
  • Enable channels for your organization
  • Restrict which channel plugins can run
• Research preview
• How channels compare
• Next steps

​

scheduled-tasks

• Compare scheduling options
• Run a prompt repeatedly with /loop
  • Run on a fixed interval
  • Let Claude choose the interval
  • Run the built-in maintenance prompt
  • Customize the default prompt with loop.md
  • Stop a loop
• Set a one-time reminder
• Manage scheduled tasks
• How scheduled tasks run
  • Jitter
  • Seven-day expiry
• Cron expression reference
• Disable scheduled tasks
• Limitations

​

goal

• Compare ways to keep a session running
• Use /goal
  • Set a goal
  • Write an effective condition
  • Check status
  • Clear a goal
  • Resume with an active goal
  • Run non-interactively
• How evaluation works
  • When a turn fails
    • Errors you have to fix clear the goal
    • Other errors retry or pause the goal
  • Background work defers evaluation
  • Evaluation model and cost
• Requirements
• See also

​

headless

• Basic usage
  • Start faster with bare mode
  • Background tasks at exit
  • Stop a run with SIGTERM
  • If the working directory is deleted
• Examples
  • Pipe data through Claude
  • Add Claude to a build script
  • Get structured output
  • Stream responses
    • Follow subagent messages
    • Handle API retries
    • Read session metadata
    • Fail CI when a plugin or MCP server doesn’t load
    • Track plugin installs
  • Auto-approve tools
  • Turn off permission prompts in unattended runs
  • Create a commit
  • Customize the system prompt
  • Continue conversations
• Next steps

​

deep-links

• How deep links work
  • What a launched session shows
• Build a link
  • Choose between cwd and repo
• Examples
  • Embed a link in a runbook
  • Open a link from the shell
• Registration and supported platforms
• Open a VS Code tab instead of a terminal
• Troubleshooting
  • Clicking the link does nothing
  • xdg-open is not found on Linux
  • The link renders as plain text instead of being clickable
  • The session opens in my home directory instead of the repo
  • The link opens the wrong terminal
• Learn more

​

Guides

​

large-codebases

• What this guide covers
  • Settings on this page
  • The example monorepo
• Choose where to start Claude
• Layer CLAUDE.md files by directory
  • Choose between per-directory CLAUDE.md and path-scoped rules
  • Exclude irrelevant CLAUDE.md files
• Reduce what Claude reads
  • Block reads of generated and vendored code
  • Reduce file reads with code intelligence
• Scope worktrees and file access
  • Check out only the directories you need
  • Grant access across packages or repositories
• Add per-directory skills
  • Keep skills discoverable
• Centralize conventions when layering stops scaling
  • Recommend the right plugin at session start
• Put it together
• Scope and plan changes that span packages
• Next steps

​

Troubleshooting

​

troubleshoot-install

• Find your error
• Run diagnostic checks
  • Check network connectivity
  • Verify your PATH
  • Check for conflicting installations
  • Check directory permissions
  • Verify the binary works
• Common installation issues
  • Install script returns HTML instead of a shell script
  • command not found: claude after installation
  • curl: (56) Failure writing output to destination
  • Homebrew cask unavailable or outdated
  • TLS or SSL connection errors
  • Failed to fetch version from downloads.claude.ai
  • Wrong install command on Windows
  • running scripts is disabled on this system
  • The process cannot access the file during Windows install
  • claude.exe missing after an update on Windows
  • Install killed on low-memory Linux servers
  • Install hangs in Docker
  • Raw mode is not supported during install
  • claude update or claude doctor hangs
  • Claude Desktop overrides the claude command on Windows
  • Claude Code on Windows requires either Git for Windows (for bash) or PowerShell
  • Claude Code does not support 32-bit Windows
  • Linux musl or glibc binary mismatch
  • Illegal instruction
  • dyld: cannot load on macOS
  • Exec format error on WSL1
  • npm install errors in WSL
  • Permission errors during installation
  • Native binary not found after npm install
  • npm ENOTEMPTY error during update or reinstall
• Login and authentication
  • Reset your login
  • OAuth error: Invalid code
  • 403 Forbidden after login
  • Claude Code access has not been granted for this account
  • This organization has been disabled with an active subscription
  • OAuth login fails in WSL2, SSH, or containers
  • Not logged in or token expired
  • Bedrock, Agent Platform, or Foundry credentials not loading
• Still stuck

​

troubleshooting

• Performance and stability
  • High CPU or memory usage
  • Large tables are cut off in the terminal
  • Auto-compaction stops with a thrashing error
  • Command hangs or freezes
  • Garbled or corrupted text in an editor’s integrated terminal
  • Mouse wheel scrolls one line at a time in fullscreen rendering
  • Clipboard commands such as pbcopy fail inside the sandbox
  • Copied text doesn’t reach your local clipboard over SSH
  • Search and discovery issues
  • Slow or incomplete search results on WSL
• Get more help

​

debug-your-config

• See what loaded into context
• Check resolved settings
• Check MCP servers
• Check hooks
• Test against a clean configuration
• Check common causes
• Related resources

​

errors

• Find your error
• Automatic retries
  • What you see while Claude Code retries or waits
  • Tune retry behavior
• Server errors
  • API Error: 500 Internal server error
  • API Error: Repeated 529 Overloaded errors
  • Request timed out
  • No response from API
  • The response above may be incomplete
  • Auto mode cannot determine the safety of an action
  • The server returned no safety verdict
  • Agent terminated early due to an API error
• Usage limits
  • You’ve hit your session limit
  • Usage credits required for 1M context
  • The prompt to confirm went unanswered
  • Server is temporarily limiting requests
  • Request rejected (429)
  • You’ve hit your monthly spend limit
  • Spend limit reached
  • Credit balance is too low
  • Could not update your spend limit
• Authentication errors
  • Not logged in
  • Could not resolve authentication method
  • Invalid API key
  • Your apiKeyHelper script is failing
  • Invalid request header value
  • This organization has been disabled
  • Your organization has disabled API key authentication
  • Your organization has disabled Claude subscription access
  • Routines are disabled by your organization’s policy
  • Remote Control requires the Anthropic API
  • Remote Control couldn’t refresh your login
  • Remote Control stopped because the signed-in account changed
  • Remote Control stopped because the app running the session signed out or switched accounts
  • OAuth token revoked or expired
  • API Error: 401 Invalid authentication credentials
  • Login expired
  • Could not refresh your login because another Claude Code process is refreshing it
  • Couldn’t save your login
  • Failed to start OAuth callback server
  • Claude login not accepted
  • Artifacts need a claude.ai login
  • Administrator policy requires a Cloud gateway sign-in
  • Your account is on hold
  • Anthropic profile login expired
  • OAuth scope requirement
  • claude.ai rejected the session token
  • MCP server needs you to sign in again
  • MCP server URL is missing or not a valid URL
  • Issuer mismatch in authorization response
  • Refusing to send credentials to non-https token endpoint
  • AWS credentials expired or invalid
  • AWS authentication failed
  • Google Cloud credentials expired or invalid
  • Google Cloud authentication failed
  • Microsoft Foundry authentication failed
  • Could not load AWS or Google Cloud credentials
  • AWS default-chain credential resolve timed out
  • Bedrock setup verification timed out waiting for AWS
  • Cloud gateway session expired
  • Sign-in timed out while waiting for you to continue
  • Gateway refused the request
• Network and connection errors
  • Unable to connect to API
  • Unable to connect to Anthropic services
  • Socket is closed
  • API returned an empty or malformed response
  • Streaming response ended before any complete data was received
  • Bedrock streaming response has an unexpected content-type
  • SSL certificate errors
  • Host not allowed in a cloud session
  • The proxy refused the connection
  • The cloud environments service returned an empty or unexpected response
  • Couldn’t reconnect to your Remote Control session
  • Sessions ended while this machine was offline
  • Couldn’t share the transcript
  • Couldn’t send feedback
• Request errors
  • Prompt is too long
  • Context exceeds the token limit
  • Request too large
  • Image was too large
  • Unable to resize image
  • PDF errors
  • Extra inputs are not permitted
  • Tool input schema is invalid
  • tool_use.name over 200 characters
  • There’s an issue with the selected model
  • Model is not a recognized model id
  • Model not found
  • Couldn’t confirm model with the API
  • API error when checking the picked model
  • Claude Opus is not available with the Claude Pro plan
  • Claude Code does not support this model
  • Model is restricted by your organization’s settings
  • Can’t switch to the default model
  • Model switch was blocked by a PreModelSwitch hook
  • Couldn’t save it as your default
  • thinking.type.enabled is not supported for this model
  • Effort isn’t available with thinking turned off
  • Thinking budget exceeds output limit
  • Tool use or thinking block mismatch
  • Invalid data in redacted_thinking block
  • Unsupported tool content removed
  • role ‘system’ must precede an ‘assistant’ message
  • Invalid encrypted_content in search_result block
  • Usage Policy refusal
  • Safety measures flagged a cybersecurity topic
• Installation errors
  • Installation was killed before it could finish
  • The connection dropped while downloading the update
• Command-line errors
  • Conflict between --bg and --print
  • Invalid --agents configuration
  • Cloud sessions cannot be created from a --restricted session
  • Cloud sessions are disabled by your organization’s policy
  • The --json-schema value is not a valid JSON Schema
  • Settings file exceeds the 2MiB limit
  • The current directory no longer exists
  • Temp directory refused or cannot be created
  • Directory couldn’t be resolved to a real location
  • Workspace not trusted when starting Remote Control
  • Not carried over to the sessions Remote Control starts
  • claude import is not yet available in this build
  • Could not read Claude Code config
  • Could not import a server from Claude Desktop
  • Cannot add MCP server to the managed scope
  • Can’t read .mcp.json
  • MCP server was not saved or removed
  • MCP server may not have been saved or removed
  • Server is Anthropic-hosted and doesn’t support local OAuth
  • Server rejected the Authorization header minted by the configured headersHelper
  • MCP permission prompt tool not found
  • OAuth callback port is already in use
  • No available ports for OAuth redirect
  • /security-review fails without origin/HEAD
  • Input must be provided when using --print
  • Input contained only whitespace
  • stream-json input carried over 256M characters with no newline
  • Unknown command
  • Diff is too large for ultrareview
  • Could not find merge-base with the base branch
  • Your checkout has no branches
  • No GitHub account is connected to your Claude account
  • Your connected GitHub account can’t see the repository
  • The GitHub App preflight failed transiently
  • The repository upload can’t follow a git setting
  • GitHub isn’t connected to your Claude account
  • Single sign-on authorization needed
  • Failed to resume the conversation
  • No conversation found with the session ID
  • Windows reported an error (EBADF) when Claude Code read this session’s transcript file
  • Cannot switch renderers in this session
  • Couldn’t open Claude Desktop
  • /terminal-setup left your Zed keymap unchanged
  • Skill usage reports are not available on this connection
  • Custom output styles can’t be selected over Remote Control
  • Output styles are saved to local settings which this session doesn’t load
• Plugin errors
  • plugin eval is currently in early access
  • Marketplace is registered from an untrusted source
  • Marketplace name is another spelling of a reserved name
  • Claude Code refuses the marketplace name
  • Marketplace is already added from a different source
  • Plugin command references user_config in a shell command
  • Plugin archive integrity check failed
  • Path escapes plugin directory
  • Path could not be checked
  • Marketplace entry path does not stay inside the marketplace directory
  • Failed to load marketplace configuration
  • Plugin is required by your organization
  • Plugin was not uninstalled
• Tool errors
  • Agent would be spawned with zero tools
  • File is covered by a Read deny rule
  • Path cannot contain null bytes
  • subagent_type is required
  • Memory index is over its read limit
  • pkill pattern matches the Claude Code process
  • Failed to write to a teammate’s inbox
  • Teammate’s agent definition was not restored
  • Message too large for cross-session delivery
  • Too many messages to this session just now
  • Cross-session message was dropped at the recipient session’s inbox
  • Refusing to send a cross-session message
  • Refusing to read, write, or search a path
  • Task output swap refused
  • Disk quota or temp filesystem is full
  • The source file is not valid UTF-8 text
  • Reading a local file from outside the connected folders in a Cowork session
  • WebFetch cannot fetch localhost
• Background session errors
  • Commands refused in a background session
  • Write or command blocked because the path cannot be safely resolved
  • Write or command blocked because the path names a network location
  • Command blocked by the worktree isolation checks
  • This session has no saved transcript
  • This session is running in another terminal
  • This session’s saved conversation is no longer on disk
  • Worktree has commits that are not pushed anywhere
  • Terminal host process died
  • Session isn’t responding
  • Session was stopped while the respawn was in flight
  • Session agent no longer available
  • CLAUDE_CODE_PROCESS_WRAPPER launcher errors
  • EUNKNOWN when starting a background session
  • EACCES when starting a background session
  • Background service exited before it became reachable
  • Working directory no longer exists when starting a background session
  • Workspace not trusted when dispatching a background session
• Wrapper and IDE errors
  • Claude Code process exited with code N
  • Could not locate the Claude CLI on PATH
  • The connection to Claude Code ended before this message completed
• Rewind warnings and errors
  • Restored the code, but skipped files
  • No files were restored
• Session saving warnings
  • Transcript writes are failing
  • Transcript saving is off because CLAUDE_CODE_SKIP_PROMPT_HISTORY is set
  • Transcript saving is off because of an inherited CLAUDE_CODE_CHILD_SESSION marker
• Configuration warnings
  • Fullscreen renderer didn’t finish starting
  • Claude Code exited after an unrecoverable interface error
  • Agent descriptions are over the 15.0k-token limit
  • A skill, command, or workflow wasn’t loaded because its name is reserved
  • Workspace has not been trusted
  • Working directory is a network path
  • Remote managed settings failed to load
  • Managed settings were not approved
  • Managed settings block the default model
  • MCP server is blocked by enterprise managed policy
  • Managed settings document could not be parsed
  • otelHeadersHelper failed
  • headersHelper not run
  • Malformed Tool(content) rule
  • Is not matched by file permission checks
  • Has a wildcard before the rest of the command
  • crossSessionInbound must be one of accept, hold, refuse
  • The 200K limit isn’t enforced
  • Unrecognized model ID on a request
  • Stale sandbox mask files left by a killed session
• Responses seem lower quality than usual
• Report an error

​

Plugins

​

overview

• Understand what a plugin is
  • Decide whether you need a plugin
  • What an enabled plugin adds to your sessions
• Get plugins from a marketplace
  • Make an installed plugin available in your session
• Tell Anthropic’s marketplaces from third-party ones
• Understand install scopes
• Next steps

​

Use plugins

​

install

• Install a plugin
  • Choose an install scope
  • JetBrains, non-interactive runs, and the Agent SDK
  • Plugins from your claude.ai account
  • Install from your shell
• Add a marketplace
  • Add a marketplace and install in one command
  • Add a private marketplace
  • Add a marketplace from claude.ai
• Manage installed plugins
  • Manage plugins synced from claude.ai
  • Uninstall a plugin the project enables
  • See what an installed plugin adds to your sessions
  • Find plugins you no longer use
  • Plugins with dependencies
  • Manage plugins from your shell
• Keep plugins updated
  • Turn auto-update on or off for a marketplace
  • Update one plugin now
  • Auto-update from a private marketplace
• Manage marketplaces
• Next steps

​

anthropic-marketplaces

• Anthropic’s marketplaces
  • The demo marketplace in anthropics/claude-code
• Find plugins in the official marketplace
• Browse and install from Anthropic’s marketplaces
  • Add the community or demo marketplace
• Third-party marketplaces
• Next steps

​

code-intelligence

• Install a code intelligence plugin
• See what Claude gains
  • Read the diagnostics yourself
• Accept or dismiss the recommendation dialog
  • When the recommendation dialog appears
  • Respond to the recommendation dialog
  • Turn recommendations back on
• Troubleshoot code intelligence
• Add a language without an official plugin
• Next steps

​

security

• Understand what a plugin can do
• Identify Anthropic’s marketplaces by name
  • Official marketplace names
• Review a plugin before you install
  • Remove a plugin you no longer trust
• Recognize when Claude Code refuses or warns
  • Trust warning before you install
  • Untrusted marketplace sources and failed integrity checks
• Enforce plugin controls for your organization
• Find plugins in telemetry
• Next steps

​

Create plugins

​

create

• Decide when to use a plugin
• Create your first plugin
  • Share your plugin
  • Plugin layout
• Develop without a marketplace
  • Load a plugin for one session
    • From a directory or .zip
    • From a folder of plugins
    • From a URL
    • From an environment variable
  • Make a plugin load in every session
    • Scaffold the plugin with claude plugin init
    • Name the plugin’s skills
    • Stop loading the plugin
    • Share the plugin through a repository
• Test and debug
  • A component path isn’t found
  • --plugin-dir at a marketplace root doesn’t load the plugins under plugins/
  • The plugin loads but its skills are missing
  • The userConfig dialog never appears
  • Check that the plugin changes Claude’s behavior
• Convert an existing .claude/ setup
• Next steps

​

components

• Explore the plugin directory
• Add each kind of component
  • Skills
  • Commands
    • Define commands in the manifest
  • Agents
    • Organize agents in subfolders
    • Frontmatter fields in plugin agents
  • Hooks
    • When plugin hooks fire
    • Environment, quoting, and matching MCP tools
  • MCP servers
    • Reach users on claude.ai and Cowork
    • Server names, tool names, and reloads
    • Include a packaged MCPB server
  • LSP servers
  • Executables
  • Default settings
  • Themes and output styles
  • Channels
  • Monitors
• Ask the user for configuration values
  • When the configuration dialog appears
• Reference plugin paths and store data
  • Install dependencies into the data directory
• Next steps

​

dependencies

• Declare dependencies
  • Declare a dependency with a version constraint
  • Bundle plugins for a team
  • Depend on a plugin from another marketplace
  • Test a plugin and its dependency locally
• Release a plugin that others depend on
  • Create a release tag
  • Constrain a dependency that has a non-git source
• How dependencies behave for your users
  • How a constraint resolves against tags
  • Confirm the resolved version
  • Combine constraints from several plugins
• See also

​

plugin-evals

• Requirements
• How an eval run works
  • What happens in a run
  • How a case is scored
  • The no-plugin baseline
• Create your first eval suite
• Write and refine cases
  • Write a case manually
  • Set run limits and tools in prompt.md
  • Choose and weight graders
    • Choose graders that give a stable signal
  • Score against the no-plugin baseline
  • Use a different eval directory
• Set up fixtures and mocks
  • Seed the workspace or conversation
  • Mock MCP servers
    • Replay agent mock answers
• Run evals
  • Choose what to evaluate
  • Grant tools
  • Command options
  • Run evals in CI
• Read the results
  • HTML report
  • JSON result
• What a run can access
  • Trust the plugin directory
  • How runs are isolated
• Eval suite reference
  • prompt.md frontmatter
  • case.yaml fields
  • Grader frontmatter
    • What a grader can look at
    • Grader types
  • Mock files
• Troubleshooting
  • “plugin eval is currently in early access”
  • “plugin eval is currently unavailable”
  • “is not a trusted plugin directory, and this run cannot stop to ask you about it”
  • “is too old for claude plugin eval”
  • “No eval cases found”
  • The baseline arm shows no plugin, or delta is zero
  • “Agent type ’…’ not found” for one of your plugin’s agents
  • Everything scores zero although the right files were produced
  • A regex over the trace doesn’t match text I can see
  • Tools are denied, MCP tools are missing, or Bash won’t run
  • The run exits 1 but the results look fine
  • --json output path must end in .json
  • A grader shows passed: false under a run that scored 1.0
  • Runs fail with a usage-limit or rate-limit error partway through
  • Runs time out or hit the turn cap
• See also

​

publish

• Choose how to distribute
• Prepare your plugin for release
• Share a plugin without a marketplace
  • Ship a plugin with your own tool
• Publish through your own marketplace
  • Add the marketplace file to your repository
  • Control who can install
  • Tell users how to install
  • Ship updates to users
• Submit to Anthropic’s directory
  • How a listed plugin reaches Claude Code users
• Ship updates, renames, and removals
  • Release a new version
  • Tag a release
  • Rename or remove a plugin
• Declare dependencies
• Next steps

​

measure

• Measure what a plugin costs
  • Lower the always-on figure
  • Cost shown to users before install
• Check whether a plugin is used
  • Not used recently in /plugin
  • Find skills that never run
  • Unused plugins in /doctor
  • Usage share in /usage
• Measure across a fleet
  • OpenTelemetry events for plugin installs and use
  • Redacted plugin names in your backend
  • Query the Analytics API
• Next steps

​

cli-hints

• Emit the hint
• Hint format
• Check when the prompt appears
• Preview what the user sees
• Next steps

​

Run a marketplace

​

create-marketplace

• Create a marketplace
• Add plugin entries
• Rules for plugin entries
  • Write relative paths from the marketplace root
  • Keep the entry name and the manifest name the same
• Choose a plugin source
• Validate and test
  • Problems that validation reports
  • Problems that surface when you add or install
  • Test an edit to a plugin
  • Remove the marketplace to start over
• Host your marketplace
• Next steps

​

host-marketplace

• Host your marketplace
  • Register the marketplace for everyone in a repository
  • Avoid relative-path entries in a URL-hosted marketplace
  • Stay within the download limits for hosted files
  • Edit plugins in place on a shared directory
  • Keep plugin files out of Git LFS
  • Share files within a marketplace with symlinks
• Distribute through organization settings
• Grant access to a private marketplace
  • Serve users who have no git-host account
  • What background auto-update does with credentials
• Roll out to a whole company
• Keep users up to date
  • Turn on auto-update
  • Release a new version
  • Hold users on one version
  • Change the command of a command source
• Run release channels
• Rename or remove a plugin
  • Migrate users with a renames map
  • Uninstall removed plugins from users’ machines
• Authenticate archive downloads
  • Add a headersHelper to a plugin entry
  • Write the headersHelper command
  • When Claude Code skips a headersHelper command or drops its output
  • How users accept a headersHelper command
  • Installs and updates that refuse a command instead of asking
  • When a marketplace url source’s command runs
• Depend on and recommend other plugins
• Work around what a marketplace can’t do
• Next steps

​

relevance

• Understand how plugin relevance works
• Add relevance to a plugin entry
• Field reference
  • relevance
  • relevance.signals
    • Working directory matching
    • Command name matching
    • Manifest dependency matching
• Validate your marketplace
• Enable suggestions in managed settings
• Preview what the user sees
• See also

​

Manage plugins for your organization

​

org

• Pre-install and require plugins
  • Choose a delivery mechanism
    • Which managed source applies on a machine
  • Require a marketplace and its plugins
  • Require plugins per repository
  • When each surface applies the plugin keys
  • Confirm the rollout
• Seed containers and CI
• Restrict what users can install
  • Control matrix
    • Aliases for the marketplace keys
  • Allowlist with strictKnownMarketplaces
    • How entries match
    • Keep skills-directory plugins loading
    • Marketplaces hosted on claude.ai
    • Lock every source out
  • Blocklist with blockedMarketplaces
  • Allow the official marketplace and your own
• Set update policy
  • Turn auto-update on or off per marketplace
  • Turn updates off for the whole fleet
  • Assign release channels to user groups
• Recommend plugins
• Audit and review
  • OpenTelemetry events
  • Analytics API
• Plan for what managed settings can’t enforce
• Troubleshoot policy
• Next steps

​

Troubleshooting

​

troubleshooting

• Find where /plugin runs
  • /plugin isn't available in this environment
  • zsh: no such file or directory: /plugin
  • The term '/plugin' is not recognized as the name of a cmdlet
  • claude: command not found after claude plugin ...
  • Unknown command and command spellings that don’t exist
• Add a marketplace
  • Marketplace "claude-plugins-official" not found
  • Marketplace "<name>" not found
  • Invalid marketplace source format
  • '<source>' is not a valid GitHub owner/repo shorthand
  • Path does not exist: <path>
  • Marketplace file not found at <path>/.claude-plugin/marketplace.json
  • SSH authentication failed or HTTPS authentication failed
  • SSH host key is not in your known_hosts file
  • Command 'git' not found or is in an unsafe location
  • Git clone timed out after 120s
  • Marketplace updates keep failing offline
  • Marketplace add fails on a GitHub Enterprise Server host
• Install a plugin
  • Plugin "<name>" not found in marketplace "<marketplace>"
    • not found in marketplace with a refresh hint
    • not found in marketplace with no hint
  • Plugin "<name>" not found in any marketplace
  • Plugin '<name>@<marketplace>' is already installed globally
  • This plugin uses a source type your Claude Code version does not support
  • Plugin archive integrity check failed
  • Marketplace "<name>" is registered from an untrusted source
  • Plugin <name> has a corrupt manifest file or has an invalid manifest file
  • Plugin directory not found at path: <path>
  • No plugins available or No marketplaces configured
  • Marketplace "<name>" is already added from a different source
  • Cannot add marketplace "<name>": its network source differs from the one declared for it in settings
  • Failed to install: <plugin> (<reason>)
  • Could not move the new copy of this plugin version into <path>
  • Dependency errors
• Plugin installed but not working
  • Plugin doesn’t appear or its skills don’t show up
  • Run /reload-plugins to activate.
  • Plugin "<name>" not cached at <path>
  • installed_plugins.json holds a record under "<id>" that this version of Claude Code cannot read
  • installed_plugins.json could not be read and was rebuilt
  • install records under names that no version of Claude Code can use were removed from installed_plugins.json
  • Disabled in ~/.claude/settings.json but still loads
  • Plugin "<name>" is enabled in project settings but isn't installed here
  • Failed to load hooks from <path> and hooks that don’t fire
    • Hooks fail to load
    • hook error notices in the transcript
    • A plugin hook blocks a tool call or prompt
    • Hook loads but never fires
  • Invalid MCP server config for "<server>" and MCP servers that don’t start
    • Invalid MCP server config for "<server>": <error>
    • Server is configured but never connects
    • Server works with --plugin-dir but fails after install
  • Language server doesn’t start, uses too much memory, or reports wrong diagnostics
    • Language server doesn’t start
    • Language server uses too much memory
    • False positive diagnostics in a monorepo
• Build a plugin
  • commands path not found: <path>
  • --plugin-dir at a marketplace root doesn’t load the plugins under plugins/
  • Files the plugin references outside its directory aren’t found
  • ${CLAUDE_PLUGIN_ROOT} shows forward slashes on Windows
  • Plugin loads but its skills are missing
  • Skill loads but Claude never invokes the skill
  • <directory> is not a plugin or skill folder from claude plugin eval init
  • The userConfig dialog never appears
  • claude plugin validate reports errors
  • Plugin <name> has conflicting manifests
  • Warning: No commands found in plugin <name> custom directory
• Host a marketplace
  • Plugins with relative paths fail in URL-based marketplaces
  • Marketplace validation errors
• Blocked by your organization
  • Marketplace source '<source>' is blocked by enterprise policy
  • Marketplace "<name>" is not in the allowed marketplace list
  • Plugin "<name>" is blocked by your organization's policy and cannot be installed
  • --plugin-dir is disabled by your organization's managed settings (disableSideloadFlags)
  • Plugins from ~/.claude/skills/ are blocked by your organization's managed settings
  • Command-sourced plugins are disabled by your organization's managed settings
  • Marketplace '<name>' is seed-managed
• Next steps

​

loading

• Check which stage a plugin reached
  • Plugins and marketplaces that aren’t on disk at session start
• Find where a plugin came from
  • Entry name and manifest name
  • Plugins shared through a repository
  • Plugins synced from claude.ai
    • Sync timing in terminal sessions
    • Sign-in requirements for terminal sync
    • Control which synced plugins load
• Find where a plugin is enabled
  • Disabled in user settings but still loads
  • Enabled in project settings but not installed
• Find plugins on disk
  • In-place and copied plugins
  • Paths that escape the plugin directory
  • Cleanup of previous versions
  • Node.js package dependencies
    • When the dependency install runs
    • Limits on the dependency install
    • When the dependency install fails or is skipped
• Versions and updates
  • How Claude Code computes the version
  • When Claude Code refreshes a marketplace before an install
  • When auto-update runs
    • Which marketplaces and plugins auto-update
  • When a command source re-runs
• Name conflicts
  • Keep a session-only plugin from loading
• Next steps

​

Reference

​

manifest-reference

• Manifest file
  • Unrecognized fields
  • Validate the manifest
• Fields
  • name
  • displayName
  • version
  • metadata
  • defaultEnabled
  • dependencies
  • settings
• Component path forms
  • Path-only fields
  • commands
  • hooks
  • mcpServers
  • lspServers
  • monitors
• Path rules
  • Containment and existence
  • How each key combines with its default location
• User configuration
  • Limit a field to fixed options
  • Where values are stored
  • Reference a saved value
  • Fields that run through a shell
• Channels
• Environment variables
  • Where each variable resolves
  • Quoting and path separators
• Standard layout
• Marketplace entries and the manifest
  • How entry fields combine with plugin.json
  • Metadata precedence
• Next steps

​

marketplace-reference

• Marketplace file
  • Reserved names
• Top-level fields
• Plugin entries
  • How an entry combines with plugin.json
    • Hooks in an entry
    • Display fields
  • Strict mode
• Plugin sources
  • Relative path plugin source
    • Bare names under pluginRoot
  • github plugin source
  • url plugin source
  • git-subdir plugin source
  • npm plugin source
  • archive plugin source
  • command plugin source
    • What the command must do
    • Output that fails the install or update
    • Copy mode and link mode
• Marketplace sources
  • Fields by type
  • Source values valid only in policy lists
  • Source objects in settings
• Validation messages
  • Invalid input on a source
  • Failures that validation doesn’t catch
• Next steps

​

cli-reference

• claude plugin commands
  • plugin init
  • plugin install
    • JSON result format
    • Accept a displayed install command
  • plugin uninstall
    • What an uninstall deletes and keeps
  • plugin enable
  • plugin disable
  • plugin update
  • plugin list
    • JSON output
  • plugin details
  • plugin prune
  • plugin eval
  • plugin eval init
  • plugin tag
  • plugin validate
    • Validate a directory
    • Output and exit codes
• claude plugin marketplace commands
  • plugin marketplace add
  • plugin marketplace list
  • plugin marketplace remove
  • plugin marketplace update
• /plugin in a session
• /reload-plugins
  • Reload summary
  • Reloads that change MCP tools
  • Sessions without an interactive terminal
• Flags that load a plugin for one session
• Next steps

​

Setup and access

​

admin-setup

• Choose your API provider
• Decide how settings reach devices
  • WSL sessions in Claude Code Desktop
• Decide what to enforce
• Set up usage visibility
• Review data handling
• Verify and onboard
• Next steps

​

setup

• System requirements
  • Additional dependencies
• Install Claude Code
  • Set up on Windows
  • Alpine Linux and musl-based distributions
• Verify your installation
• Authenticate
• Update Claude Code
  • Auto-updates
  • Configure release channel
  • Pin a minimum version
  • Disable auto-updates
  • Update manually
• Advanced installation options
  • Install a specific version
  • Install with Linux package managers
  • Install with npm
  • Binary integrity and code signing
    • Verify the manifest signature
    • Platform code signatures
• Uninstall Claude Code
  • Native installation
  • Homebrew installation
  • WinGet installation
  • apt / dnf / apk
  • npm
  • Remove configuration files

​

authentication

• Log in to Claude Code
  • Log in with multiple accounts
• Set up team authentication
  • Claude for Teams or Enterprise
  • Claude Console authentication
    • Sign in without an API key
  • Cloud provider authentication
  • Restrict login to your organization
• Credential management
  • Renew an expiring login
  • Authentication precedence
    • Anthropic profiles and federation credentials
  • Generate a long-lived token

​

managed-settings

• Deploy a managed settings file
• Choose a delivery mechanism
  • Where and when a policy applies
  • Where each mechanism stores the policy
  • Split a file-based policy across teams
• How Claude Code combines managed sources
  • Keys read from every admin source
  • Compose every managed source
  • Compute the policy with a helper program
  • Let an embedding host add policy
    • Keep Cowork folder access when only managed rules apply
  • What a developer can change
• Check that a policy is in force
  • Read the source in /status
  • Find entries Claude Code dropped
    • Keys that fail closed
    • Invalid values inside sandbox
• Keys only a managed source can set
• Turn telemetry off for your organization
• See also

​

server-managed-settings

• Requirements
• Choose between server-managed and endpoint-managed settings
• Configure server-managed settings
  • Verify settings delivery
  • Access control
  • Managed-only settings
  • Current limitations
• Settings delivery
  • Settings precedence
  • Per-key exceptions across managed sources
  • Fetch and caching behavior
  • Invalid entries in delivered settings
  • Enforce fail-closed startup
  • Security approval dialogs
    • Approval memory
    • Environment variables and the approval dialog
• Platform availability
• Audit logging
• Security considerations
• See also

​

managed-mcp

• Choose a pattern
• Exclusive control with managed-mcp.json
  • Deploy managed-mcp.json
  • Authenticate with per-user credentials
  • Servers passed with --mcp-config or --strict-mcp-config
  • How allowlists and denylists apply to the managed set
  • Validate the configuration
  • Disable MCP entirely
  • Allow claude.ai connectors alongside the managed set
  • Allow Claude in Chrome alongside the managed set
• Provide servers through managed settings
  • What an entry can contain
  • How provided servers load
  • What users can see and change
  • Where managedMcpServers applies
  • When provided servers connect
• Policy-based control with allowlists and denylists
  • Match servers by URL, command, or name
  • How a server is evaluated
    • How policy entries expand
  • Example configuration
  • Restrict the allowlist to managed settings only
• How restrictions appear to users
• Monitor MCP usage
• Configuration summary
• Related resources

​

auto-mode-config

• Common boundaries
  • Add a human checkpoint
• Where the classifier reads configuration
• Define trusted infrastructure
• Generate environment entries with /auto-mode-setup
  • What /auto-mode-setup reads
  • Review and save the draft
  • Turn off /auto-mode-setup
• Override the block and allow rules
• Edit rules from /permissions
• Route all shell commands through the classifier
• Inspect the defaults and your effective config
• Review denials
  • Fix a denial with an allow rule, an environment entry, or a retry
  • Fix repeated denials
• See also

​

Deployment

​

third-party-integrations

• Compare deployment options
• Configure proxies and gateways
• Best practices for organizations
  • Invest in documentation and memory
  • Simplify deployment
  • Start with guided usage
  • Pin model versions for cloud providers
  • Configure security policies
  • Use MCP for integrations
• Next steps

​

feature-availability

• Availability by model provider
  • Features available on every provider
  • Features that require a Claude subscription
  • CLI capabilities that vary by provider
  • Admin and analytics
  • Summary by provider
• Availability by subscription plan
• Model availability
• Related resources

​

amazon-bedrock

• Prerequisites
• Sign in with Bedrock
• Set up manually
  • 1. Submit use case details
  • 2. Configure AWS credentials
    • Credential caching and resolution timeout
    • Advanced credential configuration
      • Example configuration
      • Configuration settings explained
  • 3. Configure Claude Code
  • 4. Pin model versions
    • Map each model version to an inference profile
• Startup model checks
• Cross-region inference profile prefixes
• IAM configuration
• 1M token context window
• Service tiers
• AWS Guardrails
• Use the Mantle endpoint
  • Enable Mantle
  • Select a Mantle model
  • Run Mantle alongside the Invoke API
  • Route Mantle through a gateway
  • Mantle environment variables
• Troubleshooting
  • Authentication loop with SSO and corporate proxies
  • Certificate errors behind a TLS-inspecting proxy
  • Region issues
  • Streaming errors behind a gateway or proxy
  • Zero token counts in /context
  • Mantle endpoint errors
• Additional resources

​

claude-platform-on-aws

• Prerequisites
• Setup
  • 1. Configure AWS credentials
  • 2. Configure Claude Code
  • 3. Pin model versions
  • 4. Launch and verify
• Use the Agent SDK
• Route through a corporate proxy
• Troubleshooting
  • 403 Forbidden or AccessDenied on every request
  • Requests fail with a missing-workspace error
  • Requests still go to api.anthropic.com
• Additional resources

​

google-vertex-ai

• Prerequisites
• Sign in with Agent Platform
• Region configuration
• Set up manually
  • 1. Enable Agent Platform API
  • 2. Request model access
  • 3. Configure GCP credentials
    • Advanced credential configuration
  • 4. Configure Claude Code
  • 5. Pin model versions
  • 6. Verify your configuration
• Startup model checks
• IAM configuration
• 1M token context window
• Troubleshooting
• Additional resources

​

microsoft-foundry

• Prerequisites
• Setup
  • 1. Provision Microsoft Foundry resource
  • 2. Configure Azure credentials
  • 3. Configure Claude Code
  • 4. Pin model versions
  • 5. Run Claude Code
• Azure RBAC configuration
• Troubleshooting
• Additional resources

​

network-config

• Proxy configuration
  • Environment variables
  • Basic authentication
• CA certificate store
• Custom CA certificates
• mTLS authentication
• Verify your configuration
• Apply network settings to background agents
  • Set network variables in settings, not the shell
  • Configure a corporate launcher as a setting
• Streaming idle watchdogs
• Network access requirements
  • Organization IP allowlists and proxy egress
  • GitHub allow lists and firewalls
  • Desktop and claude.ai
• Additional resources

​

corporate-launcher

• What the launcher covers
  • Processes that start outside the launcher
  • Helper process names in process monitors
• Set up the launcher
• The launcher contract
  • Format of the launcher value
• Relationship to CLAUDE_CODE_SHELL_PREFIX
• Related resources

​

devcontainer

• Add Claude Code to your dev container
• Persist authentication and settings across rebuilds
• Enforce organization policy
• Restrict network egress
• Run without permission prompts
• Try the reference container
• Next steps

​

Gateways

​

gateways

• How a gateway works
• Choose a gateway
  • Claude apps gateway
  • Other gateways
• Subscriptions and gateways
• Configure separately from the gateway
• Next steps

​

Gateways > Claude apps gateway

​

claude-apps-gateway

• Why Claude apps gateway
  • Other gateway implementations
• Quickstart
  • Prerequisites
  • Steps
• Connect developers
  • Set the gateway URL
  • Allow a gateway on public address space you own
  • Deliver policy to Claude Desktop sessions
    • Which machines need the opt-in
    • Set the opt-in
  • Restrict parent settings
    • Deploy the locks
    • Lock behavior across sources
    • Settings the locks don’t cover
  • Connect Claude Desktop
  • CI pipelines and remote machines
  • What’s enforced on developers
  • What the organization can see
• Availability and limitations
• Next steps

​

claude-apps-gateway-config

• File structure
• Secret expansion
• Required sections
  • listen
  • oidc
    • IdP requests through a forward proxy
    • Proxy-only egress
  • session
  • store
  • upstreams
    • Upstream error messages
    • Anthropic API
      • Per-user identity headers for a proxy you run
    • Amazon Bedrock
      • Apply an Amazon Bedrock guardrail
    • Claude Platform on AWS
    • Google Cloud Agent Platform
    • Microsoft Foundry
    • Static headers on upstream requests
    • Multiple upstreams
• Optional sections
  • admin
  • enforcement
  • pricing
    • Mark prices up
    • Send the rates to signed-in clients
  • models
  • managed
    • Matcher values that stop the gateway at boot
    • What goes in cli
    • MCP servers in a policy
    • Claude Desktop overlay
    • Precedence with other managed sources
  • telemetry
    • Add your own labels
    • Export directly to your collector
    • When a destination fails
  • HTTP tuning
  • load_test_mode
• Complete example
• Client-side managed settings
• Related

​

claude-apps-gateway-spend-limits

• Set a cap
  • Authenticate to the admin API
• How enforcement works
  • How requests are priced
  • Postgres availability
  • Usage warnings in Claude Code
• Admin API reference
  • /effective
  • /audit
  • Pagination
• Data lifecycle
• Related

​

claude-apps-gateway-deploy

• Identity provider setup
• Deployment
  • Container image
  • Kubernetes
  • Cloud Run
  • Push the gateway URL to developer machines
  • Large rollouts
• Operations
  • Logs
  • Health
  • Concurrent upstream requests
  • Outage behavior
    • Readiness grace period
  • JWT secret rotation
  • Postgres
  • Upgrades
• Security
  • Data flow
  • Threat model summary
  • User-code brute-force resistance
  • Compliance posture
• Troubleshooting
• Related

​

claude-apps-gateway-on-aws

• Architecture
• Prerequisites
  • Set your environment variables
• Deploy the gateway
• Terraform reference
• Troubleshooting
• Telemetry
  • Client metrics, logs, and traces
  • Gateway logs
  • Container metrics
  • Spend
• Next steps

​

claude-apps-gateway-on-gcp

• What you’ll build
• Prerequisites
• Deploy the gateway
• Terraform reference
• Troubleshooting
• Next steps

​

Gateways > Other gateways

​

llm-gateway

• What a gateway provides
• Roll out a gateway
• Subscriptions and gateways
• Related pages

​

llm-gateway-connect

• Check for an existing configuration
• Configure Claude Code yourself
  • Set the credential variable
  • Set the base URL and credential
    • Set as shell environment variables
    • Set in a settings file
  • Verify the connection
    • Confirm in Claude Code
  • How the credential variable maps to a header
  • Conflicts with an existing login
• Configure each surface
  • VS Code extension
  • Desktop app
  • GitHub Actions
  • Agent SDK
  • Slack, cloud sessions, and Remote Control
• Additional configuration
  • Send additional headers
  • Add gateway models to the model picker
  • Rotate credentials with apiKeyHelper
  • Turn off traffic outside the gateway path
  • Route to a cloud provider through a gateway
    • Amazon Bedrock
    • Google Cloud’s Agent Platform
    • Microsoft Foundry
    • Claude Platform on AWS
    • Confirm the provider route
• Troubleshoot gateway errors
• Related resources

​

llm-gateway-rollout

• Prerequisites
  • Gateway requirements
• Rollout steps
  • Confirm the gateway routes your models
  • Issue developer credentials
  • Test Claude Code against the gateway
  • Distribute the configuration
    • What to distribute
    • Distribute through managed settings
    • Hand developers the values to set themselves
  • Verify the rollout
• Maintain the gateway
  • Plan Claude Code version upgrades
• Related resources

​

llm-gateway-protocol

• API formats
  • Foundry and Claude Platform on AWS
  • Optional endpoints and startup traffic
  • Streaming
  • Format mismatch with the upstream
• How the connection method changes client behavior
  • Requests and defaults by connection method
  • Settings for unrecognized model IDs
• Request headers
  • Gateway hint headers
  • Forward as open lists
• Response headers
• System prompt attribution block
• Feature pass-through
  • Automatic retry and error forwarding
  • Disable pre-release capabilities
• Model discovery
  • When discovery runs
  • Request and response
  • Picker entries and caching
• Related resources

​

Usage and costs

​

monitoring-usage

• Quick start
• Administrator configuration
  • How managed settings lock the OTLP destination
• Configuration details
  • Common configuration variables
  • mTLS authentication
  • Metrics cardinality control
  • Traces (beta)
    • Span hierarchy
    • Span attributes
  • Dynamic headers
    • Settings configuration
    • Script requirements
    • Refresh behavior
  • Multi-team organization support
  • Example configurations
• Telemetry from cloud sessions and Claude Tag
  • Attribute telemetry to cloud sessions
• Available metrics and events
  • Standard attributes
    • Repository attributes
  • Metrics
  • Metric details
    • Session counter
    • Lines of code counter
    • Pull request counter
    • Commit counter
    • Cost counter
    • Token counter
    • Code edit tool decision counter
    • Active time counter
  • Events
    • Event correlation attributes
    • User prompt event
    • Assistant response event
    • Tool result event
    • API request event
    • API error event
    • API refusal event
    • API request body event
    • API response body event
    • Tool decision event
    • Permission mode changed event
    • Auth event
    • MCP server connection event
    • Internal error event
    • Plugin installed event
    • Plugin loaded event
    • Skill activated event
    • At mention event
    • API retries exhausted event
    • Hook registered event
    • Hook execution start event
    • Hook execution complete event
    • Hook plugin metrics event
    • Compaction event
    • Subagent completed event
    • Feedback survey event
    • Retention sweep event
    • Managed settings resolved event
• Interpret metrics and events data
  • Usage monitoring
  • Cost monitoring
  • Alerting and segmentation
  • Detect retry exhaustion
  • Event analysis
• Audit security events
  • Attribute actions to users
  • Audit MCP activity
  • Map security questions to events
  • Send events to a SIEM
• Backend considerations
  • For metrics
  • For events/logs
  • For traces
• Service information
• ROI measurement resources
• Security and privacy
• Monitor Claude Code on Amazon Bedrock

​

costs

• Track your costs
  • Using the /usage command
    • Prompt cache statistics
    • Plan usage breakdown
    • Check your usage-credits spend
    • When the usage request fails
  • Analyze your usage patterns
  • Add usage credits to your subscription
• Manage costs for your organization
  • Report spend at your contracted rates
  • Claude for Teams and Enterprise
  • Claude Console
    • Rate limit recommendations
  • Cloud providers
  • When a developer asks about a limit
  • Agent team token costs
• Reduce token usage
  • Manage context proactively
  • Choose the right model
  • Reduce MCP server overhead
  • Install code intelligence plugins for typed languages
  • Offload processing to hooks and skills
  • Move instructions from CLAUDE.md to skills
  • Adjust extended thinking
  • Delegate verbose operations to subagents
  • Manage agent team costs
  • Write specific prompts
  • Work efficiently on complex tasks
• Background token usage
• Why usage climbs in a long session
• Understanding changes in Claude Code behavior

​

analytics

• Access analytics for Team and Enterprise
  • Enable contribution metrics
  • Review summary metrics
  • Explore the charts
    • Track adoption
    • Measure PRs per user
    • View pull requests breakdown
    • Find top contributors
  • PR attribution
    • Attribution process
    • Time window
    • Excluded files
    • Attribution notes
  • Get the most from analytics
    • Monitor adoption
    • Measure ROI
    • Identify power users
    • Access data programmatically
• Access analytics for API customers
  • View team insights
• Related resources

​

Security and data

​

security

• How we approach security
  • Security foundation
  • Permission-based architecture
  • Built-in protections
  • User responsibility
• Protect against prompt injection
  • Core protections
  • Privacy safeguards
  • Additional safeguards
• MCP security
• IDE security
• Cloud execution security
• Security best practices
  • Working with sensitive code
  • Team security
  • Reporting security issues
• Related resources

​

data-usage

• Data policies
  • Data training policy
  • Development Partner Program
  • Feedback using the /feedback command
  • Session quality surveys
  • Data retention
• Data access
• Local Claude Code: Data flow and dependencies
  • Cloud execution: Data flow and dependencies
• Telemetry services
• Default behaviors by API provider
  • WebFetch domain safety check

​

zero-data-retention

• ZDR scope
  • Route Claude Code traffic to your ZDR organization
  • What ZDR covers
  • What ZDR does not cover
• Features disabled under ZDR
  • Model availability under ZDR
• Data retention for policy violations
• Request ZDR

​

Adoption

​

communications-kit

• Launch communications
  • Before you send
  • The announcement
  • Executive sponsor variant
  • Pilot group variant
  • Champion recruitment DM
• Tips and tricks campaign
  • Get started
  • Project memory
  • Control and safety
  • Connect your tools
  • Automate your workflows
  • Day-to-day development
  • Share and scale
  • Security and admin
• Quick reference
  • FAQ responses
  • Prompt templates

​

champion-kit

• The champion role
  • What this should cost you
• Share what you discover
  • What is worth sharing
  • Where to share it
  • The format that works
• Be the person people ask
  • Answer with a prompt rather than an explanation
  • Point at the feature rather than the documentation
  • Questions you are likely to hear
• Grow the circle
  • Patterns that tend to work
  • Thirty-day playbook
  • When someone wants to go deeper
• Respond to common concerns
• Quick-reference sheet

​

Settings

​

settings

• Settings files and who they affect
  • Compare the scope of each settings file
  • Find or create your settings files
  • Share settings with your team
  • Keep personal settings out of a repository
    • Where Claude Code keeps the local file in a git repository
  • Check what your organization enforces
• Change a setting
  • Use the /config menu
  • Edit a settings file
  • Change a setting for one session
  • When edits take effect
  • Confirm what loaded
  • Fix a broken settings file
• Settings precedence
  • Lists merge instead of overriding
  • Precedence examples
    • Team settings override personal settings
    • Organization settings override everything
    • The command line overrides your files for one session
    • A flag or environment variable sets the same thing
  • Troubleshoot a setting that doesn’t apply
    • A value you set is ignored
    • A change you made in Claude Code is lost in new sessions
    • A managed change hasn’t reached you
    • A committed key doesn’t reach teammates
    • Permission rules combine differently than you expected
  • Exceptions to managed settings precedence
• Settings in cloud sessions
• What’s next

​

settings-reference

• Settings index
• Model and responses
  • advisorModel
  • alwaysThinkingEnabled
  • availableModels
  • availableModelsMatch
  • deniedModels
  • effortLevel
  • enforceAvailableModels
  • fallbackModel
  • fastMode
  • fastModePerSessionOptIn
  • language
  • maxEffortLevel
  • model
  • modelOverrides
  • modelPicker
    • Fields for modelPicker
  • modelPricing
    • Fields for modelPricing
    • Which models a modelPricing row applies to
  • modelSettings
  • outputStyle
  • promptCacheTtl
  • showThinkingSummaries
  • subagentPromptCacheTtl
  • switchModelsOnFlag
  • ultracode
• Permission settings
  • allowManagedPermissionRulesOnly
  • autoMode
  • autoMode.classifyAllShell
  • disableAutoMode
  • permissions
  • useAutoModeDuringPlan
  • permissions.allow
    • Permission rule syntax
  • permissions.ask
  • permissions.deny
  • permissions.additionalDirectories
  • permissions.blockReadsOutsideWorkingDirectories
    • Sandboxed commands under the block
  • permissions.defaultMode
  • permissions.disableBypassPermissionsMode
  • skipAutoPermissionPrompt
  • skipDangerousModePermissionPrompt
• Sandbox settings
  • sandbox
  • sandbox.enabled
  • sandbox.failIfUnavailable
  • sandbox.autoAllowBashIfSandboxed
  • sandbox.excludedCommands
  • sandbox.allowUnsandboxedCommands
  • sandbox.filesystem
    • Sandbox path prefixes
  • sandbox.filesystem.allowWrite
  • sandbox.filesystem.denyWrite
  • sandbox.filesystem.denyRead
  • sandbox.filesystem.allowRead
  • sandbox.filesystem.allowManagedReadPathsOnly
  • sandbox.filesystem.disabled
  • sandbox.ignoreViolations
  • sandbox.enableWeakerNestedSandbox
  • sandbox.enableWeakerNetworkIsolation
  • sandbox.allowAppleEvents
  • sandbox.ripgrep
  • sandbox.bwrapPath
  • sandbox.socatPath
  • sandbox.credentials
    • Invalid credential entries in managed settings
  • sandbox.credentials.files
    • Mask fields for files
  • sandbox.credentials.envVars
    • Mask fields for environment variables
  • sandbox.credentials.allowPlaintextInject
  • sandbox.credentials.awsPairs
  • sandbox.credentials.sigv4
  • sandbox.network
  • sandbox.network.allowUnixSockets
  • sandbox.network.allowAllUnixSockets
  • sandbox.network.allowLocalBinding
  • sandbox.network.allowMachLookup
  • sandbox.network.allowedDomains
  • sandbox.network.deniedDomains
  • sandbox.network.strictAllowlist
  • sandbox.network.allowManagedDomainsOnly
  • sandbox.network.httpProxyPort
  • sandbox.network.socksProxyPort
  • sandbox.network.tlsTerminate
• Memory and context
  • autoCompactEnabled
  • autoCompactWindow
  • autoMemoryDirectory
  • autoMemoryEnabled
  • bashOutputMaxChars
  • claudeMd
  • claudeMdExcludes
  • env
    • How env values interact with your shell
    • When Claude Code applies env values
    • Variables Claude Code ignores in env
  • fileCheckpointingEnabled
  • plansDirectory
  • skillListingBudgetFraction
  • skillListingMaxDescChars
  • taskOutputMaxChars
• Interface and terminal
  • askUserQuestionTimeout
  • autoContinueAtUsageLimit
  • autoScrollEnabled
  • axScreenReader
  • bashEditDiffEnabled
  • companyAnnouncements
  • defaultShell
  • dialogExpiry
  • editorMode
  • emojiCompletionEnabled
  • fileSuggestion
    • Command input and output
  • footerLinksRegexes
    • Badge constraints
  • keybindingFlavor
  • maxProseWidth
  • prefersReducedMotion
  • promptSuggestionEnabled
  • respectGitignore
  • respondToBashCommands
  • showClearContextOnPlanAccept
  • showTurnDuration
  • spellcheck
  • spinnerTipsEnabled
  • spinnerTipsOverride
  • spinnerVerbs
  • statusLine
  • subagentStatusLine
  • syntaxHighlightingDisabled
  • terminalProgressBarEnabled
  • terminalTitleFromRename
  • theme
  • timeFormat
  • timeZone
  • tui
  • verbose
  • viewMode
  • vimInsertModeRemaps
  • voice
  • voiceEnabled
  • wheelScrollAccelerationEnabled
• Git and attribution
  • attribution
  • includeCoAuthoredBy
  • includeGitInstructions
  • prUrlTemplate
  • attribution.commit
  • attribution.pr
  • attribution.sessionUrl
• Hooks and automation
  • allowedHttpHookUrls
  • allowManagedHooksOnly
    • What runs under allowManagedHooksOnly
  • disableAllHooks
    • Status line and file suggestion gates
  • disableWorkflows
  • enableWorkflows
  • hooks
  • httpHookAllowedEnvVars
  • workflowKeywordTriggerEnabled
  • workflowSizeGuideline
• Plugins and skills
  • disableBundledSkills
  • disableSkillShellExecution
  • skillOverrides
  • syncClaudeAiSkills
  • syncClaudeAiPlugins
  • allowedChannelPlugins
  • blockedMarketplaces
  • channelsEnabled
  • disableCommandPluginSources
  • pluginSuggestionMarketplaces
  • pluginTrustMessage
  • strictKnownMarketplaces
    • Allowed source types
    • Owner wildcards
    • Exact matching
    • Allow only the official marketplace
    • Combine with extraKnownMarketplaces
  • strictPluginOnlyCustomization
  • strictPluginOnlyCustomization.skills
  • strictPluginOnlyCustomization.agents
  • strictPluginOnlyCustomization.hooks
  • strictPluginOnlyCustomization.mcp
  • enabledPlugins
  • extraKnownMarketplaces
    • Marketplace source types
    • Marketplace key aliases
  • pluginConfigs
• MCP
  • allowAllClaudeAiMcps
  • allowClaudeInChromeWithManagedMcp
  • allowedMcpServers
  • allowManagedMcpServersOnly
  • deniedMcpServers
  • disableClaudeAiConnectors
  • disabledMcpjsonServers
  • enableAllProjectMcpServers
  • enabledMcpjsonServers
  • managedMcpServers
• Agents, sessions, and worktrees
  • agent
  • crossSessionInbound
  • disableAgentView
  • isolatePeerMachines
  • processWrapper
  • teammateMode
  • worktree
  • worktree.baseRef
  • worktree.symlinkDirectories
  • worktree.sparsePaths
  • worktree.bgIsolation
• Remote, desktop, and notifications
  • agentPushNotifEnabled
  • awaySummaryEnabled
  • disableArtifact
  • disableDeepLinkRegistration
  • disableDesktopLocalSessions
  • disableRemoteControl
  • enableArtifact
  • inputNeededNotifEnabled
  • preferredNotifChannel
  • remote.defaultEnvironmentId
  • remoteControlAtStartup
  • sshConfigs
  • sshHostAllowlist
• Authentication and providers
  • apiKeyHelper
  • awsAuthRefresh
  • awsCredentialExport
  • forceLoginMethod
  • forceLoginGatewayUrl
  • forceLoginOrgUUID
  • gatewayInternalNetworks
  • gcpAuthRefresh
  • otelHeadersHelper
• Updates and versioning
  • autoUpdatesChannel
  • minimumVersion
  • requiredMaximumVersion
  • requiredMinimumVersion
• Tools
  • browserExternalPageTools
  • disableBrowserExternalNavigation
  • disableMobileSimulatorTools
• Privacy and telemetry
  • cleanupPeriodDays
  • desktopSessionCleanupPeriodDays
  • feedbackDrafts
  • feedbackSurveyRate
  • skipWebFetchPreflight
• Enterprise and managed settings
  • disableSideloadFlags
  • forceRemoteSettingsRefresh
  • managedSourcesBehavior
  • parentSettingsBehavior
  • policyHelper
    • Write the helper output
    • Helper failures
  • policyHelper.path
  • policyHelper.timeoutMs
  • policyHelper.refreshIntervalMs
  • wslInheritsWindowsSettings
• Global config settings
  • autoConnectIde
  • autoInstallIdeExtension
  • claudeInChromeDefaultEnabled
  • copyFullResponse
  • copyOnSelect
  • defaultToAgentsView
  • diffTool
  • externalEditorContext
  • leftArrowOpensAgents
  • permissionExplainerEnabled
  • prStatusFooterEnabled
  • teammateDefaultModel
• See also

​

settings-example

• Your own settings
• A team’s shared settings
• An organization’s managed settings

​

Permissions and sandboxing

​

permissions

• Permission system
  • Add a comment when you answer a permission prompt
• Manage permissions
• Permission modes
• Permission rule syntax
  • Match all uses of a tool
  • Use specifiers for fine-grained control
  • Match by input parameter
  • Wildcard patterns
  • Tool name wildcards
• Tool-specific permission rules
  • Bash
    • Compound commands
    • Wrappers
    • What a Bash rule doesn’t match
    • Read-only commands
    • Redirections
  • PowerShell
  • Read and Edit
    • Symlinks
      • How rules match a symlinked path
      • Writes through a symlink
      • Paths that can’t be resolved or that change
  • WebFetch
    • Allow or deny every fetch
  • MCP
  • Agent (subagents)
  • Cd
• Extend permissions with hooks
• Working directories
  • Move the session to another directory
  • Additional directories grant file access, not configuration
• How permissions interact with sandboxing
• Managed settings
• Settings precedence
• Project allow rules and workspace trust
  • When your local settings file needs trust
  • What runs before you trust a folder
• Example configurations
• See also

​

permission-modes

• Available modes
  • Actions no mode auto-approves
• Common setups
• Which mode a session starts in
  • Start in a different permission mode
• Switch permission modes
• Auto-approve file edits with acceptEdits mode
• Analyze before you edit with plan mode
  • Review and approve a plan
  • Set plan mode as the default
• Eliminate permission prompts with auto mode
  • Auto mode on Bedrock, Agent Platform, or Foundry
  • Server-side classifier review
  • What the classifier blocks by default
  • The first read outside the working directories
  • Boundaries you state in conversation
  • Approvals you state in conversation
  • When auto mode falls back
    • Repeated-block thresholds
  • How auto mode evaluates actions
• Allow only pre-approved tools with dontAsk mode
• Skip all checks with bypassPermissions mode
• Protected paths
• Critical paths
  • Which paths are critical
  • Other targets that count as critical paths
  • Removals inside nested commands and inline scripts
  • Rewrite a flagged command
  • Critical-path removals in each permission mode
  • Time limits and denials in auto and bypassPermissions modes
  • Remove-Item in PowerShell
• See also

​

sandboxing

• Get started
  • Set up Linux and WSL2
  • Sandbox modes
    • Auto-allow mode
    • Regular permissions mode
    • The unsandboxed retry escape hatch
    • Temporary directories
• Configure sandboxing
  • Disable filesystem isolation
    • Which settings can disable it
    • What changes when filesystem isolation is off
  • Protect credentials
  • Mask credentials
    • Mask environment variables
    • Re-sign AWS requests
    • Mask credential files
• How sandboxing works
  • Filesystem isolation
  • Protected paths
  • Network isolation
    • Per-command allowed domains in auto mode
    • IPv6 addresses in domain lists
  • OS-level enforcement
• How sandboxing relates to permissions and permission modes
  • Permission rules
  • Permission modes
• Configure the sandbox for your organization
  • Enforce sandboxing with managed settings
  • Keep developers from widening the policy
  • Custom proxy configuration
• Troubleshooting
• Limitations
  • Security limitations
  • Platform and tool compatibility
  • Scope
• See also

​

sandbox-environments

• Compare sandboxing approaches
• Choose an approach
  • How isolation relates to permission modes
• Sandboxed Bash tool
• Sandbox runtime
  • Set up and launch the runtime
  • What the runtime blocks on its own
  • After unattended runs
• Dev containers
• Custom container
• Virtual machine
• Cloud sessions
• Enforce isolation across an organization
• See also

​

Environments

​

cloud-environments

• The Default environment
• Configure your environment
  • Set environment variables
  • Add API credentials
    • Requirements
    • Add a credential
    • Which requests get the credential
    • Requests that never get the credential
  • Select an environment from the CLI
  • Archive an environment
  • Organization-shared environments
  • Set the environment a Claude Tag channel uses
• Network access
  • Access levels
  • Allow specific domains
  • GitHub proxy
  • Security proxy
• What’s available in cloud sessions
  • What carries over from your setup
  • Installed tools
  • Work with GitHub issues and pull requests
  • Link output back to the session
  • Run tests, start services, and add packages
    • Run tests
    • Start services
    • Add packages
  • Resource limits
  • Time limits
• Setup scripts
  • Script requirements
  • Environment caching
  • Setup scripts vs. SessionStart hooks
  • Install dependencies with a SessionStart hook
    • Limitations in cloud sessions
• Default allowed domains
• Related resources

​

Environments > Self-hosted environments

​

self-hosted-environments

• How self-hosted environments work
• Availability and limitations
• Why self-host
• Environments, runners, and sessions
  • Key concepts
  • Session lifecycle
  • Runner lifecycle
  • Network paths
• What stays on your infrastructure
• Get started

​

self-hosted-environments-quickstart

• Prerequisites
  • Organization and roles
  • Host and network
  • Software on the runner host
• Set up an environment and runner
• Send a follow-up message to a running session
• What’s next

​

self-hosted-environments-deploy

• Harden your deployment
• Network requirements
  • Default-deny egress
  • Authenticate to an egress proxy
    • Choose where the Proxy-Authorization value comes from
    • Configurations the runner refuses to start with
    • What the runner changes while a proxy-authorization flag is set
• Configure git
  • Let the runner configure git
  • Ship git config in your image
  • Use the Anthropic git proxy
    • Trust a private certificate authority with Anthropic-managed git
  • Rewrite git URLs for private networks
• Build the runner image
• Size CPU and memory for sessions
• Kubernetes
• Docker Compose
• Shutdown timing
  • Defer the drain past the first signal
    • What happens to the sessions the runner holds after the first signal
    • Size the stop timeout
  • What reaches a running post-session hook
• Keep the base directory and capacity identical across runners
• Reuse a pre-warmed checkout
• Pin the version
• Scale the fleet
• Known issues and limitations
  • Connector traffic leaves your network
  • Some sessions don’t count as idle
  • Additional limitations
  • Report an issue
• Troubleshooting
  • When the runner exits
    • Recognize a failed start
    • Restart with a wait that grows
    • Check why the runner keeps exiting
• What’s next

​

self-hosted-environments-configuration

• Wrapper scripts
  • Keep stdin and file descriptor 3 attached
  • Provision credentials scoped to the session creator
• Lifecycle hooks
  • checkout
  • post-session
    • Hook timing when the runner releases a session
  • command
• On-demand runners
  • The spawn-runner hook
• MCP servers
  • Turn off built-in session tools
• Prompt sessions to push their work
• Permissions and tool approval
  • How each session’s config is assembled
  • Repository-committed permission rules
• What’s next

​

self-hosted-environments-testing

• Install the capture hook on your test runner
  • Save the hook files
  • Before you start the runner
• Run the test loop
  • --environment dispatch behavior
• Example script
• Remote test runners
• Authenticate from CI
  • Long-lived CI host
  • Ephemeral CI runners
• Create a dedicated test environment
  • Mint the admin token
  • Create the environment
  • Delete the environment

​

self-hosted-environments-reference

• Runner CLI flags
• Orchestrator CLI flags
  • SCM connector flags
• Environment-variable-only settings
• Telemetry
• Health endpoint
• Prometheus metrics
  • Pass through session-child metrics
  • Session lifecycle counter semantics
• What’s next

​

self-hosted-environments-identity

• The session token
  • What the token proves
  • Token format
• Verify the token
  • Verify the token from your service
  • Verify the token inside the session
• Claims reference
  • The act chain
• Scope derived credentials
• Related environment variables
• What’s next

​

Model and responses

​

model-config

• Available models
  • Model aliases
  • Work with Fable
    • Fable and usage credits
  • Setting your model
    • Set a default model for new sessions
    • A new session starts on a different model than you picked
• Restrict model selection
  • Surface coverage
  • Default model behavior
  • Enforce the allowlist for the Default model
  • Control the model users run on
  • Merge behavior
  • Mantle model IDs
  • Block specific models or versions
  • Organization model restrictions
• Organization default model
• Organization effort limits
• Special model behavior
  • default model setting
  • opusplan model setting
  • Fallback model chains
  • Automatic model fallback
    • Check what triggered fallback
    • Ask before switching
    • Enable fallback on Bedrock, Agent Platform, and Foundry
    • Security research and biology workloads
  • Adjust effort level
    • Choose an effort level
    • Use ultrathink for one-off deep reasoning
    • Set the effort level
    • Adaptive reasoning and fixed thinking budgets
  • Extended thinking
  • Extended context
    • Sonnet 5.5 and Sonnet 5 context window
• Context window and auto-compaction
  • Set the auto-compact window
  • Default auto-compact thresholds
  • Correct the window for a gateway or custom model ID
• Checking your current model
• Add a custom model option
• Environment variables
  • Pin models for third-party deployments
  • Customize pinned model display and capabilities
  • Override model IDs per version
  • Prompt caching configuration
• Version history

​

fast-mode

• Toggle fast mode
  • Switch models while fast mode is on
  • Use fast mode in cloud sessions
• Understand the cost tradeoff
  • See where fast mode spend appears
• Decide when to use fast mode
  • Fast mode vs effort level
• Requirements
  • Enable fast mode for your organization
  • Use fast mode behind proxies and LLM gateways
  • Require per-session opt-in
• Handle rate limits
• Research preview
• See also

​

advisor

• When to use the advisor
• Enable the advisor
  • Use the /advisor command
  • Set advisorModel in settings
  • Use the --advisor flag
• Choose an advisor model
  • Fable advisor and usage credits
  • Common model pairings
• When Claude consults the advisor
• What you see during a session
• Cost
• Impact on prompt caching
• Requirements
• Turn the advisor off
• Compare with related features
• See also

​

output-styles

• Built-in output styles
  • Default
  • Proactive
  • Concise
  • Explanatory
  • Learning
• Change your output style
• Create a custom output style
  • Frontmatter reference
• Choose between an output style and other features
• How output styles work
• Related resources

​

Interface

​

terminal-config

• Enter multiline prompts
• Enable Option key shortcuts on macOS
• Get a terminal bell or notification
  • Play a sound with a Notification hook
• Configure tmux
• Fix Backspace deleting a whole word on Windows
• Match the color theme
  • Create a custom theme
    • Text and accent colors
    • Status colors
    • Input box and mode indicators
    • Diff rendering
    • Fullscreen mode
    • Usage meter and speaker labels
    • Shimmer variants and subagent colors
• Switch to fullscreen rendering
• Cap response width in wide terminals
• Paste large content
  • How Claude treats pasted text
  • Delete and restore a collapsed paste
  • Recall a prompt that had pasted text
• Edit prompts with Vim keybindings
• Related resources

​

fullscreen

• Enable fullscreen rendering
  • Fullscreen by default
• What changes
• Use the mouse
• Scroll the conversation
  • Auto-follow
  • Mouse wheel scrolling
  • Scroll in the JetBrains IDE terminal
• Search and review the conversation
• Watch your changes in the diff panel
• Clear the conversation
• Use with tmux
• Keep native text selection
• Troubleshooting
  • Stale or misplaced text on screen
  • Claude Code's fullscreen renderer didn't finish starting last time appears at startup
    • How Claude Code counts failed starts
• Research preview

​

accessibility

• Turn on screen reader mode
• Turn off screen reader mode
• Accessibility settings
• What your screen reader hears
  • Jump between turns
• Answer menus and prompts
• Hear when Claude Code needs you
• Known limitations
• Report an issue

​

voice-dictation

• Requirements
• Enable voice dictation
• Hold to record
• Tap to record and send
• Cancel a recording
• Change the dictation language
• Rebind the dictation key
• Troubleshooting
  • Terminal not listed in macOS Microphone settings
• See also

​

statusline

• Set up a status line
  • Use the /statusline command
  • Manually configure a status line
  • Disable the status line
• Build a status line step by step
• How status lines work
• Available data
  • Context window fields
  • Prompt cache fields
    • Last miss cause
• Examples
  • Context window usage
  • Git status with colors
  • Cost and duration tracking
  • Display multiple lines
  • Clickable links
  • Rate limit usage
  • Cache expensive operations
  • Windows configuration
• Subagent status lines
• Tips
• Troubleshooting

​

keybindings

• Configuration file
• Contexts
• Available actions
  • App actions
  • History actions
  • Chat actions
  • Autocomplete actions
  • Confirmation actions
  • Permission actions
  • Transcript actions
  • History search actions
  • Task actions
  • Theme actions
  • Help actions
  • Tabs actions
  • Attachments actions
  • Footer actions
  • Message selector actions
  • Diff actions
  • Diff panel actions
  • Model picker actions
  • Effort slider actions
  • Select actions
  • Plugin actions
  • Settings actions
  • Agents actions
  • Voice actions
  • Scroll actions
• Keystroke syntax
  • Modifiers
  • Uppercase letters
  • Non-US keyboard layouts
  • Chords
  • Special keys
• Unbind default shortcuts
• Reserved shortcuts
• Terminal conflicts
• Text fields
• Vim mode interaction
• Validation

​

Reference

​

cli-reference

• CLI commands
• CLI flags
  • System prompt flags
    • System prompt flags in resumed conversations
• See also

​

commands

• Commands across a typical workflow
• All commands
• How the command menu matches what you type
• MCP prompts
• See also

​

env-vars

• Set environment variables
  • In your shell
  • In settings files
• Precedence
• Variables
• Features that need feature-flag fetching
  • First session after an install or upgrade
• See also

​

tools-reference

• Configure tools with permission rules and hooks
• Agent tool behavior
• AskUserQuestion tool behavior
  • Question auto-continue timeout
• Bash tool behavior
  • What persists between commands
  • Timeout and output limits
    • Output limits
  • Background commands
  • Memory limit on Linux and WSL
• Edit tool behavior
• EndConversation tool behavior
• Glob tool behavior
• Grep tool behavior
• LSP tool behavior
• Monitor tool
  • WebSocket source
• NotebookEdit tool behavior
• PowerShell tool
  • Enable the PowerShell tool
  • Shell selection in settings, hooks, and skills
  • Windows encoding and exit codes
  • Preview limitations
• Read tool behavior
• SendFeedback tool behavior
  • What you see when Claude drafts
  • Review and edit a draft
  • Send a draft
  • Discard or keep a draft
  • Turn Claude-drafted feedback off
  • Sessions without Claude-drafted feedback
• Task tool availability
• WebFetch tool behavior
• WebSearch tool behavior
  • Session search limit
• Write tool behavior
• Check which tools are available
• See also

​

interactive-mode

• Keyboard shortcuts
  • General controls
  • Text editing
  • Word boundaries in editing shortcuts
  • Theme and display
  • Multiline input
  • Quick commands
  • Transcript viewer
  • Voice input
• Commands
  • Complete a command mid-prompt
• Vim editor mode
  • Mode switching
  • Remap INSERT-mode key sequences
  • Navigation (NORMAL mode)
  • Editing (NORMAL mode)
  • Text objects (NORMAL mode)
  • Visual mode
• Command history
  • Reverse search with Ctrl+R
• Background Bash commands
  • How backgrounding works
  • Shell mode with ! prefix
• Queue messages while Claude works
  • When Claude Code sends what you queued
  • Take back what you queued
• Prompt suggestions
  • When Claude Code skips suggestions
  • Turn prompt suggestions off
• Emoji shortcodes
• Check spelling as you type
  • Prerequisites
  • Turn spell checking on or off
  • What Claude Code underlines
  • When Claude Code underlines nothing
• Invisible characters in prompts
• Review changes with /diff
  • Diff panel
  • Diff viewer
• Side questions with /btw
• Task list
• Session recap
• Wait for a usage limit to reset
  • Cancel the wait
  • Start a wait yourself
  • Turn automatic continue off
• PR review status
  • GitLab merge requests
• Issue reference links
• See also

​

checkpointing

• How checkpoints work
  • Automatic tracking
  • Rewind and summarize
    • Rewind past a cleared conversation
    • Guide a summary
• Common use cases
• Limitations
  • Bash command changes not tracked
  • Subagent edits not restored
  • External changes not tracked
  • Messages sent mid-turn not checkpointed
  • Symlinked and hard-linked paths not restored
  • Not a replacement for version control
• See also

​

hooks

• Hook lifecycle
  • How a hook resolves
• Configuration
  • Hook locations
  • Matcher patterns
    • Match MCP tools
  • Hook handler fields
    • Common fields
    • Command hook fields
      • Exec form and shell form
    • HTTP hook fields
    • MCP tool hook fields
      • How the tool’s result is read
      • When the server is still connecting
      • Events that fire before MCP servers are available
    • Prompt and agent hook fields
  • Reference scripts by path
  • Hooks in skills and agents
  • The /hooks menu
  • Disable or remove hooks
• Hook input and output
  • Common input fields
  • Exit code output
    • Exit code 0
    • Exit code 2
    • Other exit codes
    • Timeouts
    • Exit code 2 behavior per event
  • HTTP response handling
  • JSON output
    • Emit terminal notifications
    • Add context for Claude
    • Decision control
• Hook events
  • SessionStart
    • SessionStart input
    • SessionStart decision control
    • Persist environment variables
  • Setup
    • Setup input
    • Setup decision control
  • InstructionsLoaded
    • InstructionsLoaded input
    • InstructionsLoaded decision control
  • UserPromptSubmit
    • UserPromptSubmit input
    • UserPromptSubmit decision control
    • What a blocked prompt leaves behind
  • UserPromptExpansion
    • UserPromptExpansion input
    • UserPromptExpansion decision control
  • MessageDisplay
    • MessageDisplay input
    • MessageDisplay output
  • PreToolUse
    • PreToolUse input
      • Bash
      • PowerShell
      • Write
      • Edit
      • Read
      • Glob
      • Grep
      • WebFetch
      • WebSearch
      • Agent
      • AskUserQuestion
      • ExitPlanMode
    • PreToolUse decision control
    • Defer a tool call for later
  • PermissionRequest
    • PermissionRequest input
    • PermissionRequest decision control
    • Permission update entries
  • PostToolUse
    • PostToolUse input
    • PostToolUse decision control
    • Annotate a result for the auto mode classifier
  • PostToolUseFailure
    • PostToolUseFailure input
    • PostToolUseFailure decision control
  • PostToolBatch
    • PostToolBatch input
    • PostToolBatch decision control
  • PermissionDenied
    • PermissionDenied input
    • PermissionDenied decision control
  • Notification
    • Notification input
  • SubagentStart
    • SubagentStart input
  • SubagentStop
    • SubagentStop input
  • TaskCreated
    • TaskCreated input
    • TaskCreated decision control
  • TaskCompleted
    • TaskCompleted input
    • TaskCompleted decision control
  • Stop
    • Stop input
    • Stop decision control
  • StopFailure
    • StopFailure input
  • TeammateIdle
    • TeammateIdle input
    • TeammateIdle decision control
  • ConfigChange
    • ConfigChange input
    • ConfigChange decision control
  • CwdChanged
    • CwdChanged input
    • CwdChanged output
  • DirectoryAdded
    • DirectoryAdded input
  • FileChanged
    • FileChanged input
    • FileChanged output
  • WorktreeCreate
    • WorktreeCreate input
    • WorktreeCreate output
  • WorktreeRemove
    • WorktreeRemove input
  • PreCompact
    • PreCompact input
  • PostCompact
    • PostCompact input
  • PreModelSwitch
    • PreModelSwitch input
    • PreModelSwitch decision control
  • PostModelSwitch
    • PostModelSwitch input
    • PostModelSwitch decision control
  • SessionEnd
    • SessionEnd input
  • Elicitation
    • Elicitation input
    • Elicitation output
  • ElicitationResult
    • ElicitationResult input
    • ElicitationResult output
• Prompt-based hooks
  • How prompt-based hooks work
  • Prompt hook configuration
  • Response schema
  • Check multiple conditions before stopping
• Agent-based hooks
  • How agent hooks work
  • Agent hook configuration
• Run hooks in the background
  • Configure an async hook
  • How async hooks execute
  • Run tests after file changes
  • Limitations
• Security considerations
  • Disclaimer
  • Workspace trust
  • Security best practices
• Windows PowerShell tool
• Debug hooks

​

channels-reference

• Overview
• What you need
• Example: build a webhook receiver
• Test during the research preview
• Server options
• Notification format
• Expose a reply tool
• Gate inbound messages
• Relay permission prompts
  • How relay works
  • Permission request fields
  • Add relay to a chat bridge
  • Full example
• Package as a plugin
• See also

​

Glossary

​

glossary

• A
  • AGENTS.md
  • Agent teams
  • Agentic coding
  • Agentic harness
  • Agentic loop
  • Artifact
  • Auto memory
  • Auto mode
• B
  • Bare mode
  • Bundled skills
• C
  • Channel
  • Checkpoint
  • .claude directory
  • CLAUDE.md
  • Cloud session
  • Command
  • Compaction
  • Connector
  • Context window
• D
  • Dispatch
• E
  • Effort level
  • Extended thinking
• F
  • Frontmatter
• H
  • Hook
• M
  • Managed settings
  • MCP (Model Context Protocol)
  • MCP server
  • MCP Tool Search
• N
  • Non-interactive mode
• O
  • Output style
• P
  • Permission mode
  • Permission rule
  • Plan mode
  • Plugin
  • Project trust
  • Prompt injection
• R
  • Remote Control
  • Rules
• S
  • Sandboxing
  • Session
  • Settings layers
  • Skill
  • Subagent
  • Surface
  • System prompt
  • System reminder
• T
  • Teleport
  • Tool
  • Turn
• V
  • Verification loop
• W
  • Worktree isolation
• Deprecated and renamed terms

​

Agent SDK

​

overview

• Compare the Agent SDK to other Claude tools
• Capabilities
• Get started
• Changelog
• Report bugs
• Branding guidelines
• License and terms
• Next steps

​

quickstart

• Prerequisites
• Setup
• Create a buggy file
• Build an agent that finds and fixes bugs
  • Run your agent
  • Try other prompts
  • Customize your agent
• Key concepts
• Next steps

​

migration-guide

• Overview
• What’s Changed
• Migration Steps
  • For TypeScript/JavaScript Projects
  • For Python Projects
• Breaking changes
  • Python: ClaudeCodeOptions renamed to ClaudeAgentOptions
  • System prompt no longer default
  • Settings sources default
• Next Steps

​

troubleshooting

• CLI startup
  • CLINotFoundError: Claude Code not found
  • CLIConnectionError: Refusing to execute batch script
  • CLIConnectionError: Failed to start Claude Code
  • CLIConnectionError: Not connected
• CLI process exit
  • ProcessError: Command failed with exit code
  • Claude Code process exited with code N
  • Claude Code returned an error result
• Structured outputs
  • structured_output is None but the result says success
• Report a new issue

​

Build agents

​

configuration

• Pass options to a session
• Load settings files
• Choose a model
• Set environment variables
• Set the working directory
• Limit turns and spend
• Change configuration mid-session
• Configure specific features
• Next steps

​

examples

• Run a minimal agent first
• Explore a demo application
• Work through a Python recipe

​

Core concepts

​

agent-loop

• The loop at a glance
• Turns and messages
• Message types
  • Handle messages
• Tool execution
  • Built-in tools
  • Tool permissions
  • Parallel tool execution
• Control how the loop runs
  • Turns and budget
  • Effort level
  • Permission mode
  • Model
• The context window
  • What consumes context
  • Automatic compaction
  • Keep context efficient
• Sessions and continuity
• Handle the result
• Hooks
• Put it all together
• Next steps

​

claude-code-features

• Control filesystem settings with settingSources
  • What settingSources does not control
• Project instructions (CLAUDE.md and rules)
  • CLAUDE.md load locations
• Skills
• Hooks
  • When to use which hook type
• Choose the right feature
• Related resources

​

sessions

• Choose an approach
  • Continue, resume, and fork
• Automatic session management
  • Python: ClaudeSDKClient
  • TypeScript: continue: true
• Use session options with query()
  • Capture the session ID
  • Resume by ID
  • Fork to explore alternatives
• Resume across hosts
• Related resources

​

session-storage

• The SessionStore interface
• Quick start
• Write your own adapter
• Reference implementations
  • Validate your adapter
• Behavior notes
  • Dual-write architecture
  • Resume from the store
  • Mirror writes are best-effort
  • getSessionMessages returns the post-compaction chain
  • forkSession is not a byte copy
  • Subagent transcripts
  • Retention
• Supported on
• Related resources

​

Input and output

​

streaming-vs-single-mode

• Overview
• Streaming Input Mode (Recommended)
  • Benefits
  • Implementation Example
• Single Message Input
  • When to Use Single Message Input
  • Limitations
  • Implementation Example

​

user-input

• Detect when Claude needs input
• Handle tool approval requests
  • Respond to tool requests
• Handle clarifying questions
  • Question format
    • Option previews (TypeScript)
  • Response format
    • Support free-text input
  • Complete example
• Limitations
• Other ways to get user input
  • Streaming input
  • Custom tools
• Related resources

​

streaming-output

• Enable streaming output
• StreamEvent reference
• Message flow
• Stream tool calls
• Build a streaming UI
• Known limitations
• Next steps

​

structured-outputs

• Why structured outputs?
• Quick start
• Type-safe schemas with Zod and Pydantic
• Output format configuration
• Example: TODO tracking agent
• Error handling
• Related resources

​

Extend with tools

​

custom-tools

• Quick reference
• Create a custom tool
  • Weather tool example
  • Call a custom tool
  • Add more tools
  • Add tool annotations
• Control tool access
  • Configure allowed tools
• Handle errors
• Return images and resources
  • Images
  • Resources
• Return structured data
• Example: unit converter
• Next steps

​

mcp

• Quickstart
• Add an MCP server
  • In code
  • From a config file
• Connection timing
• Allow MCP tools
  • Tool naming convention
  • Auto-approve with allowedTools
  • Discover available tools
• Transport types
  • stdio servers
  • HTTP/SSE servers
  • SDK MCP servers
• MCP tool search
• Authentication
  • Pass credentials via environment variables
  • HTTP headers for remote servers
  • OAuth2 authentication
• Examples
  • List issues from a repository
  • Query a database
• Error handling
• Troubleshooting
  • Server shows “failed” status
  • Tools not being called
  • Connection timeouts
  • Tool output exceeds maximum allowed tokens
• Related resources

​

tool-search

• How tool search works
• Configure tool search
• Optimize tool discovery
• Limits
• Related documentation

​

subagents

• Overview
• Benefits of using subagents
• Create subagents
  • Programmatic definition (recommended)
  • AgentDefinition configuration
  • Filesystem-based definition (alternative)
• What subagents inherit
• Invoke subagents
  • Automatic invocation
  • Explicit invocation
  • Dynamic agent configuration
• Detect subagent invocation
• Resume subagents
• Tool restrictions
  • Common tool combinations
• Cap subagent depth, concurrency, and spend
  • Run Opus 5 with subagents
• Scale up with dynamic workflows
• Troubleshooting
  • Claude not delegating to subagents
  • Filesystem-based agents not loading
• Related documentation

​

Customize behavior

​

modifying-system-prompts

• How system prompts work
  • Decide on a starting point
• Customize agent behavior
  • CLAUDE.md files for project-level instructions
    • Load CLAUDE.md with the SDK
  • Output styles for persistent configurations
    • Create an output style
    • Activate an output style
  • Append to the claude_code preset
    • Improve prompt caching across users and machines
  • Custom system prompts
    • Cache the static part of a custom prompt
  • Change the prompt of an existing session
    • Update Claude’s instructions mid-session
    • Turn recording off while you iterate on wording
• Context Claude Code adds outside the system prompt
  • Reminders Claude Code adds to the conversation
  • Turn off the context your agent replaces
  • See what Claude received
• Compare the four approaches
• Combine approaches
  • Combine an output style with session-specific additions
• See also

​

skills

• How skills work with the Agent SDK
• Use skills with the Agent SDK
  • Set up skills in a session
  • Confirm skills loaded
  • Allow only specific skills
• Commands in Agent SDK sessions
  • Discover available commands
  • Dispatch commands by name
  • Compact history with /compact
  • Reset context with /clear
• Create skills
  • Choose a discovery level
  • Create and dispatch your first skill
• Pre-approve tools for skills
• Troubleshooting
  • Skills not found
  • Skill not being used
  • Invalid skill name error
  • Additional troubleshooting
• Next steps
• Related resources

​

plugins

• Loading plugins
  • Path specifications
• Verifying plugin installation
• Use plugin skills
• Complete example
• Plugin structure reference
• Multiple plugin sources
• Troubleshooting
  • Plugin not loading
  • Skills not appearing
• See also

​

Control and observability

​

permissions

• How permissions are evaluated
• Allow and deny rules
• Permission modes
  • Available modes
  • Set permission mode
  • Mode details
    • Accept edits mode (acceptEdits)
    • Don’t ask mode (dontAsk)
    • Bypass permissions mode (bypassPermissions)
    • Plan mode (plan)
• Related resources

​

hooks

• How hooks work
• Available hooks
• Configure hooks
  • Matchers
  • Callback functions
    • Inputs
    • Outputs
    • Asynchronous output
• Examples
  • Modify tool input
  • Add context and block a tool
  • Auto-approve specific tools
  • Register multiple hooks
  • Filter with multi-tool matchers
  • Track subagent activity
  • Make HTTP requests from hooks
  • Forward notifications to Slack
• Fix common issues
  • Hook not firing
  • Matcher not filtering as expected
  • Hook timeout
  • Tool blocked unexpectedly
  • Modified input not applied
  • Session hooks not available in Python
  • Subagent permission prompts multiplying
  • Recursive hook loops with subagents
  • systemMessage not appearing in output
• Related resources

​

file-checkpointing

• How checkpointing works
• Implement checkpointing
• Common patterns
  • Checkpoint before risky operations
  • Multiple restore points
• Try it out
• Limitations
• Troubleshooting
  • Checkpointing options not recognized
  • User messages don’t have UUIDs
  • “No file checkpoint found for this message” error
  • “File rewinding is not enabled” error
  • “ProcessTransport is not ready for writing” error
• Next steps

​

cost-tracking

• Understand token usage
• Track costs in streaming input mode
• Get the total cost of a query
• Track per-step and per-model usage
  • Track per-step usage
  • Break down usage per model
• Accumulate costs across multiple calls
• Handle errors, caching, and output token counts
  • Read output tokens from the result message
  • Track costs on failed conversations
  • Recover totals after a session crash
  • Track cache tokens
  • Extend the prompt cache TTL to one hour
• Related documentation

​

observability

• How telemetry flows from the SDK
• Enable telemetry export
  • Flush telemetry from short-lived calls
• Read agent traces
• Link traces to your application
• Tag telemetry from your agent
• Attribute actions to your end users
• Control sensitive data in exports
• Related documentation

​

todo-tracking

• Model availability
• Todo lifecycle
• When Claude creates todos
• Examples
  • Monitor todo changes
  • Display progress in real time
• Related documentation

​

Deployment

​

hosting

• The subprocess model
  • State that lives on local disk
• Choose a session pattern
  • Ephemeral sessions
  • Long-running sessions
  • Hybrid sessions
  • Multi-agent container
• Provision the container
  • Container-based sandboxing
  • Runtime dependencies
  • Resources
  • Network
• Handle production concerns
  • Session and state persistence
  • Observability
  • Auth and secrets
  • Scaling and concurrency
  • Cost
  • Multi-tenant isolation
• Known limitations
• Troubleshoot deployment failures
• Next steps

​

secure-deployment

• Threat model
• Built-in security features
• Security principles
  • Security boundaries
  • Least privilege
  • Defense in depth
• Isolation technologies
  • Sandbox runtime
  • Containers
  • gVisor
  • Virtual machines
  • Cloud deployments
• Credential management
  • The proxy pattern
  • Configuring Claude Code to use a proxy
  • Implementing a proxy
  • Credentials for other services
    • Custom tools
    • Traffic forwarding
• Filesystem configuration
  • Read-only code mounting
  • Writable locations
• Further reading

​

SDK references

​

typescript

• Installation
  • Compile to a single executable
  • Import the /core entry when you bundle the Agent SDK
• Functions
  • query()
    • Parameters
    • Returns
  • startup()
    • Parameters
    • Returns
    • Example
  • prewarm()
    • Example
  • tool()
    • Parameters
    • ToolAnnotations
  • createSdkMcpServer()
    • Parameters
  • listSessions()
    • Parameters
    • Return type: SDKSessionInfo
    • Example
  • getSessionMessages()
    • Parameters
    • Return type: SessionMessage
    • Example
  • getSessionInfo()
    • Parameters
  • renameSession()
    • Parameters
  • tagSession()
    • Parameters
  • resolveSettings()
    • Parameters
    • Return type: ResolvedSettings
    • Example
• Types
  • Options
    • Handle slow or stalled API responses
  • Query object
    • Methods
    • applyFlagSettings()
    • updateSettings()
  • WarmQuery
    • Methods
  • SpareProcess
    • Members
  • SDKControlInitializeResponse
  • SDKControlInterruptResponse
  • SDKControlGetContextUsageResponse
  • SDKControlReadFileResponse
    • What readFile() can read
  • SDKControlReloadPluginsResponse
  • SDKControlReloadSkillsResponse
  • SDKControlReloadOutputStylesResponse
  • SDKControlMcpReadResourceResponse
  • AgentDefinition
  • AgentMcpServerSpec
  • SettingSource
    • Default behavior
    • Why use settingSources
    • Settings precedence
  • PermissionMode
  • CanUseTool
  • PermissionResult
  • ToolConfig
  • McpServerConfig
    • McpStdioServerConfig
    • McpSSEServerConfig
    • McpHttpServerConfig
    • McpSdkServerConfigWithInstance
    • McpClaudeAIProxyServerConfig
  • SdkPluginConfig
• Message Types
  • SDKMessage
  • SDKAssistantMessage
  • SDKUserMessage
  • SDKUserMessageReplay
  • SDKResultMessage
    • user_message_uuid
    • user_message_uuids
    • resume_reason
    • queued_turn_count
    • startup_failure_reason
  • SDKSystemMessage
  • SDKPartialAssistantMessage
  • SDKCompactBoundaryMessage
  • SDKInformationalMessage
  • SDKWorkerShuttingDownMessage
  • SDKPluginInstallMessage
  • SDKPermissionDeniedMessage
  • SDKPermissionDenial
  • SDKContextUsage
  • SDKContextUsageCategory
  • SDKMessageOrigin
  • Task-notification subkinds
    • Declare a scheduled run
  • Peer origin fields
• Hook Types
  • HookEvent
  • HookCallback
  • HookCallbackMatcher
  • HookInput
  • BaseHookInput
    • PreToolUseHookInput
    • PostToolUseHookInput
    • PostToolUseFailureHookInput
    • PostToolBatchHookInput
    • PermissionDeniedHookInput
    • NotificationHookInput
    • UserPromptSubmitHookInput
    • UserPromptExpansionHookInput
    • SessionStartHookInput
    • SessionEndHookInput
    • StopHookInput
    • StopFailureHookInput
    • SubagentStartHookInput
    • SubagentStopHookInput
    • PreCompactHookInput
    • PostCompactHookInput
    • PreModelSwitchHookInput
    • PostModelSwitchHookInput
    • PermissionRequestHookInput
    • SetupHookInput
    • TeammateIdleHookInput
    • TaskCreatedHookInput
    • TaskCompletedHookInput
    • ElicitationHookInput
    • ElicitationResultHookInput
    • ConfigChangeHookInput
    • InstructionsLoadedHookInput
    • DirectoryAddedHookInput
    • WorktreeCreateHookInput
    • WorktreeRemoveHookInput
    • CwdChangedHookInput
    • FileChangedHookInput
    • MessageDisplayHookInput
  • HookJSONOutput
    • AsyncHookJSONOutput
    • SyncHookJSONOutput
• Tool Input Types
  • ToolInputSchemas
  • Agent
  • AskUserQuestion
  • Bash
  • Monitor
  • TaskOutput
  • Edit
  • Read
  • Write
  • Glob
  • Grep
  • TaskStop
  • NotebookEdit
  • WebFetch
  • WebSearch
  • Workflow
  • TodoWrite
  • TaskCreate
  • TaskUpdate
  • TaskGet
  • TaskList
  • ExitPlanMode
  • ListMcpResources
  • ReadMcpResource
  • EnterWorktree
  • ExitWorktree
  • EnterPlanMode
  • CronCreate
  • CronDelete
  • CronList
  • ScheduleWakeup
  • RemoteTrigger
  • PushNotification
  • REPL
  • ReportFindings
  • Artifact
  • Projects
  • ReadMcpResourceDir
  • RefreshMcpTools
  • ShowOnboardingRolePicker
  • McpInput
• Tool Output Types
  • ToolOutputSchemas
  • Agent
  • AskUserQuestion
  • Bash
  • Monitor
  • Edit
  • Read
  • Write
  • Glob
  • Grep
  • TaskStop
  • NotebookEdit
  • WebFetch
  • WebSearch
  • Workflow
  • TodoWrite
  • TaskCreate
  • TaskUpdate
  • TaskGet
  • TaskList
  • ExitPlanMode
  • ListMcpResources
  • ReadMcpResource
  • EnterWorktree
  • ExitWorktree
  • EnterPlanMode
  • CronCreate
  • CronDelete
  • CronList
  • ScheduleWakeup
  • RemoteTrigger
  • PushNotification
  • ReportFindings
  • Artifact
  • Projects
  • ReadMcpResourceDir
  • RefreshMcpTools
  • ShowOnboardingRolePicker
  • McpOutput
• Permission Types
  • PermissionUpdate
  • PermissionBehavior
  • PermissionUpdateDestination
  • PermissionRuleValue
• Other Types
  • ApiKeySource
  • SdkBeta
  • SlashCommand
  • ModelInfo
  • AgentInfo
  • McpServerProvenance
  • McpServerStatus
  • McpServerStatusConfig
  • AccountInfo
  • ModelUsage
  • ConfigScope
  • NonNullableUsage
  • Usage
  • CallToolResult
  • SDKMcpResourceLink
  • ThinkingConfig
  • SpawnedProcess
  • SpawnOptions
  • McpSetServersResult
  • RewindFilesResult
  • SDKStatusMessage
  • SDKTaskNotificationMessage
  • SDKToolUseSummaryMessage
  • SDKHookStartedMessage
  • SDKHookProgressMessage
  • SDKHookResponseMessage
  • SDKToolProgressMessage
  • SDKAuthStatusMessage
  • SDKTaskStartedMessage
  • SDKTaskProgressMessage
  • SDKTaskUpdatedMessage
  • SDKBackgroundTasksChangedMessage
  • SDKThinkingTokensMessage
  • SDKFilesPersistedEvent
  • SDKRateLimitEvent
  • SDKLocalCommandOutputMessage
  • SDKCommandsChangedMessage
  • SDKPromptSuggestionMessage
  • SDKConversationResetMessage
  • AbortError
• Sandbox Configuration
  • SandboxSettings
    • Example usage
  • SandboxNetworkConfig
  • SandboxFilesystemConfig
  • Permissions Fallback for Unsandboxed Commands
• See also

​

typescript-v2-preview

• Installation
• Quick start
  • One-shot prompt
  • Basic session
  • Multi-turn conversation
  • Session resume
  • Cleanup
• API reference
  • unstable_v2_createSession()
  • unstable_v2_resumeSession()
  • unstable_v2_prompt()
  • SDKSession interface
• Feature availability
• See also

​

python

• Installation
• Choosing between query() and ClaudeSDKClient
• Functions
  • query()
    • Parameters
    • Returns
    • Example - With options
  • tool()
    • Parameters
    • Input schema options
    • Returns
    • Example
    • ToolAnnotations
  • create_sdk_mcp_server()
    • Parameters
    • Returns
    • Example
  • list_sessions()
    • Parameters
    • Return type: SDKSessionInfo
    • Example
  • get_session_messages()
    • Parameters
    • Return type: SessionMessage
    • Example
  • get_session_info()
    • Parameters
    • Example
  • rename_session()
    • Parameters
    • Example
  • tag_session()
    • Parameters
    • Example
• Classes
  • ClaudeSDKClient
    • Methods
    • Context Manager Support
    • Example - Continuing a conversation
    • Example - Streaming input with ClaudeSDKClient
    • Example - Using interrupts
    • Example - Advanced permission control
• Types
  • SdkMcpTool
  • Transport
  • ClaudeAgentOptions
    • Handle slow or stalled API responses
  • OutputFormat
  • SystemPromptPreset
  • SystemPromptCustom
  • SystemPromptFile
  • SettingSource
    • Default behavior
    • Why use setting_sources
    • Settings precedence
  • AgentDefinition
  • PermissionMode
  • EffortLevel
  • CanUseTool
  • ToolPermissionContext
  • PermissionResult
  • PermissionResultAllow
  • PermissionResultDeny
  • PermissionUpdate
  • PermissionRuleValue
  • ToolsPreset
  • ThinkingConfig
  • TaskBudget
  • SdkBeta
  • McpSdkServerConfig
  • McpServerConfig
    • McpStdioServerConfig
    • McpSSEServerConfig
    • McpHttpServerConfig
  • McpServerStatusConfig
  • McpStatusResponse
  • McpServerStatus
  • SdkPluginConfig
• Message Types
  • Message
  • UserMessage
  • AssistantMessage
  • AssistantMessageError
  • SystemMessage
  • ResultMessage
  • StreamEvent
  • RateLimitEvent
  • RateLimitInfo
  • ConversationResetMessage
  • TaskStartedMessage
  • TaskUsage
  • TaskProgressMessage
  • TaskNotificationMessage
• Content Block Types
  • ContentBlock
  • TextBlock
  • ThinkingBlock
  • ToolUseBlock
  • ToolResultBlock
• Error Types
  • ClaudeSDKError
  • CLINotFoundError
  • CLIConnectionError
  • ProcessError
  • ResultError
  • CLIJSONDecodeError
• Hook Types
  • HookEvent
  • HookCallback
  • HookContext
  • HookMatcher
  • HookInput
  • BaseHookInput
  • PreToolUseHookInput
  • PostToolUseHookInput
  • PostToolUseFailureHookInput
  • UserPromptSubmitHookInput
  • StopHookInput
  • SubagentStopHookInput
  • PreCompactHookInput
  • NotificationHookInput
  • SubagentStartHookInput
  • PermissionRequestHookInput
  • HookJSONOutput
    • SyncHookJSONOutput
    • HookSpecificOutput
    • AsyncHookJSONOutput
  • Hook Usage Example
• Tool Input/Output Types
  • Agent
  • AskUserQuestion
  • Bash
  • Monitor
  • Edit
  • Read
  • Write
  • Glob
  • Grep
  • NotebookEdit
  • WebFetch
  • WebSearch
  • TodoWrite
  • TaskCreate
  • TaskUpdate
  • TaskGet
  • TaskList
  • TaskOutput
  • TaskStop
  • ExitPlanMode
  • ListMcpResources
  • ReadMcpResource
• Build a continuous conversation interface
• Error handling
• Sandbox Configuration
  • SandboxSettings
    • Example usage
  • SandboxNetworkConfig
  • SandboxIgnoreViolations
  • Permissions Fallback for Unsandboxed Commands
• See also

​

What’s New

​

index

• (No headings found)

​

2026-w37

• (No headings found)

​

2026-w36

• (No headings found)

​

2026-w35

• (No headings found)

​

2026-w34

• (No headings found)

​

2026-w33

• (No headings found)

​

2026-w32

• (No headings found)

​

2026-w30

• (No headings found)

​

2026-w29

• (No headings found)

​

2026-w28

• (No headings found)

​

2026-w27

• (No headings found)

​

2026-w26

• (No headings found)

​

2026-w25

• (No headings found)

​

2026-w24

• (No headings found)

​

2026-w23

• (No headings found)

​

2026-w22

• (No headings found)

​

2026-w21

• (No headings found)

​

2026-w20

• (No headings found)

​

2026-w19

• (No headings found)

​

2026-w18

• (No headings found)

​

2026-w17

• (No headings found)

​

2026-w16

• (No headings found)

​

2026-w15

• (No headings found)

​

2026-w14

• (No headings found)

​

2026-w13

• (No headings found)

​

Resources

​

legal-and-compliance

• Legal agreements
  • License
  • Commercial agreements
  • Can customers offer Claude Code in their products?
• Compliance
  • Healthcare compliance (BAA)
• Usage policy
  • Acceptable use
  • Authentication and credential use
• Security and trust
  • Trust and safety
  • Security vulnerability reporting