CalvinBackup/claude-howto
1
0
Fork 0
mirror of https://github.com/luongnv89/claude-howto.git synced 2026-05-09 22:07:32 +02:00
Code Issues Packages Projects Releases Wiki Activity

docs: Complete Phases 3-4 — new feature coverage and reference doc updates

Browse Source 
Phase 3: Added agent teams tutorial, scheduled tasks, Chrome integration,
remote control expansion, plugin marketplaces/LSP, keyboard customization,
and desktop app expansion across 3 guide files (~612 net lines).

Phase 4: Cascading updates to 6 reference documents — synced command counts
(40→55), added bundled skills, 18 hook events, new features (agent teams,
scheduled tasks, Chrome, keybindings), and updated all dates to March 2026.
This commit is contained in:
Luong NGUYEN
2026-03-13 05:13:17 +01:00
parent ef52705f78
commit 132de292e4
10 changed files with 829 additions and 135 deletions
Download Patch File Download Diff File Expand all files Collapse all files
04-subagents/README.md
+123 -9
View File
@@ -533,29 +533,143 @@ This command:
## Agent Teams (Experimental) ## Agent Teams (Experimental)
Agent teams allow multiple agents to work together on complex tasks, coordinating across separate contexts. Agent Teams coordinate multiple Claude Code instances working together on complex tasks. Unlike subagents (which are delegated subtasks returning results), teammates work independently with their own context and communicate directly through a shared mailbox system.
> **Note**: Agent Teams is experimental and requires Claude Code v2.1.32+. Enable it before use.
### Subagents vs Agent Teams
| Aspect | Subagents | Agent Teams |
|--------|-----------|-------------|
| **Delegation model** | Parent delegates subtask, waits for result | Team lead assigns work, teammates execute independently |
| **Context** | Fresh context per subtask, results distilled back | Each teammate maintains its own persistent context |
| **Coordination** | Sequential or parallel, managed by parent | Shared task list with automatic dependency management |
| **Communication** | Return values only | Inter-agent messaging via mailbox |
| **Session resumption** | Supported | Not supported with in-process teammates |
| **Best for** | Focused, well-defined subtasks | Large multi-file projects requiring parallel work |
### Enabling Agent Teams ### Enabling Agent Teams
Set the environment variable or add it to your `settings.json`:
```bash ```bash
export CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 export CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1
``` ```
### Display Mode Or in `settings.json`:
Control how teammate activity is displayed using the `--teammate-mode` flag: ```json
{
"env": {
"CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1"
}
}
```
| Mode | Description | ### Starting a team
|------|-------------|
| `auto` | Automatically choose the best display mode | Once enabled, ask Claude to work with teammates in your prompt:
| `in-process` | Show teammate output inline in the current terminal |
| `tmux` | Show each teammate in a separate tmux pane | ```
User: Build the authentication module. Use a team — one teammate for the API endpoints,
one for the database schema, and one for the test suite.
```
Claude will create the team, assign tasks, and coordinate the work automatically.
### Display modes
Control how teammate activity is displayed:
| Mode | Flag | Description |
|------|------|-------------|
| **Auto** | `--teammate-mode auto` | Automatically chooses the best display mode for your terminal |
| **In-process** | `--teammate-mode in-process` | Shows teammate output inline in the current terminal (default) |
| **Split-panes** | `--teammate-mode tmux` | Opens each teammate in a separate tmux or iTerm2 pane |
```bash ```bash
claude --teammate-mode tmux claude --teammate-mode tmux
``` ```
> **Note**: Agent teams is an experimental feature and may change in future releases. > **Note**: Split-pane mode requires tmux or iTerm2. It is not available in VS Code terminal, Windows Terminal, or Ghostty.
### Architecture
```mermaid
graph TB
Lead["Team Lead<br/>(Coordinator)"]
TaskList["Shared Task List<br/>(Dependencies)"]
Mailbox["Mailbox<br/>(Messages)"]
T1["Teammate 1<br/>(Own Context)"]
T2["Teammate 2<br/>(Own Context)"]
T3["Teammate 3<br/>(Own Context)"]
Lead -->|assigns tasks| TaskList
Lead -->|sends messages| Mailbox
TaskList -->|picks up work| T1
TaskList -->|picks up work| T2
TaskList -->|picks up work| T3
T1 -->|reads/writes| Mailbox
T2 -->|reads/writes| Mailbox
T3 -->|reads/writes| Mailbox
T1 -->|updates status| TaskList
T2 -->|updates status| TaskList
T3 -->|updates status| TaskList
style Lead fill:#e1f5fe,stroke:#333,color:#333
style TaskList fill:#fff9c4,stroke:#333,color:#333
style Mailbox fill:#f3e5f5,stroke:#333,color:#333
style T1 fill:#e8f5e9,stroke:#333,color:#333
style T2 fill:#e8f5e9,stroke:#333,color:#333
style T3 fill:#e8f5e9,stroke:#333,color:#333
```
**Key components**:
- **Team Lead**: The main Claude Code session that creates the team, assigns tasks, and coordinates
- **Shared Task List**: A synchronized list of tasks with automatic dependency tracking
- **Mailbox**: An inter-agent messaging system for teammates to communicate status and coordinate
- **Teammates**: Independent Claude Code instances, each with their own context window
### Task assignment and messaging
The team lead breaks work into tasks and assigns them to teammates. The shared task list handles:
- **Automatic dependency management** — tasks wait for their dependencies to complete
- **Status tracking** — teammates update task status as they work
- **Inter-agent messaging** — teammates send messages via the mailbox for coordination (e.g., "Database schema is ready, you can start writing queries")
### Plan approval workflow
For complex tasks, the team lead creates an execution plan before teammates begin work. The user reviews and approves the plan, ensuring the team's approach aligns with expectations before any code changes are made.
### Hook events for teams
Agent Teams introduce two additional [hook events](../06-hooks/):
| Event | Fires When | Use Case |
|-------|-----------|----------|
| `TeammateIdle` | A teammate finishes its current task and has no pending work | Trigger notifications, assign follow-up tasks |
| `TaskCompleted` | A task in the shared task list is marked complete | Run validation, update dashboards, chain dependent work |
### Best practices
- **Team size**: Keep teams at 3-5 teammates for optimal coordination
- **Task sizing**: Break work into tasks that take 5-15 minutes each — small enough to parallelize, large enough to be meaningful
- **Avoid file conflicts**: Assign different files or directories to different teammates to prevent merge conflicts
- **Start simple**: Use in-process mode for your first team; switch to split-panes once comfortable
- **Clear task descriptions**: Provide specific, actionable task descriptions so teammates can work independently
### Limitations
- **Experimental**: Feature behavior may change in future releases
- **No session resumption**: In-process teammates cannot be resumed after a session ends
- **One team per session**: Cannot create nested teams or multiple teams in a single session
- **Fixed leadership**: The team lead role cannot be transferred to a teammate
- **Split-pane restrictions**: tmux/iTerm2 required; not available in VS Code terminal, Windows Terminal, or Ghostty
- **No cross-session teams**: Teammates exist only within the current session
> **Warning**: Agent Teams is experimental. Test with non-critical work first and monitor teammate coordination for unexpected behavior.
--- ---
07-plugins/README.md
+178 -2
View File
@@ -119,9 +119,34 @@ my-plugin/
└── plugin.test.js └── plugin.test.js
``` ```
## LSP Server Configuration ### LSP server configuration
Plugins can include Language Server Protocol (LSP) support via `.lsp.json`: Plugins can include Language Server Protocol (LSP) support for real-time code intelligence. LSP servers provide diagnostics, code navigation, and symbol information as you work.
**Configuration locations**:
- `.lsp.json` file in the plugin root directory
- Inline `lsp` key in `plugin.json`
#### Field reference
| Field | Required | Description |
|-------|----------|-------------|
| `command` | Yes | LSP server binary (must be in PATH) |
| `extensionToLanguage` | Yes | Maps file extensions to language IDs |
| `args` | No | Command-line arguments for the server |
| `transport` | No | Communication method: `stdio` (default) or `socket` |
| `env` | No | Environment variables for the server process |
| `initializationOptions` | No | Options sent during LSP initialization |
| `settings` | No | Workspace configuration passed to the server |
| `workspaceFolder` | No | Override the workspace folder path |
| `startupTimeout` | No | Maximum time (ms) to wait for server startup |
| `shutdownTimeout` | No | Maximum time (ms) for graceful shutdown |
| `restartOnCrash` | No | Automatically restart if the server crashes |
| `maxRestarts` | No | Maximum restart attempts before giving up |
#### Example configurations
**Go (gopls)**:
```json ```json
{ {
@@ -135,6 +160,57 @@ Plugins can include Language Server Protocol (LSP) support via `.lsp.json`:
} }
``` ```
**Python (pyright)**:
```json
{
"python": {
"command": "pyright-langserver",
"args": ["--stdio"],
"extensionToLanguage": {
".py": "python",
".pyi": "python"
}
}
}
```
**TypeScript**:
```json
{
"typescript": {
"command": "typescript-language-server",
"args": ["--stdio"],
"extensionToLanguage": {
".ts": "typescript",
".tsx": "typescriptreact",
".js": "javascript",
".jsx": "javascriptreact"
}
}
}
```
#### Available LSP plugins
The official marketplace includes pre-configured LSP plugins:
| Plugin | Language | Server Binary | Install Command |
|--------|----------|---------------|----------------|
| `pyright-lsp` | Python | `pyright-langserver` | `pip install pyright` |
| `typescript-lsp` | TypeScript/JavaScript | `typescript-language-server` | `npm install -g typescript-language-server typescript` |
| `rust-lsp` | Rust | `rust-analyzer` | Install via `rustup component add rust-analyzer` |
#### LSP capabilities
Once configured, LSP servers provide:
- **Instant diagnostics** — errors and warnings appear immediately after edits
- **Code navigation** — go to definition, find references, implementations
- **Hover information** — type signatures and documentation on hover
- **Symbol listing** — browse symbols in the current file or workspace
## Plugin Settings ## Plugin Settings
Plugins can ship a `settings.json` file to provide default configuration. This currently supports the `agent` key, which sets the main thread agent for the plugin: Plugins can ship a `settings.json` file to provide default configuration. This currently supports the `agent` key, which sets the main thread agent for the plugin:
@@ -327,6 +403,106 @@ Enterprise and advanced users can control marketplace behavior through settings:
- **Custom npm registries**: Plugins can specify custom npm registry URLs for dependency resolution - **Custom npm registries**: Plugins can specify custom npm registry URLs for dependency resolution
- **Version pinning**: Lock plugins to specific versions for reproducible environments - **Version pinning**: Lock plugins to specific versions for reproducible environments
### Marketplace definition schema
Plugin marketplaces are defined in `.claude-plugin/marketplace.json`:
```json
{
"name": "my-team-plugins",
"owner": "my-org",
"plugins": [
{
"name": "code-standards",
"source": "./plugins/code-standards",
"description": "Enforce team coding standards",
"version": "1.2.0",
"author": "platform-team"
},
{
"name": "deploy-helper",
"source": {
"source": "github",
"repo": "my-org/deploy-helper",
"ref": "v2.0.0"
},
"description": "Deployment automation workflows"
}
]
}
```
| Field | Required | Description |
|-------|----------|-------------|
| `name` | Yes | Marketplace name in kebab-case |
| `owner` | Yes | Organization or user who maintains the marketplace |
| `plugins` | Yes | Array of plugin entries |
| `plugins[].name` | Yes | Plugin name (kebab-case) |
| `plugins[].source` | Yes | Plugin source (path string or source object) |
| `plugins[].description` | No | Brief plugin description |
| `plugins[].version` | No | Semantic version string |
| `plugins[].author` | No | Plugin author name |
### Plugin source types
Plugins can be sourced from multiple locations:
| Source | Syntax | Example |
|--------|--------|---------|
| **Relative path** | String path | `"./plugins/my-plugin"` |
| **GitHub** | `{ "source": "github", "repo": "owner/repo" }` | `{ "source": "github", "repo": "acme/lint-plugin", "ref": "v1.0" }` |
| **Git URL** | `{ "source": "url", "url": "..." }` | `{ "source": "url", "url": "https://git.internal/plugin.git" }` |
| **Git subdirectory** | `{ "source": "git-subdir", "url": "...", "path": "..." }` | `{ "source": "git-subdir", "url": "https://github.com/org/monorepo.git", "path": "packages/plugin" }` |
| **npm** | `{ "source": "npm", "package": "..." }` | `{ "source": "npm", "package": "@acme/claude-plugin", "version": "^2.0" }` |
| **pip** | `{ "source": "pip", "package": "..." }` | `{ "source": "pip", "package": "claude-data-plugin", "version": ">=1.0" }` |
GitHub and git sources support optional `ref` (branch/tag) and `sha` (commit hash) fields for version pinning.
### Distribution methods
**GitHub (recommended)**:
```bash
# Users add your marketplace
/plugin marketplace add owner/repo-name
```
**Other git services** (full URL required):
```bash
/plugin marketplace add https://gitlab.com/org/marketplace-repo.git
```
**Private repositories**: Supported via git credential helpers or environment tokens. Users must have read access to the repository.
**Official marketplace submission**: Submit plugins to the Anthropic-curated marketplace for broader distribution.
### Strict mode
Control how marketplace definitions interact with local `plugin.json` files:
| Setting | Behavior |
|---------|----------|
| `strict: true` (default) | Local `plugin.json` is authoritative; marketplace entry supplements it |
| `strict: false` | Marketplace entry is the entire plugin definition |
**Organization restrictions** with `strictKnownMarketplaces`:
| Value | Effect |
|-------|--------|
| Not set | No restrictions — users can add any marketplace |
| Empty array `[]` | Lockdown — no marketplaces allowed |
| Array of patterns | Allowlist — only matching marketplaces can be added |
```json
{
"strictKnownMarketplaces": [
"my-org/*",
"github.com/trusted-vendor/*"
]
}
```
> **Warning**: In strict mode with `strictKnownMarketplaces`, users can only install plugins from allowlisted marketplaces. This is useful for enterprise environments requiring controlled plugin distribution.
## Plugin Installation & Lifecycle ## Plugin Installation & Lifecycle
```mermaid ```mermaid
09-advanced-features/README.md
+337 -30
View File
@@ -13,21 +13,23 @@ Comprehensive guide to Claude Code's advanced capabilities including planning mo
2. [Planning Mode](#planning-mode) 2. [Planning Mode](#planning-mode)
3. [Extended Thinking](#extended-thinking) 3. [Extended Thinking](#extended-thinking)
4. [Background Tasks](#background-tasks) 4. [Background Tasks](#background-tasks)
5. [Permission Mode](#permission-mode) 5. [Scheduled Tasks](#scheduled-tasks)
6. [Headless Mode](#headless-mode) 6. [Permission Mode](#permission-mode)
7. [Session Management](#session-management) 7. [Headless Mode](#headless-mode)
8. [Interactive Features](#interactive-features) 8. [Session Management](#session-management)
9. [Remote Control](#remote-control) 9. [Interactive Features](#interactive-features)
10. [Web Sessions](#web-sessions) 10. [Chrome Integration](#chrome-integration)
11. [Desktop App](#desktop-app) 11. [Remote Control](#remote-control)
12. [Task List](#task-list) 12. [Web Sessions](#web-sessions)
13. [Prompt Suggestions](#prompt-suggestions) 13. [Desktop App](#desktop-app)
14. [Git Worktrees](#git-worktrees) 14. [Task List](#task-list)
15. [Sandboxing](#sandboxing) 15. [Prompt Suggestions](#prompt-suggestions)
16. [Managed Settings (Enterprise)](#managed-settings-enterprise) 16. [Git Worktrees](#git-worktrees)
17. [Configuration and Settings](#configuration-and-settings) 17. [Sandboxing](#sandboxing)
18. [Best Practices](#best-practices) 18. [Managed Settings (Enterprise)](#managed-settings-enterprise)
19. [Related Concepts](#related-concepts) 19. [Configuration and Settings](#configuration-and-settings)
20. [Best Practices](#best-practices)
21. [Related Concepts](#related-concepts)
--- ---
@@ -447,6 +449,72 @@ Claude: [Shows linter output from bg-5002]
--- ---
## Scheduled Tasks
Scheduled Tasks let you run prompts automatically on a recurring schedule or as one-time reminders. Tasks are session-scoped — they run while Claude Code is active and are cleared when the session ends. Available since v2.1.72+.
### The `/loop` command
```bash
# Explicit interval
/loop 5m check if the deployment finished
# Natural language
/loop check build status every 30 minutes
```
Standard 5-field cron expressions are also supported for precise scheduling.
### One-time reminders
Set reminders that fire once at a specific time:
```
remind me at 3pm to push the release branch
in 45 minutes, run the integration tests
```
### Managing scheduled tasks
| Tool | Description |
|------|-------------|
| `CronCreate` | Create a new scheduled task |
| `CronList` | List all active scheduled tasks |
| `CronDelete` | Remove a scheduled task |
**Limits and behavior**:
- Up to **50 scheduled tasks** per session
- Session-scoped — cleared when the session ends
- Recurring tasks auto-expire after **3 days**
- Tasks only fire while Claude Code is running — no catch-up for missed fires
### Behavior details
| Aspect | Detail |
|--------|--------|
| **Recurring jitter** | Up to 10% of the interval (max 15 minutes) |
| **One-shot jitter** | Up to 90 seconds on :00/:30 boundaries |
| **Missed fires** | No catch-up — skipped if Claude Code was not running |
| **Persistence** | Not persisted across restarts |
### Disabling scheduled tasks
```bash
export CLAUDE_CODE_DISABLE_CRON=1
```
### Example: monitoring a deployment
```
/loop 5m check the deployment status of the staging environment.
If the deploy succeeded, notify me and stop looping.
If it failed, show the error logs.
```
> **Tip**: Scheduled tasks are session-scoped. For persistent automation that survives restarts, use CI/CD pipelines, GitHub Actions, or Desktop App scheduled tasks instead.
---
## Permission Modes ## Permission Modes
Permission modes control what actions Claude can take without explicit approval. Permission modes control what actions Claude can take without explicit approval.
@@ -749,6 +817,79 @@ Claude Code supports keyboard shortcuts for efficiency. Here's the complete refe
| `Tab` | Autocomplete | | `Tab` | Autocomplete |
| `↑ / ↓` | Command history | | `↑ / ↓` | Command history |
### Customizing keybindings
Create custom keyboard shortcuts by running `/keybindings`, which opens `~/.claude/keybindings.json` for editing (v2.1.18+).
**Configuration format**:
```json
{
"$schema": "https://www.schemastore.org/claude-code-keybindings.json",
"bindings": [
{
"context": "Chat",
"bindings": {
"ctrl+e": "chat:externalEditor",
"ctrl+u": null,
"ctrl+k ctrl+s": "chat:stash"
}
},
{
"context": "Confirmation",
"bindings": {
"ctrl+a": "confirmation:yes"
}
}
]
}
```
Set a binding to `null` to unbind a default shortcut.
### Available contexts
Keybindings are scoped to specific UI contexts:
| Context | Key Actions |
|---------|-------------|
| **Chat** | `submit`, `cancel`, `cycleMode`, `modelPicker`, `thinkingToggle`, `undo`, `externalEditor`, `stash`, `imagePaste` |
| **Confirmation** | `yes`, `no`, `previous`, `next`, `nextField`, `cycleMode`, `toggleExplanation` |
| **Global** | `interrupt`, `exit`, `toggleTodos`, `toggleTranscript` |
| **Autocomplete** | `accept`, `dismiss`, `next`, `previous` |
| **HistorySearch** | `search`, `previous`, `next` |
| **Settings** | Context-specific settings navigation |
| **Tabs** | Tab switching and management |
| **Help** | Help panel navigation |
There are 18 contexts total including `Transcript`, `Task`, `ThemePicker`, `Attachments`, `Footer`, `MessageSelector`, `DiffDialog`, `ModelPicker`, and `Select`.
### Chord support
Keybindings support chord sequences (multi-key combinations):
```
"ctrl+k ctrl+s" → Two-key sequence: press ctrl+k, then ctrl+s
"ctrl+shift+p" → Simultaneous modifier keys
```
**Keystroke syntax**:
- **Modifiers**: `ctrl`, `alt` (or `opt`), `shift`, `meta` (or `cmd`)
- **Uppercase implies Shift**: `K` is equivalent to `shift+k`
- **Special keys**: `escape`, `enter`, `return`, `tab`, `space`, `backspace`, `delete`, arrow keys
### Reserved and conflicting keys
| Key | Status | Notes |
|-----|--------|-------|
| `Ctrl+C` | Reserved | Cannot be rebound (interrupt) |
| `Ctrl+D` | Reserved | Cannot be rebound (exit) |
| `Ctrl+B` | Terminal conflict | tmux prefix key |
| `Ctrl+A` | Terminal conflict | GNU Screen prefix key |
| `Ctrl+Z` | Terminal conflict | Process suspend |
> **Tip**: If a shortcut does not work, check for conflicts with your terminal emulator or multiplexer.
### Tab Completion ### Tab Completion
Claude Code provides intelligent tab completion: Claude Code provides intelligent tab completion:
@@ -848,23 +989,123 @@ Use this for quick command execution without switching contexts.
--- ---
## Chrome Integration
Chrome Integration connects Claude Code to your Chrome or Microsoft Edge browser for live web automation and debugging. This is a beta feature available since v2.0.73+ (Edge support added in v1.0.36+).
### Enabling Chrome Integration
**At startup**:
```bash
claude --chrome # Enable Chrome connection
claude --no-chrome # Disable Chrome connection
```
**Within a session**:
```
/chrome
```
Select "Enabled by default" to activate Chrome Integration for all future sessions. Claude Code shares your browser's login state, so it can interact with authenticated web apps.
### Capabilities
| Capability | Description |
|------------|-------------|
| **Live debugging** | Read console logs, inspect DOM elements, debug JavaScript in real time |
| **Design verification** | Compare rendered pages against design mockups |
| **Form validation** | Test form submissions, input validation, and error handling |
| **Web app testing** | Interact with authenticated apps (Gmail, Google Docs, Notion, etc.) |
| **Data extraction** | Scrape and process content from web pages |
| **Session recording** | Record browser interactions as GIF files |
### Site-level permissions
The Chrome extension manages per-site access. Grant or revoke access for specific sites at any time through the extension popup. Claude Code only interacts with sites you have explicitly allowed.
### How it works
Claude Code controls the browser in a visible window — you can watch actions happen in real time. When the browser encounters a login page or CAPTCHA, Claude pauses and waits for you to handle it manually before continuing.
### Known limitations
- **Browser support**: Chrome and Edge only — Brave, Arc, and other Chromium browsers are not supported
- **WSL**: Not available in Windows Subsystem for Linux
- **Third-party providers**: Not supported with Bedrock, Vertex, or Foundry API providers
- **Service worker idle**: The Chrome extension service worker may go idle during extended sessions
> **Tip**: Chrome Integration is a beta feature. Browser support may expand in future releases.
---
## Remote Control ## Remote Control
Remote Control allows you to control a locally running Claude Code instance from Claude.ai or the Claude app. This is useful when you want to interact with Claude Code through a web interface while it runs against your local codebase. Remote Control lets you continue a locally running Claude Code session from your phone, tablet, or any browser. Your local session keeps running on your machine — nothing moves to the cloud. Available on Pro, Max, Team, and Enterprise plans (v2.1.51+).
### Starting Remote Control ### Starting Remote Control
**From the CLI**:
```bash ```bash
# Start with default session name
claude remote-control claude remote-control
# Start with a custom name
claude remote-control --name "Auth Refactor"
``` ```
This starts a Remote Control session that bridges your local Claude Code environment with the Claude.ai web interface. You can then issue commands from the browser that execute against your local file system and tools. **From within a session**:
### Use Cases ```
/remote-control
/remote-control "Auth Refactor"
```
- Control Claude Code from a mobile device or tablet **Available flags**:
- Collaborate with team members through a shared web interface
- Use the richer Claude.ai UI while maintaining local tool execution | Flag | Description |
|------|-------------|
| `--name "title"` | Custom session title for easy identification |
| `--verbose` | Show detailed connection logs |
| `--sandbox` | Enable filesystem and network isolation |
| `--no-sandbox` | Disable sandboxing (default) |
### Connecting to a session
Three ways to connect from another device:
1. **Session URL** — Printed to the terminal when the session starts; open in any browser
2. **QR code** — Press `spacebar` after starting to display a scannable QR code
3. **Find by name** — Browse your sessions at claude.ai/code or in the Claude mobile app (iOS/Android)
### Security
- **No inbound ports** opened on your machine
- **Outbound HTTPS only** over TLS
- **Scoped credentials** — multiple short-lived, narrowly scoped tokens
- **Session isolation** — each remote session is independent
### Remote Control vs Claude Code on the web
| Aspect | Remote Control | Claude Code on Web |
|--------|---------------|-------------------|
| **Execution** | Runs on your machine | Runs on Anthropic cloud |
| **Local tools** | Full access to local MCP servers, files, and CLI | No local dependencies |
| **Use case** | Continue local work from another device | Start fresh from any browser |
### Limitations
- One remote session per Claude Code instance
- Terminal must stay open on the host machine
- Session times out after ~10 minutes if the network is unreachable
### Use cases
- Control Claude Code from a mobile device or tablet while away from your desk
- Use the richer claude.ai UI while maintaining local tool execution
- Quick code reviews on the go with your full local development environment
--- ---
@@ -905,24 +1146,85 @@ Or from within an interactive REPL:
## Desktop App ## Desktop App
The Claude Code Desktop App provides a standalone application for visual diff review and managing multiple sessions. Available for macOS and Windows. The Claude Code Desktop App provides a standalone application with visual diff review, parallel sessions, and integrated connectors. Available for macOS and Windows (Pro, Max, Team, and Enterprise plans).
### Handing Off from CLI ### Installation
If you are in a CLI session and want to switch to the Desktop App: Download from [claude.ai](https://claude.ai) for your platform:
- **macOS**: Universal build (Apple Silicon and Intel)
- **Windows**: x64 and ARM64 installers available
See the [Desktop Quickstart](https://code.claude.com/docs/en/desktop-quickstart) for setup instructions.
### Handing off from CLI
Transfer your current CLI session to the Desktop App:
``` ```
/desktop /desktop
``` ```
This transfers your current session to the Desktop App for a richer visual experience. ### Core features
### Features | Feature | Description |
|---------|-------------|
| **Diff view** | File-by-file visual review with inline comments; Claude reads comments and revises |
| **App preview** | Auto-starts dev servers with an embedded browser for live verification |
| **PR monitoring** | GitHub CLI integration with auto-fix CI failures and auto-merge when checks pass |
| **Parallel sessions** | Multiple sessions in the sidebar with automatic Git worktree isolation |
| **Scheduled tasks** | Recurring tasks (hourly, daily, weekdays, weekly) that run while the app is open |
| **Rich rendering** | Code, markdown, and diagram rendering with syntax highlighting |
- Visual diff review for file changes ### App preview configuration
- Multiple simultaneous sessions in tabs
- Rich rendering of code, markdown, and diagrams Configure dev server behavior in `.claude/launch.json`:
- Available for macOS and Windows
```json
{
"command": "npm run dev",
"port": 3000,
"readyPattern": "ready on",
"persistCookies": true
}
```
### Connectors
Connect external services for richer context:
| Connector | Capability |
|-----------|------------|
| **GitHub** | PR monitoring, issue tracking, code review |
| **Slack** | Notifications, channel context |
| **Linear** | Issue tracking, sprint management |
| **Notion** | Documentation, knowledge base access |
| **Asana** | Task management, project tracking |
| **Calendar** | Schedule awareness, meeting context |
> **Note**: Connectors are not available for remote (cloud) sessions.
### Remote and SSH sessions
- **Remote sessions**: Run on Anthropic cloud infrastructure; continue even when the app is closed. Accessible from claude.ai/code or the Claude mobile app
- **SSH sessions**: Connect to remote machines over SSH with full access to the remote filesystem and tools. Claude Code must be installed on the remote machine
### Permission modes in Desktop
The Desktop App supports the same 4 permission modes as the CLI:
| Mode | Behavior |
|------|----------|
| **Ask permissions** (default) | Review and approve every edit and command |
| **Auto accept edits** | File edits auto-approved; commands require manual approval |
| **Plan mode** | Review approach before any changes are made |
| **Bypass permissions** | Automatic execution (sandbox-only, admin-controlled) |
### Enterprise features
- **Admin console**: Control Code tab access and permission settings for the organization
- **MDM deployment**: Deploy via MDM on macOS or MSIX on Windows
- **SSO integration**: Require single sign-on for organization members
- **Managed settings**: Centrally manage team configuration and model availability
--- ---
@@ -1248,3 +1550,8 @@ For more information about Claude Code and related features:
- [MCP Guide](../05-mcp/) - External data access - [MCP Guide](../05-mcp/) - External data access
- [Hooks Guide](../06-hooks/) - Event-driven automation - [Hooks Guide](../06-hooks/) - Event-driven automation
- [Plugins Guide](../07-plugins/) - Bundled extensions - [Plugins Guide](../07-plugins/) - Bundled extensions
- [Official Scheduled Tasks Documentation](https://code.claude.com/docs/en/scheduled-tasks)
- [Official Chrome Integration Documentation](https://code.claude.com/docs/en/chrome)
- [Official Remote Control Documentation](https://code.claude.com/docs/en/remote-control)
- [Official Keybindings Documentation](https://code.claude.com/docs/en/keybindings)
- [Official Desktop App Documentation](https://code.claude.com/docs/en/desktop)
CATALOG.md
+36 -9
View File
@@ -7,7 +7,7 @@
> Quick reference guide to all Claude Code features: commands, agents, skills, plugins, and hooks. > Quick reference guide to all Claude Code features: commands, agents, skills, plugins, and hooks.
**Navigation**: [Commands](#slash-commands) | [Sub-Agents](#sub-agents) | [Skills](#skills) | [Plugins](#plugins) | [MCP Servers](#mcp-servers) | [Hooks](#hooks) | [Memory](#memory-files) | [New Features](#new-features-february-2026) **Navigation**: [Commands](#slash-commands) | [Sub-Agents](#sub-agents) | [Skills](#skills) | [Plugins](#plugins) | [MCP Servers](#mcp-servers) | [Hooks](#hooks) | [Memory](#memory-files) | [New Features](#new-features-march-2026)
--- ---
@@ -15,14 +15,14 @@
| Feature | Built-in | Examples | Total | Reference | | Feature | Built-in | Examples | Total | Reference |
|---------|----------|----------|-------|-----------| |---------|----------|----------|-------|-----------|
| **Slash Commands** | 40 | 8 | 48 | [01-slash-commands/](01-slash-commands/) | | **Slash Commands** | 55 | 8 | 63 | [01-slash-commands/](01-slash-commands/) |
| **Sub-Agents** | 6 | 10 | 16 | [04-subagents/](04-subagents/) | | **Sub-Agents** | 6 | 10 | 16 | [04-subagents/](04-subagents/) |
| **Skills** | - | 4 | 4 | [03-skills/](03-skills/) | | **Skills** | 5 bundled | 4 | 9 | [03-skills/](03-skills/) |
| **Plugins** | - | 3 | 3 | [07-plugins/](07-plugins/) | | **Plugins** | - | 3 | 3 | [07-plugins/](07-plugins/) |
| **MCP Servers** | 1 | 8 | 9 | [05-mcp/](05-mcp/) | | **MCP Servers** | 1 | 8 | 9 | [05-mcp/](05-mcp/) |
| **Hooks** | 16 events | 7 | 7 | [06-hooks/](06-hooks/) | | **Hooks** | 18 events | 7 | 7 | [06-hooks/](06-hooks/) |
| **Memory** | 7 types | 3 | 3 | [02-memory/](02-memory/) | | **Memory** | 7 types | 3 | 3 | [02-memory/](02-memory/) |
| **Total** | **70** | **43** | **90** | | | **Total** | **92** | **43** | **110** | |
--- ---
@@ -35,15 +35,22 @@ Commands are user-invoked shortcuts that execute specific actions.
| Command | Description | When to Use | | Command | Description | When to Use |
|---------|-------------|-------------| |---------|-------------|-------------|
| `/help` | Show help information | Get started, learn commands | | `/help` | Show help information | Get started, learn commands |
| `/btw` | Side question without adding to context | Quick tangent questions |
| `/chrome` | Configure Chrome integration | Browser automation |
| `/clear` | Clear conversation history | Start fresh, reduce context | | `/clear` | Clear conversation history | Start fresh, reduce context |
| `/model` | Switch AI model | Change performance/cost | | `/diff` | Interactive diff viewer | Review changes |
| `/config` | View/edit configuration | Customize behavior | | `/config` | View/edit configuration | Customize behavior |
| `/status` | Show session status | Check current state | | `/status` | Show session status | Check current state |
| `/agents` | List available agents | See delegation options | | `/agents` | List available agents | See delegation options |
| `/skills` | List available skills | See auto-invoke capabilities | | `/skills` | List available skills | See auto-invoke capabilities |
| `/hooks` | List configured hooks | Debug automation | | `/hooks` | List configured hooks | Debug automation |
| `/insights` | Analyze session patterns | Session optimization |
| `/install-slack-app` | Install Claude Slack app | Slack integration |
| `/keybindings` | Customize keyboard shortcuts | Key customization |
| `/mcp` | List MCP servers | Check external integrations | | `/mcp` | List MCP servers | Check external integrations |
| `/memory` | View loaded memory files | Debug context loading | | `/memory` | View loaded memory files | Debug context loading |
| `/mobile` | Generate mobile QR code | Mobile access |
| `/passes` | View usage passes | Subscription info |
| `/plugin` | Manage plugins | Install/remove extensions | | `/plugin` | Manage plugins | Install/remove extensions |
| `/plan` | Enter planning mode | Complex implementations | | `/plan` | Enter planning mode | Complex implementations |
| `/rewind` | Rewind to checkpoint | Undo changes, explore alternatives | | `/rewind` | Rewind to checkpoint | Undo changes, explore alternatives |
@@ -51,18 +58,21 @@ Commands are user-invoked shortcuts that execute specific actions.
| `/cost` | Show token usage costs | Monitor spending | | `/cost` | Show token usage costs | Monitor spending |
| `/context` | Show context window usage | Manage conversation length | | `/context` | Show context window usage | Manage conversation length |
| `/export` | Export conversation | Save for reference | | `/export` | Export conversation | Save for reference |
| `/extra-usage` | Configure extra usage limits | Rate limit management |
| `/feedback` | Submit feedback or bug report | Report issues |
| `/login` | Authenticate with Anthropic | Access features | | `/login` | Authenticate with Anthropic | Access features |
| `/logout` | Sign out | Switch accounts | | `/logout` | Sign out | Switch accounts |
| `/sandbox` | Toggle sandbox mode | Safe command execution | | `/sandbox` | Toggle sandbox mode | Safe command execution |
| `/vim` | Toggle vim mode | Vim-style editing | | `/vim` | Toggle vim mode | Vim-style editing |
| `/doctor` | Run diagnostics | Troubleshoot issues | | `/doctor` | Run diagnostics | Troubleshoot issues |
| `/reload-plugins` | Reload installed plugins | Plugin management |
| `/release-notes` | Show release notes | Check new features | | `/release-notes` | Show release notes | Check new features |
| `/remote-control` | Enable remote control | Remote access |
| `/permissions` | Manage permissions | Control access | | `/permissions` | Manage permissions | Control access |
| `/session` | Manage sessions | Multi-session workflows | | `/session` | Manage sessions | Multi-session workflows |
| `/rename` | Rename current session | Organize sessions | | `/rename` | Rename current session | Organize sessions |
| `/resume` | Resume previous session | Continue work | | `/resume` | Resume previous session | Continue work |
| `/todo` | View/manage todo list | Track tasks | | `/todo` | View/manage todo list | Track tasks |
| `/todos` | View all project TODOs | Track outstanding items |
| `/tasks` | View background tasks | Monitor async operations | | `/tasks` | View background tasks | Monitor async operations |
| `/copy` | Copy last response to clipboard | Share output quickly | | `/copy` | Copy last response to clipboard | Share output quickly |
| `/teleport` | Transfer session to another machine | Continue work remotely | | `/teleport` | Transfer session to another machine | Continue work remotely |
@@ -72,8 +82,10 @@ Commands are user-invoked shortcuts that execute specific actions.
| `/fork` | Fork current conversation | Explore alternatives | | `/fork` | Fork current conversation | Explore alternatives |
| `/stats` | Show session statistics | Review session metrics | | `/stats` | Show session statistics | Review session metrics |
| `/statusline` | Configure status line | Customize status display | | `/statusline` | Configure status line | Customize status display |
| `/stickers` | View session stickers | Fun rewards |
| `/fast` | Toggle fast output mode | Speed up responses | | `/fast` | Toggle fast output mode | Speed up responses |
| `/terminal-setup` | Configure terminal integration | Setup terminal features | | `/terminal-setup` | Configure terminal integration | Setup terminal features |
| `/upgrade` | Check for updates | Version management |
### Custom Commands (Examples) ### Custom Commands (Examples)
@@ -171,6 +183,16 @@ Auto-invoked capabilities with instructions, scripts, and templates.
cp -r 03-skills/* ~/.claude/skills/ cp -r 03-skills/* ~/.claude/skills/
``` ```
### Bundled Skills
| Skill | Description | When Auto-Invoked |
|-------|-------------|-------------------|
| `/simplify` | Review code for quality | After writing code |
| `/batch` | Run prompts on multiple files | Batch operations |
| `/debug` | Debug failing tests/errors | Debugging sessions |
| `/loop` | Run prompts on interval | Recurring tasks |
| `/claude-api` | Build apps with Claude API | API development |
--- ---
## Plugins ## Plugins
@@ -279,6 +301,8 @@ Event-driven automation that executes shell commands on Claude Code events.
| `WorktreeCreate` | Worktree created | Git worktree created | Setup worktree environment | | `WorktreeCreate` | Worktree created | Git worktree created | Setup worktree environment |
| `WorktreeRemove` | Worktree removed | Git worktree removed | Cleanup worktree resources | | `WorktreeRemove` | Worktree removed | Git worktree removed | Cleanup worktree resources |
| `ConfigChange` | Configuration updated | Settings modified | React to config changes | | `ConfigChange` | Configuration updated | Settings modified | React to config changes |
| `InstructionsLoaded` | Instructions loaded | Memory files processed | Custom instruction handling |
| `Setup` | Agent setup | Agent initialization | Environment configuration |
| `TeammateIdle` | Teammate agent idle | Agent team coordination | Distribute work | | `TeammateIdle` | Teammate agent idle | Agent team coordination | Distribute work |
| `TaskCompleted` | Task finished | Background task done | Post-task processing | | `TaskCompleted` | Task finished | Background task done | Post-task processing |
@@ -354,7 +378,7 @@ cp 02-memory/personal-CLAUDE.md ~/.claude/CLAUDE.md
--- ---
## New Features (February 2026) ## New Features (March 2026)
| Feature | Description | How to Use | | Feature | Description | How to Use |
|---------|-------------|------------| |---------|-------------|------------|
@@ -368,6 +392,9 @@ cp 02-memory/personal-CLAUDE.md ~/.claude/CLAUDE.md
| **Sandboxing** | Isolated execution environments for safety | Use `/sandbox` to toggle; runs commands in restricted environments | | **Sandboxing** | Isolated execution environments for safety | Use `/sandbox` to toggle; runs commands in restricted environments |
| **MCP OAuth** | OAuth authentication for MCP servers | Configure OAuth credentials in MCP server settings for secure access | | **MCP OAuth** | OAuth authentication for MCP servers | Configure OAuth credentials in MCP server settings for secure access |
| **MCP Tool Search** | Search and discover MCP tools dynamically | Use tool search to find available MCP tools across connected servers | | **MCP Tool Search** | Search and discover MCP tools dynamically | Use tool search to find available MCP tools across connected servers |
| **Scheduled Tasks** | Set up recurring tasks with `/loop` and cron tools | Use `/loop 5m /command` or CronCreate tool |
| **Chrome Integration** | Browser automation with headless Chromium | Use `--chrome` flag or `/chrome` command |
| **Keyboard Customization** | Customize keybindings including chord support | Use `/keybindings` or edit `~/.claude/keybindings.json` |
--- ---
@@ -427,4 +454,4 @@ chmod +x ~/.claude/hooks/*.sh
--- ---
**Last Updated**: February 2026 **Last Updated**: March 2026
INDEX.md
+32 -1
View File
@@ -221,6 +221,7 @@ Event-driven automation scripts that execute automatically.
**Hook Types**: **Hook Types**:
- Tool Hooks: PreToolUse:*, PostToolUse:* - Tool Hooks: PreToolUse:*, PostToolUse:*
- Session Hooks: Stop, SubagentStop, SubagentStart - Session Hooks: Stop, SubagentStop, SubagentStart
- Agent Hooks: InstructionsLoaded, Setup
- Lifecycle Hooks: Notification, ConfigChange, WorktreeCreate, WorktreeRemove - Lifecycle Hooks: Notification, ConfigChange, WorktreeCreate, WorktreeRemove
--- ---
@@ -366,6 +367,11 @@ Advanced capabilities for complex workflows.
| `README.md` | Complete guide | All advanced features documentation | | `README.md` | Complete guide | All advanced features documentation |
| `config-examples.json` | Configuration examples | 10+ use-case-specific configurations | | `config-examples.json` | Configuration examples | 10+ use-case-specific configurations |
| `planning-mode-examples.md` | Planning examples | REST API, database migration, refactoring | | `planning-mode-examples.md` | Planning examples | REST API, database migration, refactoring |
| Scheduled Tasks | Recurring tasks with `/loop` and cron tools | Automated recurring workflows |
| Chrome Integration | Browser automation via headless Chromium | Web testing and scraping |
| Remote Control (expanded) | Connection methods, security, comparison table | Remote session management |
| Keyboard Customization | Custom keybindings, chord support, contexts | Personalized shortcuts |
| Desktop App (expanded) | Connectors, launch.json, enterprise features | Desktop integration |
| | | | | | | |
**Advanced Features Covered**: **Advanced Features Covered**:
@@ -413,6 +419,31 @@ Advanced capabilities for complex workflows.
- Environment-specific configs - Environment-specific configs
- Per-project customization - Per-project customization
### Scheduled Tasks
- Recurring tasks with `/loop` command
- Cron tools: CronCreate, CronList, CronDelete
- Automated recurring workflows
### Chrome Integration
- Browser automation via headless Chromium
- Web testing and scraping capabilities
- Page interaction and data extraction
### Remote Control (expanded)
- Connection methods and protocols
- Security considerations and best practices
- Comparison table of remote access options
### Keyboard Customization
- Custom keybindings configuration
- Chord support for multi-key shortcuts
- Context-aware keybinding activation
### Desktop App (expanded)
- Connectors for IDE integration
- launch.json configuration
- Enterprise features and deployment
--- ---
## 10. CLI Usage (1 file) ## 10. CLI Usage (1 file)
@@ -841,7 +872,7 @@ Want to add more examples? Follow the structure:
--- ---
**Last Updated**: February 2026 **Last Updated**: March 2026
**Total Examples**: 100+ files **Total Examples**: 100+ files
**Categories**: 10 features **Categories**: 10 features
**Hooks**: 8 automation scripts **Hooks**: 8 automation scripts
LEARNING-ROADMAP.md
+18 -5
View File
@@ -369,6 +369,7 @@ Before starting Level 3, make sure you're comfortable with these Level 2 concept
✅ Background task management ✅ Background task management
✅ Auto Memory for learned preferences ✅ Auto Memory for learned preferences
✅ Remote control, desktop app, and web sessions ✅ Remote control, desktop app, and web sessions
✅ Agent Teams for multi-agent collaboration
#### Hands-on Exercises #### Hands-on Exercises
@@ -390,6 +391,14 @@ claude --permission-mode acceptEdits "refactor the auth module"
# 4. Run tests in background # 4. Run tests in background
# 5. If tests fail, rewind to checkpoint # 5. If tests fail, rewind to checkpoint
# 6. Try alternative approach # 6. Try alternative approach
# Exercise 5: Enable agent teams
export CLAUDE_AGENT_TEAMS=1
# Ask Claude: "Implement feature X using a team approach"
# Exercise 6: Scheduled tasks
/loop 5m /check-status
# Or use CronCreate for persistent scheduled tasks
``` ```
#### Success Criteria #### Success Criteria
@@ -398,6 +407,8 @@ claude --permission-mode acceptEdits "refactor the auth module"
- [ ] Toggled extended thinking with Alt+T / Option+T - [ ] Toggled extended thinking with Alt+T / Option+T
- [ ] Used background tasks for long operations - [ ] Used background tasks for long operations
- [ ] Understand Remote Control, Desktop App, and Web sessions - [ ] Understand Remote Control, Desktop App, and Web sessions
- [ ] Enabled and used Agent Teams for collaborative tasks
- [ ] Used `/loop` for recurring tasks or scheduled monitoring
#### Next Steps #### Next Steps
- Read: [09-advanced-features/README.md](09-advanced-features/README.md) - Read: [09-advanced-features/README.md](09-advanced-features/README.md)
@@ -672,10 +683,12 @@ Once you've completed all milestones:
4. **Try Web Sessions** - Use Claude Code through browser-based interfaces for remote development 4. **Try Web Sessions** - Use Claude Code through browser-based interfaces for remote development
5. **Use the Desktop App** - Access Claude Code features through the native desktop application 5. **Use the Desktop App** - Access Claude Code features through the native desktop application
6. **Leverage Auto Memory** - Let Claude learn your preferences automatically over time 6. **Leverage Auto Memory** - Let Claude learn your preferences automatically over time
7. **Contribute examples** - Share with the community 7. **Set up Agent Teams** - Coordinate multiple agents on complex, multi-faceted tasks
8. **Mentor others** - Help teammates learn 8. **Use Scheduled Tasks** - Automate recurring checks with `/loop` and cron tools
9. **Optimize workflows** - Continuously improve based on usage 9. **Contribute examples** - Share with the community
10. **Stay updated** - Follow Claude Code releases and new features 10. **Mentor others** - Help teammates learn
11. **Optimize workflows** - Continuously improve based on usage
12. **Stay updated** - Follow Claude Code releases and new features
--- ---
@@ -703,7 +716,7 @@ Once you've completed all milestones:
--- ---
**Last Updated**: February 2026 **Last Updated**: March 2026
**Maintained by**: Claude How-To Contributors **Maintained by**: Claude How-To Contributors
**License**: Educational purposes, free to use and adapt **License**: Educational purposes, free to use and adapt
QUICK_REFERENCE.md
+26 -1
View File
@@ -129,6 +129,7 @@ claude -r "session" # Resume session by name/ID
| **Git Worktrees** | Built-in | `/worktree` | | **Git Worktrees** | Built-in | `/worktree` |
| **Auto Memory** | Built-in | Auto-saves to CLAUDE.md | | **Auto Memory** | Built-in | Auto-saves to CLAUDE.md |
| **Task List** | Built-in | `/task list` | | **Task List** | Built-in | `/task list` |
| **Bundled Skills** | Built-in | `/simplify`, `/loop`, `/claude-api` |
--- ---
@@ -237,6 +238,26 @@ claude --permission-mode plan
# If you need to rewind: press Esc+Esc or use /rewind # If you need to rewind: press Esc+Esc or use /rewind
``` ```
### Agent Teams
```bash
# Enable agent teams
export CLAUDE_AGENT_TEAMS=1
# Or in settings.json
{ "agentTeams": { "enabled": true } }
# Start with: "Implement feature X using a team approach"
```
### Scheduled Tasks
```bash
# Run a command every 5 minutes
/loop 5m /check-status
# One-time reminder
/loop 30m "remind me to check the deploy"
```
--- ---
## 📁 File Locations Reference ## 📁 File Locations Reference
@@ -352,7 +373,7 @@ cp -r 03-skills/code-review ~/.claude/skills/
--- ---
## New Features (February 2026) ## New Features (March 2026)
| Feature | Description | Usage | | Feature | Description | Usage |
|---------|-------------|-------| |---------|-------------|-------|
@@ -363,6 +384,10 @@ cp -r 03-skills/code-review ~/.claude/skills/
| **Auto Memory** | Automatic memory saving from conversations | Claude auto-saves key context to CLAUDE.md | | **Auto Memory** | Automatic memory saving from conversations | Claude auto-saves key context to CLAUDE.md |
| **Git Worktrees** | Isolated workspaces for parallel development | `/worktree` to create isolated workspace | | **Git Worktrees** | Isolated workspaces for parallel development | `/worktree` to create isolated workspace |
| **Model Selection** | Switch between Sonnet 4.6 and Opus 4.6 | `/model` or `--model` flag | | **Model Selection** | Switch between Sonnet 4.6 and Opus 4.6 | `/model` or `--model` flag |
| **Agent Teams** | Coordinate multiple agents on tasks | Enable with `CLAUDE_AGENT_TEAMS=1` env var |
| **Scheduled Tasks** | Recurring tasks with `/loop` | `/loop 5m /command` or CronCreate tool |
| **Chrome Integration** | Browser automation | `--chrome` flag or `/chrome` command |
| **Keyboard Customization** | Custom keybindings | `/keybindings` command |
--- ---
claude_concepts_guide.md
+39 -2
View File
@@ -534,6 +534,10 @@ graph TB
| Long-running analysis | ✅ Yes | Prevents main context exhaustion | | Long-running analysis | ✅ Yes | Prevents main context exhaustion |
| Single task | ❌ No | Adds latency unnecessarily | | Single task | ❌ No | Adds latency unnecessarily |
### Agent Teams
Agent Teams coordinate multiple agents working on related tasks. Rather than delegating to one subagent at a time, Agent Teams allow the main agent to orchestrate a group of agents that collaborate, share intermediate results, and work toward a common goal. This is useful for large-scale tasks like full-stack feature development where a frontend agent, backend agent, and testing agent work in parallel.
--- ---
## Memory ## Memory
@@ -1302,6 +1306,20 @@ graph TB
E --> E2["Fill forms"] E --> E2["Fill forms"]
``` ```
### Bundled Skills
Claude Code now includes 5 bundled skills available out of the box:
| Skill | Command | Purpose |
|-------|---------|---------|
| **Simplify** | `/simplify` | Simplify complex code or explanations |
| **Batch** | `/batch` | Run operations across multiple files or items |
| **Debug** | `/debug` | Systematic debugging of issues with root cause analysis |
| **Loop** | `/loop` | Schedule recurring tasks on a timer |
| **Claude API** | `/claude-api` | Interact with the Anthropic API directly |
These bundled skills are always available and do not require installation or configuration.
### Practical Examples ### Practical Examples
#### Example 1: Custom Code Review Skill #### Example 1: Custom Code Review Skill
@@ -2800,6 +2818,8 @@ Hooks are event-driven shell commands that execute automatically in response to
| **WorktreeCreate** | When a worktree is created | Environment setup, dependency install | | **WorktreeCreate** | When a worktree is created | Environment setup, dependency install |
| **WorktreeRemove** | When a worktree is removed | Cleanup, resource deallocation | | **WorktreeRemove** | When a worktree is removed | Cleanup, resource deallocation |
| **ConfigChange** | When configuration changes | Validation, propagation | | **ConfigChange** | When configuration changes | Validation, propagation |
| **InstructionsLoaded** | When memory/instruction files are loaded | Validation, transformation, augmentation |
| **Setup** | During agent initialization | Environment preparation, dependency checks |
### Common Hooks ### Common Hooks
@@ -3004,6 +3024,23 @@ cat error.log | claude -p "explain this error"
claude -p --output-format json "list all functions in src/" claude -p --output-format json "list all functions in src/"
``` ```
### Scheduled Tasks
Run tasks on a repeating schedule using the `/loop` command.
**Usage:**
```bash
/loop every 30m "Run tests and report failures"
/loop every 2h "Check for dependency updates"
/loop every 1d "Generate daily summary of code changes"
```
Scheduled tasks run in the background and report results when complete. They are useful for continuous monitoring, periodic checks, and automated maintenance workflows.
### Chrome Integration
Claude Code can integrate with the Chrome browser for web automation tasks. This enables capabilities like navigating web pages, filling forms, taking screenshots, and extracting data from websites directly within your development workflow.
### Session Management ### Session Management
Manage multiple work sessions. Manage multiple work sessions.
@@ -3070,6 +3107,6 @@ Complete configuration example:
--- ---
*Last updated: February 2026* *Last updated: March 2026*
*For Claude Haiku 4.5, Sonnet 4.6, and Opus 4.6* *For Claude Haiku 4.5, Sonnet 4.6, and Opus 4.6*
*Now includes: Hooks, Checkpoints, Planning Mode, Extended Thinking, Background Tasks, Permission Modes, Headless Mode, Session Management, and Auto Memory* *Now includes: Hooks, Checkpoints, Planning Mode, Extended Thinking, Background Tasks, Permission Modes, Headless Mode, Session Management, Auto Memory, Agent Teams, Scheduled Tasks, Chrome Integration, and Bundled Skills*
resources.md
+11 -1
View File
@@ -15,6 +15,12 @@
| MCP Servers | Official MCP server implementations | [github.com/modelcontextprotocol/servers](https://github.com/modelcontextprotocol/servers) | | MCP Servers | Official MCP server implementations | [github.com/modelcontextprotocol/servers](https://github.com/modelcontextprotocol/servers) |
| Anthropic Cookbook | Code examples and tutorials | [github.com/anthropics/anthropic-cookbook](https://github.com/anthropics/anthropic-cookbook) | | Anthropic Cookbook | Code examples and tutorials | [github.com/anthropics/anthropic-cookbook](https://github.com/anthropics/anthropic-cookbook) |
| Claude Code Skills | Community skills repository | [github.com/anthropics/skills](https://github.com/anthropics/skills) | | Claude Code Skills | Community skills repository | [github.com/anthropics/skills](https://github.com/anthropics/skills) |
| Agent Teams | Multi-agent coordination and collaboration | [code.claude.com/docs/en/agent-teams](https://code.claude.com/docs/en/agent-teams) |
| Scheduled Tasks | Recurring tasks with /loop and cron | [code.claude.com/docs/en/scheduled-tasks](https://code.claude.com/docs/en/scheduled-tasks) |
| Chrome Integration | Browser automation | [code.claude.com/docs/en/chrome](https://code.claude.com/docs/en/chrome) |
| Keybindings | Keyboard shortcut customization | [code.claude.com/docs/en/keybindings](https://code.claude.com/docs/en/keybindings) |
| Desktop App | Native desktop application | [code.claude.com/docs/en/desktop](https://code.claude.com/docs/en/desktop) |
| Remote Control | Remote session control | [code.claude.com/docs/en/remote-control](https://code.claude.com/docs/en/remote-control) |
## Anthropic Engineering Blog ## Anthropic Engineering Blog
@@ -219,7 +225,7 @@ These steps capture the core recommendations for smooth workflows with Claude Co
--- ---
## New Features & Capabilities (February 2026) ## New Features & Capabilities (March 2026)
### Key Feature Resources ### Key Feature Resources
@@ -233,3 +239,7 @@ These steps capture the core recommendations for smooth workflows with Claude Co
| **Permission Modes** | Fine-grained control: default, acceptEdits, plan, dontAsk, bypassPermissions | [Advanced Features](09-advanced-features/) | | **Permission Modes** | Fine-grained control: default, acceptEdits, plan, dontAsk, bypassPermissions | [Advanced Features](09-advanced-features/) |
| **7-Tier Memory** | Managed Policy, Project, Project Rules, User, User Rules, Local, Auto Memory | [Memory Guide](02-memory/) | | **7-Tier Memory** | Managed Policy, Project, Project Rules, User, User Rules, Local, Auto Memory | [Memory Guide](02-memory/) |
| **Hook Events** | PreToolUse, PostToolUse, Stop, SubagentStop, SubagentStart, Notification, and more | [Hooks Guide](06-hooks/) | | **Hook Events** | PreToolUse, PostToolUse, Stop, SubagentStop, SubagentStart, Notification, and more | [Hooks Guide](06-hooks/) |
| **Agent Teams** | Coordinate multiple agents working together on complex tasks | [Subagents Guide](04-subagents/) |
| **Scheduled Tasks** | Set up recurring tasks with `/loop` and cron tools | [Advanced Features](09-advanced-features/) |
| **Chrome Integration** | Browser automation with headless Chromium | [Advanced Features](09-advanced-features/) |
| **Keyboard Customization** | Customize keybindings including chord sequences | [Advanced Features](09-advanced-features/) |
update-plan.md
+29 -75
View File
@@ -109,97 +109,51 @@ Content existed but was missing significant features that shipped in Jan–Mar 2
--- ---
## Phase 3: New Feature Coverage (Content Gaps) ## Phase 3: New Feature Coverage (Content Gaps) ✅ COMPLETED
These are significant features that exist in official docs but have no corresponding content in the guide. Each needs a decision: create tutorial content, add a TODO note, or skip. > **Completed**: 2026-03-13
### Task 3.1: Create Agent Teams tutorial content These are significant features that existed in official docs but had no or minimal corresponding content in the guide. All 8 tasks completed — new tutorial content added.
- **Directory**: `04-subagents/README.md` (add section) or new file ### Task 3.1: Expand Agent Teams tutorial content ✅
- **Content needed**:
- What agent teams are vs. subagents (comparison table)
- How to enable (`CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1`)
- Starting a team, display modes (in-process vs tmux)
- Task assignment, teammate messaging, plan approval
- Architecture: team lead, teammates, shared task list, mailbox
- Best practices: team size (3-5), task sizing, file conflict avoidance
- Limitations (experimental, no session resumption, no nested teams)
- **Priority**: High — major new capability
- **Source**: `code.claude.com/docs/en/agent-teams`
### Task 3.2: Create Scheduled Tasks / `/loop` documentation - **File modified**: `04-subagents/README.md`
- **Change**: Expanded Agent Teams section from 25 lines to ~140 lines. Added subagents vs agent teams comparison table, enabling instructions (env var + settings.json), starting a team example, display modes table, Mermaid architecture diagram (Team Lead → Shared Task List → Teammates + Mailbox), task assignment and messaging, plan approval workflow, hook events table (TeammateIdle, TaskCompleted), best practices (5 items), limitations (6 items)
- **Directory**: `09-advanced-features/README.md` (add section) ### Task 3.2: Add Scheduled Tasks / `/loop` documentation ✅
- **Content needed**:
- `/loop [interval] <prompt>` command usage
- Cron scheduling tools for recurring prompts
- `CLAUDE_CODE_DISABLE_CRON` env var
- Use cases: polling deploys, babysitting PRs
- **Priority**: Medium — useful automation feature
- **Source**: `code.claude.com/docs/en/scheduled-tasks`
### Task 3.3: Create Chrome Integration section - **File modified**: `09-advanced-features/README.md`
- **Change**: Added new "Scheduled Tasks" section (~80 lines) between Background Tasks and Permission Modes. Covers `/loop` command syntax, one-time reminders, CronCreate/CronList/CronDelete tools table, behavior details table (jitter, missed fires, persistence), `CLAUDE_CODE_DISABLE_CRON` env var, deployment monitoring example
- **Directory**: `09-advanced-features/README.md` (add section) ### Task 3.3: Add Chrome Integration section ✅
- **Content needed**:
- `--chrome` / `--no-chrome` flags
- `/chrome` command for configuration
- Browser debugging and web testing capabilities
- **Priority**: Medium — beta feature but useful for web developers
- **Source**: `code.claude.com/docs/en/chrome`
### Task 3.4: Create Remote Control section - **File modified**: `09-advanced-features/README.md`
- **Change**: Added new "Chrome Integration" section (~65 lines) between Interactive Features and Remote Control. Covers enabling via `--chrome`/`/chrome`, capabilities table (6 items), site-level permissions, how it works, known limitations (Brave/Arc, WSL, third-party providers)
- **Directory**: `09-advanced-features/README.md` (add section or expand existing) ### Task 3.4: Expand Remote Control section ✅
- **Content needed**:
- `/remote-control` command (alias `/rc`)
- `claude remote-control` CLI subcommand
- Controlling local sessions from claude.ai or Claude app
- Optional name argument for custom session titles
- **Priority**: Medium — enables mobile/cross-device workflows
- **Source**: `code.claude.com/docs/en/remote-control`
### Task 3.5: Document Plugin Marketplaces - **File modified**: `09-advanced-features/README.md`
- **Change**: Expanded Remote Control from 18 lines to ~75 lines. Added version/plan requirements, CLI + REPL commands, flags table (--name, --verbose, --sandbox), 3 connection methods (QR code, URL, find by name), security details, Remote Control vs Claude Code on Web comparison table, limitations
- **File**: `07-plugins/README.md` (add section) ### Task 3.5: Expand Plugin Marketplaces ✅
- **Content needed**:
- Creating and distributing plugin marketplaces
- Official marketplace submission (claude.ai/settings/plugins/submit)
- `/plugin marketplace` commands
- `strictKnownMarketplaces`, `extraKnownMarketplaces` settings
- **Priority**: Medium — plugin ecosystem is maturing
- **Source**: `code.claude.com/docs/en/plugin-marketplaces`, `code.claude.com/docs/en/discover-plugins`
### Task 3.6: Document LSP Servers in Plugins - **File modified**: `07-plugins/README.md`
- **Change**: Added ~80 lines after existing marketplace section. New subsections: marketplace.json schema with code example and field reference table, plugin source types table (6 sources: relative, GitHub, git URL, git-subdir, npm, pip), distribution methods, strict mode with `strictKnownMarketplaces` allowlist
- **File**: `07-plugins/README.md` (add section) ### Task 3.6: Expand LSP Servers in Plugins ✅
- **Content needed**:
- `.lsp.json` configuration format
- Language server setup for code intelligence
- Example Go/Python/TypeScript LSP configs
- **Priority**: Low — niche feature, official marketplace covers common languages
- **Source**: `code.claude.com/docs/en/plugins-reference#lsp-servers`
### Task 3.7: Document Keyboard Shortcuts Customization - **File modified**: `07-plugins/README.md`
- **Change**: Expanded LSP section from 15 lines to ~70 lines. Added `.lsp.json` configuration locations, 12-field reference table, 3 example configs (Go/gopls, Python/pyright, TypeScript), available LSP plugins table, LSP capabilities summary
- **File**: `09-advanced-features/README.md` (add section) ### Task 3.7: Expand Keyboard Shortcuts Customization ✅
- **Content needed**:
- `/keybindings` command
- `~/.claude/keybindings.json` configuration
- Available keybinding actions (voice:pushToTalk, chat:newline, etc.)
- Context-aware bindings, chord support
- **Priority**: Low — power user feature
- **Source**: `code.claude.com/docs/en/keybindings`
### Task 3.8: Document Desktop App - **File modified**: `09-advanced-features/README.md`
- **Change**: Added ~60 lines after existing keyboard shortcuts tables. New subsections: customizing keybindings (`/keybindings` command, v2.1.18+), JSON configuration format example, available contexts table (18 contexts), chord support with keystroke syntax, reserved and conflicting keys table
- **File**: `09-advanced-features/README.md` (expand existing mention) ### Task 3.8: Expand Desktop App ✅
- **Content needed**:
- Download links (macOS, Windows, Windows ARM64) - **File modified**: `09-advanced-features/README.md`
- `/desktop` command to hand off session - **Change**: Expanded Desktop App from 20 lines to ~100 lines. Added installation info, core features table (6 features), `.claude/launch.json` app preview config, connectors table (6 connectors), remote/SSH sessions, permission modes table, enterprise features
- Visual diff review, multiple sessions, cloud session management
- **Priority**: Low — mentioned briefly already, needs expansion
- **Source**: `code.claude.com/docs/en/desktop`, `code.claude.com/docs/en/desktop-quickstart`
--- ---
@@ -282,7 +236,7 @@ After Phases 1-3, these reference documents need updates to reflect all changes.
|-------|-------|----------|-----------------| |-------|-------|----------|-----------------|
| **Phase 1** | 8 tasks | ✅ Completed 2026-03-13 | Small edits, 1 subagent batch | | **Phase 1** | 8 tasks | ✅ Completed 2026-03-13 | Small edits, 1 subagent batch |
| **Phase 2** | 10 tasks (2 skipped) | ✅ Completed 2026-03-13 | 6 files modified, 2 already complete | | **Phase 2** | 10 tasks (2 skipped) | ✅ Completed 2026-03-13 | 6 files modified, 2 already complete |
| **Phase 3** | 8 tasks | Valuable — new feature tutorials | New content creation, 3-4 subagent batches | | **Phase 3** | 8 tasks | ✅ Completed 2026-03-13 | 3 files modified, ~612 net lines added |
| **Phase 4** | 6 tasks | Required — cascade reference updates | Medium edits after Phases 1-3 | | **Phase 4** | 6 tasks | Required — cascade reference updates | Medium edits after Phases 1-3 |
| **Phase 5** | 4 tasks | Required — quality gate before merge | Automated + manual review | | **Phase 5** | 4 tasks | Required — quality gate before merge | Automated + manual review |