diff --git a/01-slash-commands/README.md b/01-slash-commands/README.md index 20bc3a1..88315bb 100644 --- a/01-slash-commands/README.md +++ b/01-slash-commands/README.md @@ -26,6 +26,7 @@ Built-in commands are shortcuts for common actions. There are **60+ built-in com | `/agents` | Manage agent configurations | | `/branch [name]` | Branch conversation into a new session (alias: `/fork`). Note: `/fork` renamed to `/branch` in v2.1.77 | | `/btw ` | Ask an ephemeral side question while Claude is working on the main task; doesn't pollute the main conversation context | +| `/cd ` | Move the session to a new working directory without breaking the prompt cache (added v2.1.169) | | `/chrome` | Configure Chrome browser integration | | `/clear` | Clear conversation (aliases: `/reset`, `/new`) | | `/color [color\|default]` | Set prompt bar color. Bare `/color` (no args) picks a random session color (v2.1.128+); pass a color name or hex to set explicitly. | @@ -99,6 +100,8 @@ Built-in commands are shortcuts for common actions. There are **60+ built-in com | `/voice` | Toggle push-to-talk voice dictation | | `/workflows` | View running and completed dynamic workflow runs (added v2.1.154). See [Dynamic Workflows](../09-advanced-features/README.md#dynamic-workflows) | +> **Why `/cd` matters:** changing directories used to lose cache warmth (making the next turn slower and costlier); `/cd` preserves the prompt cache across the switch. + ### Bundled Skills These skills ship with Claude Code and are invoked like slash commands: @@ -627,8 +630,8 @@ If both exist with the same name, the **skill takes precedence**. Remove one or --- -**Last Updated**: June 2, 2026 -**Claude Code Version**: 2.1.160 +**Last Updated**: June 10, 2026 +**Claude Code Version**: 2.1.170 **Sources**: - https://code.claude.com/docs/en/slash-commands - https://code.claude.com/docs/en/interactive-mode diff --git a/02-memory/README.md b/02-memory/README.md index 64291c3..7924658 100644 --- a/02-memory/README.md +++ b/02-memory/README.md @@ -1198,11 +1198,12 @@ For the most up-to-date information, refer to the official Claude Code documenta - [Official Memory Docs](https://code.claude.com/docs/en/memory) - Anthropic documentation --- -**Last Updated**: June 2, 2026 -**Claude Code Version**: 2.1.160 +**Last Updated**: June 10, 2026 +**Claude Code Version**: 2.1.170 **Sources**: - https://code.claude.com/docs/en/memory - https://code.claude.com/docs/en/settings +- https://code.claude.com/docs/en/cli-reference - https://github.com/anthropics/claude-code/releases/tag/v2.1.117 - https://github.com/anthropics/claude-code/releases/tag/v2.1.144 - https://github.com/anthropics/claude-code/releases/tag/v2.1.145 diff --git a/03-skills/README.md b/03-skills/README.md index 021932c..8a779dc 100644 --- a/03-skills/README.md +++ b/03-skills/README.md @@ -787,6 +787,23 @@ Skills support the `` !`command` `` syntax to inject the output of shell command When `disableSkillShellExecution` is `true`, any `` !`command` `` markers in a skill are left as literal text instead of being executed — removing the skill-level shell-injection attack surface without disabling skills themselves. Consider combining this with an `allowedTools` allowlist for defense in depth. +### Hiding bundled skills (`disableBundledSkills`) + +The `disableBundledSkills` setting (added in **v2.1.169**) hides the bundled skills, workflows, and commands that ship with Claude Code from the model. Use it when the built-in skills are noise for a given project, or to reduce the model's skill surface: + +```jsonc +// ~/.claude/settings.json or project .claude/settings.json +{ + "disableBundledSkills": true +} +``` + +The equivalent environment-variable form is: + +```bash +export CLAUDE_CODE_DISABLE_BUNDLED_SKILLS=1 +``` + ## Skills vs Other Features | Feature | Invocation | Best For | @@ -858,8 +875,8 @@ Once you start building skills seriously, two things become essential: a library - [Hooks Guide](../06-hooks/) - Event-driven automation --- -**Last Updated**: June 2, 2026 -**Claude Code Version**: 2.1.160 +**Last Updated**: June 10, 2026 +**Claude Code Version**: 2.1.170 **Sources**: - https://code.claude.com/docs/en/skills - https://code.claude.com/docs/en/settings diff --git a/05-mcp/README.md b/05-mcp/README.md index 837cbca..3ba1cf1 100644 --- a/05-mcp/README.md +++ b/05-mcp/README.md @@ -118,6 +118,8 @@ Every MCP stdio server is spawned with `CLAUDE_PROJECT_DIR= **Safety cap on consecutive blocks (v2.1.143)**: If a `Stop` hook returns `"decision": "block"` (or sets `continue: false`) **8 times in a row** for the same turn, Claude Code short-circuits the loop and ends the session with a warning. Override the threshold with the env var `CLAUDE_CODE_STOP_HOOK_BLOCK_CAP=` (set to `0` to disable the cap entirely). This prevents a buggy Stop hook from looping the session forever. +**Return field (v2.1.163):** A `Stop` or `SubagentStop` hook can return `hookSpecificOutput.additionalContext` to give Claude feedback and **continue the turn without surfacing an error label**. Previously, influencing the model from a Stop hook was awkward; now the hook can inject context cleanly, avoiding the error-label behavior of older feedback paths (such as `"decision": "block"`). + +```json +{ + "hookSpecificOutput": { + "hookEventName": "Stop", + "additionalContext": "Reminder: run the test suite before declaring done." + } +} +``` + ### SubagentStart Runs when a subagent begins execution. The matcher input is the agent type name, allowing hooks to target specific subagent types. @@ -1449,8 +1460,8 @@ Edit `~/.claude/settings.json` or `.claude/settings.json` with the hook configur --- -**Last Updated**: June 2, 2026 -**Claude Code Version**: 2.1.160 +**Last Updated**: June 10, 2026 +**Claude Code Version**: 2.1.170 **Sources**: - https://code.claude.com/docs/en/hooks - https://code.claude.com/docs/en/changelog diff --git a/07-plugins/README.md b/07-plugins/README.md index a4c1a5a..7bfb8cc 100644 --- a/07-plugins/README.md +++ b/07-plugins/README.md @@ -736,6 +736,14 @@ claude plugin install plugin-name@marketplace-name /plugin disable plugin-name ``` +### Listing installed plugins (v2.1.163) +Confirm which plugins are active in the current session: +```bash +/plugin list # all installed plugins +/plugin list --enabled # only enabled plugins +/plugin list --disabled # only disabled plugins +``` + ### Local Plugin (for development) ```bash # CLI flag for local testing (repeatable for multiple plugins) @@ -1107,10 +1115,11 @@ The following Claude Code features work together with plugins: --- -**Last Updated**: June 2, 2026 -**Claude Code Version**: 2.1.160 +**Last Updated**: June 10, 2026 +**Claude Code Version**: 2.1.170 **Sources**: - https://code.claude.com/docs/en/plugins +- https://code.claude.com/docs/en/slash-commands - https://code.claude.com/docs/en/plugin-marketplaces - https://github.com/anthropics/claude-code/releases/tag/v2.1.117 - https://github.com/anthropics/claude-code/releases/tag/v2.1.118 diff --git a/09-advanced-features/README.md b/09-advanced-features/README.md index 3050222..e2fd9a8 100644 --- a/09-advanced-features/README.md +++ b/09-advanced-features/README.md @@ -1058,6 +1058,20 @@ claude -p --json-schema '{"type":"object","properties":{"issues":{"type":"array" claude -p --no-session-persistence "one-off analysis" ``` +### Safe Mode (troubleshooting) + +`--safe-mode` (and the `CLAUDE_CODE_SAFE_MODE` environment variable, e.g. `CLAUDE_CODE_SAFE_MODE=1`) starts Claude Code with **all customizations disabled** — CLAUDE.md, plugins, skills, hooks, and MCP servers are all turned off. + +```bash +# Launch with every customization disabled +claude --safe-mode + +# Equivalent via environment variable +CLAUDE_CODE_SAFE_MODE=1 claude +``` + +It is a troubleshooting tool: when a custom config is causing problems, launch in safe mode to isolate whether the issue is in your setup or in Claude Code itself. + --- ## Session Management @@ -2071,6 +2085,18 @@ Since v2.1.83, administrators can deploy multiple managed settings files into a } ``` +### Fallback Models (`fallbackModel`) + +The `fallbackModel` setting lets you configure **up to three** fallback models, tried in order, when the primary model is overloaded or unavailable. + +```json +{ + "fallbackModel": ["claude-opus-4-8", "claude-sonnet-4-6", "claude-haiku-4-5"] +} +``` + +As of **v2.1.166** the `--fallback-model` flag also applies to interactive sessions (not just headless). On a fallback, Claude Code retries an unexpected non-retryable error once; auth, rate-limit, request-size, and transport errors still fail immediately. + ### Environment Variables Override config with environment variables: @@ -2301,9 +2327,10 @@ For more information about Claude Code and related features: --- -**Last Updated**: June 2, 2026 -**Claude Code Version**: 2.1.160 +**Last Updated**: June 10, 2026 +**Claude Code Version**: 2.1.170 **Sources**: +- https://code.claude.com/docs/en/troubleshooting - https://code.claude.com/docs/en/permission-modes - https://code.claude.com/docs/en/interactive-mode - https://code.claude.com/docs/en/settings diff --git a/10-cli/README.md b/10-cli/README.md index 45f8bc6..f201837 100644 --- a/10-cli/README.md +++ b/10-cli/README.md @@ -81,6 +81,7 @@ The older JavaScript bundle is still produced for Windows and for environments t | `--teleport` | Resume web session locally | `claude --teleport` | | `--teammate-mode` | Agent team display mode | `claude --teammate-mode tmux` | | `--bare` | Minimal mode (skip hooks, skills, plugins, MCP, auto memory, CLAUDE.md) | `claude --bare` | +| `--safe-mode` | Start with all customizations disabled (CLAUDE.md, plugins, skills, hooks, MCP) to isolate config problems; also `CLAUDE_CODE_SAFE_MODE=1` (v2.1.169) | `claude --safe-mode` | | `--enable-auto-mode` | Unlock auto permission mode (no longer required for Max subscribers on Opus 4.7) | `claude --enable-auto-mode` | | `--channels` | Subscribe to MCP channel plugins | `claude --channels discord,telegram` | | `--chrome` / `--no-chrome` | Enable/disable Chrome browser integration | `claude --chrome` | @@ -127,7 +128,7 @@ claude -p "list todos" | grep "URGENT" | Flag | Description | Example | |------|-------------|---------| | `--model` | Set model (sonnet, opus, haiku, or full name) | `claude --model opus` | -| `--fallback-model` | Automatic model fallback when overloaded | `claude -p --fallback-model sonnet "query"` | +| `--fallback-model` | Automatic model fallback when the primary is overloaded/unavailable; configure up to three via the `fallbackModel` setting. Applies to interactive sessions too since v2.1.166 (previously print mode only) | `claude -p --fallback-model sonnet "query"` | | `--agent` | Specify agent for session | `claude --agent my-custom-agent` | | `--agents` | Define custom subagents via JSON | See [Agents Configuration](#agents-configuration) | | `--effort` | Set effort level (low, medium, high, xhigh, max) | `claude --effort xhigh` | @@ -751,6 +752,7 @@ Claude Code supports multiple models with different capabilities: | Opus 4.8 | `claude-opus-4-8` | 1M tokens | Most capable; adaptive effort levels `low → max`; default effort `high` (v2.1.154) | | Sonnet 4.6 | `claude-sonnet-4-6` | 1M tokens | Balanced speed and capability; default effort for Pro/Max subscribers raised from `medium` to `high` in v2.1.117 | | Haiku 4.5 | `claude-haiku-4-5` | 200K tokens | Fastest, best for quick tasks; no effort levels | +| Fable 5 | `claude-fable-5` | — | Mythos-class model, made safe for general use (v2.1.170) | ### Model Selection @@ -801,6 +803,8 @@ The "ultrathink" keyword in prompts activates deep reasoning. The `/effort` menu | `MAX_THINKING_TOKENS` | Set extended thinking token budget | | `CLAUDE_CODE_EFFORT_LEVEL` | Set effort level (`low`/`medium`/`high`/`xhigh`/`max`) — default is `high` on Opus 4.8 (`xhigh` on Opus 4.7); `xhigh` needs Opus 4.8/4.7; `max` works on Opus 4.8/4.7/4.6 and Sonnet 4.6 | | `CLAUDE_CODE_SIMPLE` | Minimal mode, set by `--bare` flag | +| `CLAUDE_CODE_SAFE_MODE` | Set to `1` to start with all customizations disabled (CLAUDE.md, plugins, skills, hooks, MCP) — env-var form of `--safe-mode`, for isolating config problems (v2.1.169) | +| `CLAUDE_CODE_DISABLE_BUNDLED_SKILLS` | Set to `1` to hide the bundled skills, workflows, and commands from the model (v2.1.169) | | `CLAUDE_CODE_DISABLE_AUTO_MEMORY` | Disable automatic CLAUDE.md updates | | `CLAUDE_CODE_DISABLE_BACKGROUND_TASKS` | Disable background task execution | | `CLAUDE_CODE_DISABLE_CRON` | Disable scheduled/cron tasks | @@ -943,12 +947,14 @@ claude -p --output-format json "query" --- -**Last Updated**: June 2, 2026 -**Claude Code Version**: 2.1.160 +**Last Updated**: June 10, 2026 +**Claude Code Version**: 2.1.170 **Sources**: - https://code.claude.com/docs/en/cli-reference - https://code.claude.com/docs/en/settings - https://code.claude.com/docs/en/changelog +- https://code.claude.com/docs/en/troubleshooting +- https://code.claude.com/docs/en/slash-commands - https://code.claude.com/docs/en/model-config - https://platform.claude.com/docs/en/about-claude/models/overview - https://www.anthropic.com/news/claude-opus-4-8