workflow changelog runs for settings, commands, skills, subagents, and concepts reports
Settings (v2.1.78): added voiceEnabled, filesystem.allowManagedReadPathsOnly; moved showTurnDuration/terminalProgressBarEnabled to ~/.claude.json section; fixed MAX_MCP_OUTPUT_TOKENS default (25000); added 3 missing env vars; corrected 4 env var descriptions; added verification Rule 1H (file scope check) Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
Shayan Rais
@@ -1,7 +1,7 @@
|
||||
# claude-code-best-practice
|
||||
practice makes claude perfect
|
||||
|
||||
-white?style=flat&labelColor=555) <a href="https://github.com/shanraisshan/claude-code-best-practice/stargazers"><img src="https://img.shields.io/github/stars/shanraisshan/claude-code-best-practice?style=flat&label=%E2%98%85&labelColor=555&color=white" alt="GitHub Stars"></a>
|
||||
-white?style=flat&labelColor=555) <a href="https://github.com/shanraisshan/claude-code-best-practice/stargazers"><img src="https://img.shields.io/github/stars/shanraisshan/claude-code-best-practice?style=flat&label=%E2%98%85&labelColor=555&color=white" alt="GitHub Stars"></a>
|
||||
|
||||
[](best-practice/) *Click on this badge to show the latest best practice*<br>
|
||||
[](implementation/) *Click on this badge to show implementation in this repo*<br>
|
||||
@@ -43,7 +43,7 @@ practice makes claude perfect
|
||||
| [**/btw**](https://x.com/trq212/status/2031506296697131352) | `/btw` | [](https://x.com/trq212/status/2031506296697131352) Side chain conversations while Claude is working |
|
||||
| [**Code Review**](https://code.claude.com/docs/en/code-review)  | GitHub App (managed) | [](https://x.com/claudeai/status/2031088171262554195) Multi-agent PR analysis that catches bugs, security vulnerabilities, and regressions · [Blog](https://claude.com/blog/code-review) |
|
||||
| [**Scheduled Tasks**](https://code.claude.com/docs/en/scheduled-tasks) | `/loop`, cron tools | [](https://x.com/bcherny/status/2030193932404150413) [](implementation/claude-scheduled-tasks-implementation.md) Run prompts on a recurring schedule (up to 3 days), set one-time reminders, poll deployments and builds |
|
||||
| [**Voice Mode**](https://x.com/trq212/status/2028628570692890800)  | `/voice` | [](https://x.com/trq212/status/2028628570692890800) speak to prompt - /voice to activate|
|
||||
| [**Voice Dictation**](https://code.claude.com/docs/en/voice-dictation)  | `/voice` | [](https://x.com/trq212/status/2028628570692890800) Push-to-talk speech input for prompts with 20-language support and rebindable activation key |
|
||||
| [**Simplify & Batch**](https://x.com/bcherny/status/2027534984534544489) | `/simplify`, `/batch` | [](https://x.com/bcherny/status/2027534984534544489) Built-in skills for code quality and bulk operations — simplify refactors for reuse and efficiency, batch runs commands across files |
|
||||
| [**Agent Teams**](https://code.claude.com/docs/en/agent-teams)  | built-in (env var) | [](https://x.com/bcherny/status/2019472394696683904) [](implementation/claude-agent-teams-implementation.md) Multiple agents working in parallel on the same codebase with shared task coordination |
|
||||
| [**Remote Control**](https://code.claude.com/docs/en/remote-control) | `/remote-control`, `/rc` | [](https://x.com/noahzweben/status/2032533699116355819) Continue local sessions from any device — phone, tablet, or browser · [Headless Mode](https://code.claude.com/docs/en/headless) |
|
||||
@@ -175,7 +175,7 @@ claude
|
||||
| Claude | Replaced |
|
||||
|-|-|
|
||||
|[**Code Review**](https://code.claude.com/docs/en/code-review)|[Greptile](https://greptile.com), [CodeRabbit](https://coderabbit.ai), [Devin Review](https://devin.ai), [OpenDiff](https://opendiff.com), [Cursor BugBot](https://bugbot.dev)|
|
||||
|[**Voice Mode**](https://x.com/trq212/status/2028628570692890800)|[Wispr Flow](https://wisprflow.ai), [SuperWhisper](https://superwhisper.com/)|
|
||||
|[**Voice Dictation**](https://code.claude.com/docs/en/voice-dictation)|[Wispr Flow](https://wisprflow.ai), [SuperWhisper](https://superwhisper.com/)|
|
||||
|[**Remote Control**](https://code.claude.com/docs/en/remote-control)|[OpenClaw](https://openclaw.ai/)
|
||||
|[**Cowork**](https://claude.com/blog/cowork-research-preview)|[OpenAI Operator](https://openai.com/operator), [AgentShadow](https://agentshadow.ai)
|
||||
|[**Tasks**](https://x.com/trq212/status/2014480496013803643)|[Beads](https://github.com/steveyegge/beads)
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Commands Best Practice
|
||||
|
||||
<br>
|
||||
<br>
|
||||
[](../implementation/claude-commands-implementation.md)
|
||||
|
||||
Claude Code commands — frontmatter fields and official built-in slash commands.
|
||||
@@ -25,7 +25,7 @@ Claude Code commands — frontmatter fields and official built-in slash commands
|
||||
|
||||
---
|
||||
|
||||
##  **(62)**
|
||||
##  **(63)**
|
||||
|
||||
| # | Command | Tag | Description |
|
||||
|---|---------|-----|-------------|
|
||||
@@ -35,7 +35,7 @@ Claude Code commands — frontmatter fields and official built-in slash commands
|
||||
| 4 | `/color [color\|default]` |  | Set the prompt bar color for the current session |
|
||||
| 5 | `/config` |  | Open the Settings interface to adjust theme, model, output style, and other preferences. Alias: `/settings` |
|
||||
| 6 | `/keybindings` |  | Customize keyboard shortcuts per context and create chord sequences |
|
||||
| 7 | `/permissions` |  | View or update tool permissions |
|
||||
| 7 | `/permissions` |  | View or update tool permissions. Alias: `/allowed-tools` |
|
||||
| 8 | `/privacy-settings` |  | Manage privacy and telemetry preferences |
|
||||
| 9 | `/sandbox` |  | Configure sandboxing with dependency status |
|
||||
| 10 | `/statusline` |  | Set up Claude Code's status line UI |
|
||||
@@ -43,54 +43,55 @@ Claude Code commands — frontmatter fields and official built-in slash commands
|
||||
| 12 | `/terminal-setup` |  | Enable shift+enter for newlines in IDE terminals |
|
||||
| 13 | `/theme` |  | Change the color theme |
|
||||
| 14 | `/vim` |  | Enable vim-style editing mode |
|
||||
| 15 | `/context` |  | Visualize current context usage as a colored grid with token counts |
|
||||
| 16 | `/cost` |  | Show token usage statistics for the current session |
|
||||
| 17 | `/extra-usage` |  | Configure pay-as-you-go overflow billing for subscription plans |
|
||||
| 18 | `/insights` |  | Generate a report analyzing your Claude Code sessions, including project areas, interaction patterns, and friction points |
|
||||
| 19 | `/stats` |  | Visualize daily usage, session history, streaks, and model preferences |
|
||||
| 20 | `/status` |  | Open the Settings interface (Status tab) showing version, model, account, and connectivity |
|
||||
| 21 | `/usage` |  | Show plan usage limits and rate limit status (subscription plans only) |
|
||||
| 22 | `/doctor` |  | Check the health of your Claude Code installation |
|
||||
| 23 | `/feedback [description]` |  | Generate a GitHub issue URL for reporting bugs or feedback. Alias: `/bug` |
|
||||
| 24 | `/help` |  | Show slash-command help |
|
||||
| 25 | `/release-notes` |  | Show recent Claude Code release notes |
|
||||
| 26 | `/tasks` |  | List and manage background tasks |
|
||||
| 27 | `/copy` |  | Copy the last assistant response to clipboard. Shows interactive picker for code blocks |
|
||||
| 28 | `/export [filename]` |  | Export the current conversation to a file or clipboard |
|
||||
| 29 | `/agents` |  | Manage custom subagents — view, create, edit, delete |
|
||||
| 30 | `/chrome` |  | Manage Claude in Chrome browser integration |
|
||||
| 31 | `/hooks` |  | Manage hook configurations for tool events |
|
||||
| 32 | `/ide` |  | Connect to IDE integration |
|
||||
| 33 | `/mcp` |  | Manage MCP server connections |
|
||||
| 34 | `/plugin` |  | Manage Claude Code plugins |
|
||||
| 35 | `/reload-plugins` |  | Reload installed plugins without restarting |
|
||||
| 36 | `/skills` |  | List available skills |
|
||||
| 37 | `/memory` |  | Edit CLAUDE.md memory files, enable or disable auto-memory, and view auto-memory entries |
|
||||
| 38 | `/effort [low\|medium\|high\|max\|auto]` |  | Set the model effort level |
|
||||
| 39 | `/fast` |  | Toggle fast mode — same Opus 4.6 model with faster output |
|
||||
| 40 | `/model` |  | Switch models (haiku, sonnet, opus) and adjust effort level |
|
||||
| 41 | `/passes [number]` |  | Share a free week of Claude Code with friends. Only visible if your account is eligible |
|
||||
| 42 | `/plan` |  | Enter read-only planning mode — suggests approaches without making changes |
|
||||
| 43 | `/add-dir` |  | Add additional working directories to the current session |
|
||||
| 44 | `/diff` |  | Open an interactive diff viewer showing uncommitted changes and per-turn diffs |
|
||||
| 45 | `/init` |  | Initialize a new project with a CLAUDE.md guide |
|
||||
| 46 | `/pr-comments` |  | Review or reply to pull-request comments |
|
||||
| 47 | `/review` |  | Deprecated — install the `code-review` plugin instead |
|
||||
| 48 | `/security-review` |  | Run a focused security review on current changes |
|
||||
| 49 | `/desktop` |  | Continue the current session in the Claude Code Desktop app. macOS and Windows only. Alias: `/app` |
|
||||
| 50 | `/install-github-app` |  | Install the GitHub app for PR-linked workflows |
|
||||
| 51 | `/install-slack-app` |  | Install the Slack app for notifications and sharing |
|
||||
| 52 | `/mobile` |  | Show QR code to download the Claude mobile app. Aliases: `/ios`, `/android` |
|
||||
| 53 | `/remote-control` |  | Make this session available for remote control from claude.ai. Alias: `/rc` |
|
||||
| 54 | `/remote-env` |  | Inspect or copy the remote-control environment setup |
|
||||
| 55 | `/btw <question>` |  | Ask a quick side question without adding to the conversation |
|
||||
| 56 | `/clear` |  | Clear conversation history and free up context. Aliases: `/reset`, `/new` |
|
||||
| 57 | `/compact [prompt]` |  | Compress conversation to free context window. Optional prompt focuses the compaction |
|
||||
| 58 | `/exit` |  | Exit the CLI. Alias: `/quit` |
|
||||
| 59 | `/fork` |  | Fork the current conversation into a new session. Alias: `/branch` |
|
||||
| 60 | `/rename <name>` |  | Rename the current session for easier identification |
|
||||
| 61 | `/resume [session]` |  | Resume a previous conversation by ID or name, or open the session picker. Alias: `/continue` |
|
||||
| 62 | `/rewind` |  | Rewind the conversation and/or code to a previous point, or summarize from a selected message. Alias: `/checkpoint` |
|
||||
| 15 | `/voice` |  | Toggle push-to-talk voice dictation. Requires a Claude.ai account |
|
||||
| 16 | `/context` |  | Visualize current context usage as a colored grid with token counts |
|
||||
| 17 | `/cost` |  | Show token usage statistics for the current session |
|
||||
| 18 | `/extra-usage` |  | Configure pay-as-you-go overflow billing for subscription plans |
|
||||
| 19 | `/insights` |  | Generate a report analyzing your Claude Code sessions, including project areas, interaction patterns, and friction points |
|
||||
| 20 | `/stats` |  | Visualize daily usage, session history, streaks, and model preferences |
|
||||
| 21 | `/status` |  | Open the Settings interface (Status tab) showing version, model, account, and connectivity |
|
||||
| 22 | `/usage` |  | Show plan usage limits and rate limit status (subscription plans only) |
|
||||
| 23 | `/doctor` |  | Check the health of your Claude Code installation |
|
||||
| 24 | `/feedback [description]` |  | Generate a GitHub issue URL for reporting bugs or feedback. Alias: `/bug` |
|
||||
| 25 | `/help` |  | Show slash-command help |
|
||||
| 26 | `/release-notes` |  | Show recent Claude Code release notes |
|
||||
| 27 | `/tasks` |  | List and manage background tasks |
|
||||
| 28 | `/copy [N]` |  | Copy the last (or Nth-latest) assistant response to clipboard. Shows interactive picker for code blocks |
|
||||
| 29 | `/export [filename]` |  | Export the current conversation to a file or clipboard |
|
||||
| 30 | `/agents` |  | Manage custom subagents — view, create, edit, delete |
|
||||
| 31 | `/chrome` |  | Manage Claude in Chrome browser integration |
|
||||
| 32 | `/hooks` |  | Manage hook configurations for tool events |
|
||||
| 33 | `/ide` |  | Connect to IDE integration |
|
||||
| 34 | `/mcp` |  | Manage MCP server connections |
|
||||
| 35 | `/plugin` |  | Manage Claude Code plugins |
|
||||
| 36 | `/reload-plugins` |  | Reload installed plugins without restarting |
|
||||
| 37 | `/skills` |  | List available skills |
|
||||
| 38 | `/memory` |  | Edit CLAUDE.md memory files, enable or disable auto-memory, and view auto-memory entries |
|
||||
| 39 | `/effort [low\|medium\|high\|max\|auto]` |  | Set the model effort level |
|
||||
| 40 | `/fast` |  | Toggle fast mode — same Opus 4.6 model with faster output |
|
||||
| 41 | `/model` |  | Switch models (haiku, sonnet, opus) and adjust effort level |
|
||||
| 42 | `/passes [number]` |  | Share a free week of Claude Code with friends. Only visible if your account is eligible |
|
||||
| 43 | `/plan` |  | Enter read-only planning mode — suggests approaches without making changes |
|
||||
| 44 | `/add-dir` |  | Add additional working directories to the current session |
|
||||
| 45 | `/diff` |  | Open an interactive diff viewer showing uncommitted changes and per-turn diffs |
|
||||
| 46 | `/init` |  | Initialize a new project with a CLAUDE.md guide |
|
||||
| 47 | `/pr-comments` |  | Review or reply to pull-request comments |
|
||||
| 48 | `/review` |  | Deprecated — install the `code-review` plugin instead |
|
||||
| 49 | `/security-review` |  | Run a focused security review on current changes |
|
||||
| 50 | `/desktop` |  | Continue the current session in the Claude Code Desktop app. macOS and Windows only. Alias: `/app` |
|
||||
| 51 | `/install-github-app` |  | Install the GitHub app for PR-linked workflows |
|
||||
| 52 | `/install-slack-app` |  | Install the Slack app for notifications and sharing |
|
||||
| 53 | `/mobile` |  | Show QR code to download the Claude mobile app. Aliases: `/ios`, `/android` |
|
||||
| 54 | `/remote-control` |  | Make this session available for remote control from claude.ai. Alias: `/rc` |
|
||||
| 55 | `/remote-env` |  | Inspect or copy the remote-control environment setup |
|
||||
| 56 | `/branch` |  | Fork the current conversation into a new session. Alias: `/fork` |
|
||||
| 57 | `/btw <question>` |  | Ask a quick side question without adding to the conversation |
|
||||
| 58 | `/clear` |  | Clear conversation history and free up context. Aliases: `/reset`, `/new` |
|
||||
| 59 | `/compact [prompt]` |  | Compress conversation to free context window. Optional prompt focuses the compaction |
|
||||
| 60 | `/exit` |  | Exit the CLI. Alias: `/quit` |
|
||||
| 61 | `/rename <name>` |  | Rename the current session for easier identification |
|
||||
| 62 | `/resume [session]` |  | Resume a previous conversation by ID or name, or open the session picker. Alias: `/continue` |
|
||||
| 63 | `/rewind` |  | Rewind the conversation and/or code to a previous point, or summarize from a selected message. Alias: `/checkpoint` |
|
||||
|
||||
Bundled skills such as `/debug` can also appear in the slash-command menu, but they are not built-in commands.
|
||||
|
||||
|
||||
@@ -1,8 +1,8 @@
|
||||
# Claude Code Settings Reference
|
||||
|
||||
 
|
||||
 
|
||||
|
||||
A comprehensive guide to all available configuration options in Claude Code's `settings.json` files. As of v2.1.77, Claude Code exposes **60+ settings** and **100+ environment variables** (use the `"env"` field in `settings.json` to avoid wrapper scripts).
|
||||
A comprehensive guide to all available configuration options in Claude Code's `settings.json` files. As of v2.1.78, Claude Code exposes **60+ settings** and **100+ environment variables** (use the `"env"` field in `settings.json` to avoid wrapper scripts).
|
||||
|
||||
<table width="100%">
|
||||
<tr>
|
||||
@@ -75,6 +75,7 @@ Within the managed tier, precedence is: server-managed > MDM/OS-level policies >
|
||||
| `fastModePerSessionOptIn` | boolean | `false` | Require users to opt in to fast mode each session |
|
||||
| `teammateMode` | string | `"auto"` | Agent team display mode: `"auto"` (split panes in tmux/iTerm2, in-process otherwise), `"in-process"`, or `"tmux"` |
|
||||
| `includeGitInstructions` | boolean | `true` | Include git-related instructions in system prompt |
|
||||
| `voiceEnabled` | boolean | - | Enable push-to-talk voice dictation. Written automatically when you run `/voice`. Requires a Claude.ai account |
|
||||
| `feedbackSurveyRate` | number | - | Probability (0–1) that the session quality survey appears when eligible. Enterprise admins can control how often the survey is shown. Example: `0.05` = 5% of eligible sessions |
|
||||
|
||||
**Example:**
|
||||
@@ -218,7 +219,7 @@ Control what tools and operations Claude can perform.
|
||||
| `permissions.defaultMode` | string | Default permission mode. In Remote environments, only `acceptEdits` and `plan` are honored (v2.1.70+) |
|
||||
| `permissions.disableBypassPermissionsMode` | string | Prevent bypass mode activation |
|
||||
| `allowManagedPermissionRulesOnly` | boolean | **(Managed only)** Only managed permission rules apply; user/project `allow`, `ask`, `deny` rules are ignored |
|
||||
| `allow_remote_sessions` | boolean | **(Managed only)** Allow users to start Remote Control and web sessions. Defaults to `true`. Set to `false` to prevent remote session access *(not in official docs — unverified)* |
|
||||
| `allow_remote_sessions` | boolean | **(Managed only)** Allow users to start Remote Control and web sessions. Defaults to `true`. Set to `false` to prevent remote session access |
|
||||
|
||||
### Permission Modes
|
||||
|
||||
@@ -373,6 +374,7 @@ Configure bash command sandboxing for security.
|
||||
| `sandbox.filesystem.denyWrite` | array | `[]` | Path prefixes where write is denied |
|
||||
| `sandbox.filesystem.denyRead` | array | `[]` | Path prefixes where read is denied |
|
||||
| `sandbox.filesystem.allowRead` | array | `[]` | Path prefixes to re-allow read access within `denyRead` regions. Use to carve out exceptions inside broadly denied paths |
|
||||
| `sandbox.filesystem.allowManagedReadPathsOnly` | boolean | `false` | **(Managed only)** Only `allowRead` paths from managed settings are respected. `allowRead` entries from user, project, and local settings are ignored |
|
||||
| `sandbox.enableWeakerNetworkIsolation` | boolean | `false` | (macOS only) Allow access to system TLS trust (`com.apple.trustd.agent`); reduces security |
|
||||
|
||||
**Example:**
|
||||
@@ -517,12 +519,19 @@ Configure via `env` key:
|
||||
| `spinnerTipsEnabled` | boolean | `true` | Show tips while waiting |
|
||||
| `spinnerVerbs` | object | - | Custom spinner verbs with `mode` ("append" or "replace") and `verbs` array |
|
||||
| `spinnerTipsOverride` | object | - | Custom spinner tips with `tips` (string array) and optional `excludeDefault` (boolean) |
|
||||
| `terminalProgressBarEnabled` | boolean | `true` | Show progress bar in terminal |
|
||||
| `showTurnDuration` | boolean | `true` | Show turn duration messages |
|
||||
| `respectGitignore` | boolean | `true` | Respect .gitignore in file picker |
|
||||
| `prefersReducedMotion` | boolean | `false` | Reduce animations and motion effects in the UI |
|
||||
| `fileSuggestion` | object | - | Custom file suggestion command (see File Suggestion Configuration below) |
|
||||
|
||||
### Global Config Settings (`~/.claude.json`)
|
||||
|
||||
These display preferences are stored in `~/.claude.json`, **not** `settings.json`. Adding them to `settings.json` will trigger a schema validation error.
|
||||
|
||||
| Key | Type | Default | Description |
|
||||
|-----|------|---------|-------------|
|
||||
| `showTurnDuration` | boolean | `true` | Show turn duration messages after responses (e.g., "Cooked for 1m 6s"). Edit `~/.claude.json` directly to change |
|
||||
| `terminalProgressBarEnabled` | boolean | `true` | Show the terminal progress bar in supported terminals (Windows Terminal, iTerm2). Appears in `/config` as **Terminal progress bar** |
|
||||
|
||||
### Status Line Configuration
|
||||
|
||||
```json
|
||||
@@ -576,9 +585,7 @@ The file suggestion script receives a JSON object on stdin (e.g., `{"query": "sr
|
||||
"spinnerTipsOverride": {
|
||||
"tips": ["Use /compact at ~50% context", "Start with plan mode for complex tasks"],
|
||||
"excludeDefault": true
|
||||
},
|
||||
"terminalProgressBarEnabled": true,
|
||||
"showTurnDuration": false
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
@@ -647,8 +654,8 @@ Set environment variables for all Claude Code sessions.
|
||||
| `CLAUDE_CODE_ENABLE_TELEMETRY` | Enable/disable telemetry (`0` or `1`) |
|
||||
| `DISABLE_ERROR_REPORTING` | Disable error reporting (`1` to disable) |
|
||||
| `DISABLE_TELEMETRY` | Disable telemetry (`1` to disable) |
|
||||
| `MCP_TIMEOUT` | MCP startup timeout in ms (default: 10000) |
|
||||
| `MAX_MCP_OUTPUT_TOKENS` | Max MCP output tokens (default: 50000) |
|
||||
| `MCP_TIMEOUT` | MCP startup timeout in ms |
|
||||
| `MAX_MCP_OUTPUT_TOKENS` | Max MCP output tokens (default: 25000). Warning displayed when output exceeds 10,000 tokens |
|
||||
| `BASH_MAX_TIMEOUT_MS` | Bash command timeout |
|
||||
| `BASH_MAX_OUTPUT_LENGTH` | Max bash output length |
|
||||
| `CLAUDE_AUTOCOMPACT_PCT_OVERRIDE` | Auto-compact threshold percentage (1-100). Default is ~95%. Set lower (e.g., `50`) to trigger compaction earlier. Values above 95% have no effect. Use `/context` to monitor current usage. Example: `CLAUDE_AUTOCOMPACT_PCT_OVERRIDE=50 claude` |
|
||||
@@ -662,16 +669,18 @@ Set environment variables for all Claude Code sessions.
|
||||
| `CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS` | Disable experimental beta features (`1` to disable) |
|
||||
| `CLAUDE_CODE_SHELL` | Override automatic shell detection |
|
||||
| `CLAUDE_CODE_FILE_READ_MAX_OUTPUT_TOKENS` | Override default file read token limit |
|
||||
| `CLAUDE_CODE_ENABLE_TASKS` | Set to `false` to disable new task system |
|
||||
| `CLAUDE_CODE_ENABLE_TASKS` | Set to `true` to enable task tracking in non-interactive mode (`-p` flag). Tasks are on by default in interactive mode |
|
||||
| `CLAUDE_CODE_EXIT_AFTER_STOP_DELAY` | Auto-exit SDK mode after idle duration (ms) |
|
||||
| `CLAUDE_CODE_DISABLE_ADAPTIVE_THINKING` | Disable adaptive thinking (`1` to disable) |
|
||||
| `CLAUDE_CODE_DISABLE_1M_CONTEXT` | Disable 1M token context window (`1` to disable) |
|
||||
| `CLAUDE_CODE_ACCOUNT_UUID` | Override account UUID for authentication |
|
||||
| `CLAUDE_CODE_DISABLE_GIT_INSTRUCTIONS` | Disable git-related system prompt instructions |
|
||||
| `CLAUDE_CODE_NEW_INIT` | Set to `true` to make `/init` run an interactive setup flow. Asks which files to generate (CLAUDE.md, skills, hooks) before exploring the codebase. Without this, `/init` generates a CLAUDE.md automatically |
|
||||
| `CLAUDE_CODE_PLUGIN_SEED_DIR` | Path to a read-only plugin seed directory. Bundle a pre-populated plugins directory into a container image. Claude Code registers marketplaces from this directory at startup and uses pre-cached plugins without re-cloning |
|
||||
| `ENABLE_CLAUDEAI_MCP_SERVERS` | Enable Claude.ai MCP servers |
|
||||
| `CLAUDE_CODE_EFFORT_LEVEL` | Set effort level: `high`, `medium`, or `low` |
|
||||
| `CLAUDE_CODE_EFFORT_LEVEL` | Set effort level: `low`, `medium`, `high`, `max` (Opus 4.6 only), or `auto` (use model default). Takes precedence over `/effort` and the `effortLevel` setting |
|
||||
| `CLAUDE_CODE_MAX_TURNS` | Maximum agentic turns before stopping *(not in official docs — unverified)* |
|
||||
| `CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC` | Disable non-essential network traffic |
|
||||
| `CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC` | Equivalent of setting `DISABLE_AUTOUPDATER`, `DISABLE_FEEDBACK_COMMAND`, `DISABLE_ERROR_REPORTING`, and `DISABLE_TELEMETRY` |
|
||||
| `CLAUDE_CODE_SKIP_SETTINGS_SETUP` | Skip first-run settings setup flow *(not in official docs — unverified)* |
|
||||
| `CLAUDE_CODE_PROMPT_CACHING_ENABLED` | Override prompt caching behavior *(not in official docs — unverified)* |
|
||||
| `CLAUDE_CODE_DISABLE_TOOLS` | Comma-separated list of tools to disable *(not in official docs — unverified)* |
|
||||
@@ -703,7 +712,7 @@ Set environment variables for all Claude Code sessions.
|
||||
| `CLAUDE_CODE_HIDE_ACCOUNT_INFO` | Hide email/org info from UI *(not in official docs — unverified)* |
|
||||
| `CLAUDE_CODE_DISABLE_CRON` | Disable scheduled/cron tasks (`1` to disable) |
|
||||
| `DISABLE_INSTALLATION_CHECKS` | Disable installation warnings |
|
||||
| `DISABLE_BUG_COMMAND` | Disable the `/bug` command |
|
||||
| `DISABLE_FEEDBACK_COMMAND` | Disable the `/feedback` command. The older name `DISABLE_BUG_COMMAND` is also accepted |
|
||||
| `DISABLE_NON_ESSENTIAL_MODEL_CALLS` | Disable flavor text and non-essential model calls *(not in official docs — unverified)* |
|
||||
| `DISABLE_COST_WARNINGS` | Disable cost warning messages |
|
||||
| `CLAUDE_CODE_SUBAGENT_MODEL` | Override model for subagents (e.g., `haiku`, `sonnet`) |
|
||||
@@ -826,7 +835,6 @@ Set environment variables for all Claude Code sessions.
|
||||
"tips": ["Custom tip 1", "Custom tip 2"],
|
||||
"excludeDefault": false
|
||||
},
|
||||
"showTurnDuration": false,
|
||||
"prefersReducedMotion": false,
|
||||
|
||||
"env": {
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Skills Best Practice
|
||||
|
||||
<br>
|
||||
<br>
|
||||
[](../implementation/claude-skills-implementation.md)
|
||||
|
||||
Claude Code skills — frontmatter fields and official bundled skills.
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Sub-agents Best Practice
|
||||
|
||||
<br>
|
||||
<br>
|
||||
[](../implementation/claude-subagents-implementation.md)
|
||||
|
||||
Claude Code subagents — frontmatter fields and official built-in agent types.
|
||||
|
||||
@@ -58,3 +58,15 @@
|
||||
| 6 | MED | Changed Description | Update `/mobile` — "Show QR code to download the Claude mobile app" | ✅ COMPLETE (updated description + aliases at #52 in Remote tag) |
|
||||
| 7 | MED | Changed Description | Update `/remote-control` — "Make this session available for remote control from claude.ai" | ✅ COMPLETE (updated description + alias at #53 in Remote tag) |
|
||||
| 8 | LOW | Frontmatter Scope | 6 skill-only fields still absent from report (intentional scoping) | ❌ INVALID (skill-only fields — same determination as v2.1.74 run) |
|
||||
|
||||
---
|
||||
|
||||
## [2026-03-18 11:38 PM PKT] Claude Code v2.1.78
|
||||
|
||||
| # | Priority | Type | Action | Status |
|
||||
|---|----------|------|--------|--------|
|
||||
| 1 | HIGH | New Command | Add `/voice` to Config tag — toggle push-to-talk voice dictation | ✅ COMPLETE (added as #15 in Config tag) |
|
||||
| 2 | HIGH | Inverted Alias | Swap `/fork` → `/branch` as primary, `/fork` as alias | ✅ COMPLETE (swapped to `/branch` at #56 in Session tag, re-sorted alphabetically) |
|
||||
| 3 | MED | New Alias | Add `/allowed-tools` alias to `/permissions` | ✅ COMPLETE (added alias to #7 in Config tag) |
|
||||
| 4 | MED | New Argument | Add `[N]` argument syntax to `/copy` | ✅ COMPLETE (updated to `/copy [N]` at #28 in Export tag) |
|
||||
| 5 | LOW | Frontmatter Scope | 6 skill-only fields absent from report (intentional scoping) | ❌ INVALID (skill-only fields — same determination as v2.1.74 and v2.1.77 runs) |
|
||||
|
||||
@@ -135,4 +135,23 @@
|
||||
| 7 | MED | Suspect Key Escalation | `allow_remote_sessions` — NOT in official docs page or JSON schema. Mark as "not in official docs — unverified" | ✅ COMPLETE (added unverified annotation to description) |
|
||||
| 8 | LOW | Suspect Key Resolution | `sandbox.ignoreViolations` — 8 consecutive ON HOLD runs. Confirmed in JSON schema. Annotate: "in JSON schema, not on official settings page" | ✅ COMPLETE (added schema annotation to description) |
|
||||
| 9 | LOW | Suspect Key Resolution | `skipWebFetchPreflight`, `skippedMarketplaces`, `skippedPlugins`, `pluginConfigs` — 8 consecutive ON HOLD runs. All confirmed in JSON schema. Annotate: "in JSON schema, not on official settings page" | ✅ COMPLETE (added schema annotation to all 4 descriptions) |
|
||||
| 10 | LOW | Header Count | Update header env var count from "160+" to "100+" — actual table has 97 env vars | ✅ COMPLETE (header updated to "100+ environment variables", version to v2.1.77) |
|
||||
| 10 | LOW | Header Count | Update header env var count from "160+" to "100+" — actual table has 97 env vars | ✅ COMPLETE (header updated to "100+ environment variables", version to v2.1.77) |
|
||||
|
||||
---
|
||||
|
||||
## [2026-03-18 11:53 PM PKT] Claude Code v2.1.78
|
||||
|
||||
| # | Priority | Type | Action | Status |
|
||||
|---|----------|------|--------|--------|
|
||||
| 1 | HIGH | Missing Setting | Add `voiceEnabled` to General Settings table — enable push-to-talk voice dictation (boolean, written by `/voice`, requires Claude.ai account). Confirmed on official settings page | ✅ COMPLETE (added to General Settings table before feedbackSurveyRate) |
|
||||
| 2 | HIGH | Missing Setting | Add `filesystem.allowManagedReadPathsOnly` to Sandbox Settings table — managed-only, only managed `allowRead` paths are respected (boolean, default false). Confirmed on official settings page | ✅ COMPLETE (added to Sandbox Settings table before enableWeakerNetworkIsolation) |
|
||||
| 3 | HIGH | Display Location | Move `showTurnDuration` and `terminalProgressBarEnabled` from Display Settings table to a separate "Global Config Settings (~/.claude.json)" subsection. Official docs state: "Adding them to settings.json will trigger a schema validation error" | ✅ COMPLETE (created new subsection with table; removed from settings.json Display Settings table and examples) |
|
||||
| 4 | HIGH | Changed Default | Fix `MAX_MCP_OUTPUT_TOKENS` default from 50000 to 25000. Official /en/env-vars page confirms default: 25000 | ✅ COMPLETE (default updated, added warning threshold note) |
|
||||
| 5 | HIGH | Missing Env Vars | Add `CLAUDE_CODE_NEW_INIT`, `CLAUDE_CODE_PLUGIN_SEED_DIR`, `DISABLE_FEEDBACK_COMMAND` to env vars table. All confirmed on official /en/env-vars page | ✅ COMPLETE (added all 3 env vars to table) |
|
||||
| 6 | MED | Verification Fix | Remove "unverified" annotation from `allow_remote_sessions` — now confirmed on official permissions page as a managed-only setting. Previous run (v2.1.77 #7) incorrectly marked it unverified | ✅ COMPLETE (removed "unverified" annotation) |
|
||||
| 7 | MED | Env Var Rename | Update `DISABLE_BUG_COMMAND` to `DISABLE_FEEDBACK_COMMAND` — official docs say `DISABLE_FEEDBACK_COMMAND` is the current name, `DISABLE_BUG_COMMAND` is "the older name" | ✅ COMPLETE (renamed with alias note) |
|
||||
| 8 | MED | Changed Description | Update `CLAUDE_CODE_EFFORT_LEVEL` to include `max` (Opus 4.6 only) and `auto` values. Official /en/env-vars page confirms: "Values: low, medium, high, max (Opus 4.6 only), or auto" | ✅ COMPLETE (description updated with all values and precedence note) |
|
||||
| 9 | MED | Changed Description | Fix `CLAUDE_CODE_ENABLE_TASKS` description — official: "Set to true to enable task tracking in non-interactive mode (-p flag). Tasks are on by default in interactive mode." Report currently says "Set to false to disable" | ✅ COMPLETE (description corrected to match official docs) |
|
||||
| 10 | MED | Changed Description | Update `CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC` to note: "Equivalent of setting DISABLE_AUTOUPDATER, DISABLE_FEEDBACK_COMMAND, DISABLE_ERROR_REPORTING, and DISABLE_TELEMETRY" | ✅ COMPLETE (description updated with equivalent vars list) |
|
||||
| 11 | MED | Example Update | Remove `showTurnDuration` from Quick Reference example — doesn't belong in settings.json per official docs | ✅ COMPLETE (removed from Quick Reference example and Display & UX example) |
|
||||
| 12 | LOW | Env Var Default | Verify `MCP_TIMEOUT` default (report says 10000) — official docs don't specify a default value | ✅ COMPLETE (removed unverified default — official docs omit it) |
|
||||
@@ -27,6 +27,7 @@ Rules that verify settings key tables against official docs.
|
||||
| 1E | Scope Column | For each key that has a Scope column (MCP, Plugin, Permission tables), verify the scope value matches official docs (e.g., "Managed only", "Any", "Project") | content-match | settings documentation page | 2026-03-15 | v2.1.71 caught `extraKnownMarketplaces` scope wrong ("Any" → "Project"), v2.1.75 caught `autoMemoryDirectory` scope restriction. No rule existed to systematically verify scope columns |
|
||||
| 1F | Inverse Completeness | For each key in the report tables, verify it exists in official docs OR is explicitly marked as "not in official docs — unverified". Keys with no official backing must be annotated | field-level | settings documentation page + JSON schema | 2026-03-15 | Suspect keys (`sandbox.ignoreViolations`, `skipWebFetchPreflight`, etc.) stayed ON HOLD for 6 runs because no rule checked the reverse direction — items in report that shouldn't be there |
|
||||
| 1G | Edge-Case Semantics | For settings with special behavior at boundary values (e.g., `0`, empty string, `null`), verify the boundary behavior is documented and matches official docs | content-match | settings documentation page | 2026-03-15 | v2.1.75 caught `cleanupPeriodDays` zero-value behavior late; v2.1.76 added "hooks receive empty transcript_path" detail. Edge cases were under-verified |
|
||||
| 1H | File Scope Check | For each key listed in the report as a `settings.json` key (particularly Display Settings), verify it is indeed a `settings.json` key and not a `~/.claude.json`-only preference. Official docs separate "Available settings" (settings.json) from "Global config settings" (~/.claude.json). Keys in the wrong scope mislead users and may cause schema validation errors | content-match | settings documentation page "Available settings" vs "Global config settings" sections | 2026-03-18 | v2.1.78 caught `showTurnDuration` and `terminalProgressBarEnabled` listed in Display Settings as settings.json keys, but official docs explicitly state they belong in `~/.claude.json` and "Adding them to settings.json will trigger a schema validation error." No rule existed to verify file scope |
|
||||
|
||||
---
|
||||
|
||||
|
||||
@@ -29,3 +29,9 @@
|
||||
## [2026-03-17 12:42 PM PKT] Claude Code v2.1.77
|
||||
|
||||
No drift detected — frontmatter fields (10) and bundled skills (5) are fully synchronized with official docs.
|
||||
|
||||
---
|
||||
|
||||
## [2026-03-18 11:38 PM PKT] Claude Code v2.1.78
|
||||
|
||||
No drift detected — frontmatter fields (10) and bundled skills (5) are fully synchronized with official docs.
|
||||
|
||||
@@ -62,3 +62,9 @@ No drift detected — report is fully in sync with official docs. All 13 frontma
|
||||
## [2026-03-17 12:42 PM PKT] Claude Code v2.1.77
|
||||
|
||||
No drift detected — report is fully in sync with official docs. All 13 frontmatter fields and 6 built-in agents match.
|
||||
|
||||
---
|
||||
|
||||
## [2026-03-18 11:41 PM PKT] Claude Code v2.1.78
|
||||
|
||||
No drift detected — report is fully in sync with official docs. All 13 frontmatter fields and 6 built-in agents match.
|
||||
|
||||
@@ -113,3 +113,16 @@ Tracks drift between the README CONCEPTS table and official Claude Code document
|
||||
| 6 | LOW | Verification | All local badge file paths validated — no missing files | ✅ COMPLETE (all 20 badge targets exist on filesystem) |
|
||||
| 7 | LOW | Verification | Memory anchor `#organize-rules-with-clauderules` confirmed on /memory page | ✅ COMPLETE (section heading exists) |
|
||||
| 8 | LOW | Verification | All CONCEPTS descriptions checked against official docs | ✅ COMPLETE (Hooks description drift detected — see #2) |
|
||||
|
||||
---
|
||||
|
||||
## [2026-03-18 11:43 PM PKT] Claude Code v2.1.78
|
||||
|
||||
| # | Priority | Type | Action | Status |
|
||||
|---|----------|------|--------|--------|
|
||||
| 1 | HIGH | Stale URL | Commands URL `/slash-commands` serves Skills page — docs say "commands merged into skills" | ❌ INVALID (RECURRING from 2026-03-10; URL still resolves; user chose to keep as-is) |
|
||||
| 2 | HIGH | Changed URL+Name | Voice Mode in Hot table links to tweet instead of official docs `/voice-dictation`; official name is "Voice Dictation" | ✅ COMPLETE (renamed to "Voice Dictation", linked to /voice-dictation, description updated; BP badge kept linking to tweet; also updated in STARTUPS table) |
|
||||
| 3 | LOW | Verification | All 29 external docs URLs validated — no broken links found | ✅ COMPLETE (all URLs return valid pages including /slash-commands redirect) |
|
||||
| 4 | LOW | Verification | All local badge file paths validated — no missing files | ✅ COMPLETE (all 20+ badge targets exist on filesystem) |
|
||||
| 5 | LOW | Verification | Memory anchor `#organize-rules-with-clauderules` confirmed on /memory page | ✅ COMPLETE (section heading exists) |
|
||||
| 6 | LOW | Verification | All CONCEPTS descriptions checked against official docs — no drift detected | ✅ COMPLETE (all descriptions accurate) |
|
||||
|
||||
Reference in New Issue
Block a user