add Fullscreen Rendering + Computer Use to Hot table, update best-practice docs to v2.1.89
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><br>
|
||||
-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><br>
|
||||
|
||||
[](best-practice/) [](implementation/) [](orchestration-workflow/orchestration-workflow.md) [](#-tips-and-tricks) <br>
|
||||
<img src="!/tags/a.svg" height="14"> = Agents · <img src="!/tags/c.svg" height="14"> = Commands · <img src="!/tags/s.svg" height="14"> = Skills
|
||||
@@ -40,7 +40,9 @@ practice makes claude perfect
|
||||
|
||||
| Feature | Location | Description |
|
||||
|---------|----------|-------------|
|
||||
| [**Auto Mode**](https://code.claude.com/docs/en/permission-modes#eliminate-prompts-with-auto-mode)  | `--permission-mode auto` | [](https://x.com/claudeai/status/2036503582166393240) Background safety classifier replaces manual permission prompts — Claude decides what's safe while blocking prompt injection and risky escalations · [Blog](https://claude.com/blog/auto-mode) |
|
||||
| [**Fullscreen Rendering**](https://code.claude.com/docs/en/fullscreen)  | `CLAUDE_CODE_NO_FLICKER=1` | Flicker-free alt-screen rendering with mouse support, stable memory, and in-app scrolling — opt-in research preview |
|
||||
| [**Computer Use**](https://code.claude.com/docs/en/computer-use)  | `computer-use` MCP server | Let Claude control your screen — open apps, click, type, and screenshot your display on macOS · [Desktop](https://code.claude.com/docs/en/desktop#let-claude-use-your-computer) |
|
||||
| [**Auto Mode**](https://code.claude.com/docs/en/permission-modes#eliminate-prompts-with-auto-mode)  | `claude --enable-auto-mode` | [](https://x.com/claudeai/status/2036503582166393240) Background safety classifier replaces manual permission prompts — Claude decides what's safe while blocking prompt injection and risky escalations · Start with `claude --enable-auto-mode` (or `--permission-mode auto`), or cycle to it with `Shift+Tab` during a session · [Blog](https://claude.com/blog/auto-mode) |
|
||||
| [**Channels**](https://code.claude.com/docs/en/channels)  | `--channels`, plugin-based | Push events from Telegram, Discord, or webhooks into a running session — Claude reacts while you're away · [Reference](https://code.claude.com/docs/en/channels-reference) |
|
||||
| [**Slack**](https://code.claude.com/docs/en/slack) | `@Claude` in Slack | Mention @Claude in team chat with a coding task — routes to Claude Code web sessions for bug fixes, code reviews, and parallel task execution |
|
||||
| [**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) |
|
||||
@@ -90,14 +92,14 @@ All major workflows converge on the same architectural pattern: **Research → P
|
||||
|
||||
| Name | ★ | Uniqueness | Plan | <img src="!/tags/a.svg" height="14"> | <img src="!/tags/c.svg" height="14"> | <img src="!/tags/s.svg" height="14"> |
|
||||
|------|---|------------|------|---|---|---|
|
||||
| [Superpowers](https://github.com/obra/superpowers) | 127k |    | <img src="!/tags/s.svg" height="14"> [writing-plans](https://github.com/obra/superpowers/tree/main/skills/writing-plans) | 5 | 3 | 14 |
|
||||
| [Everything Claude Code](https://github.com/affaan-m/everything-claude-code) | 124k |    | <img src="!/tags/a.svg" height="14"> [planner](https://github.com/affaan-m/everything-claude-code/blob/main/agents/planner.md) | 30 | 63 | 135 |
|
||||
| [Superpowers](https://github.com/obra/superpowers) | 129k |    | <img src="!/tags/s.svg" height="14"> [writing-plans](https://github.com/obra/superpowers/tree/main/skills/writing-plans) | 5 | 3 | 14 |
|
||||
| [Everything Claude Code](https://github.com/affaan-m/everything-claude-code) | 129k |    | <img src="!/tags/a.svg" height="14"> [planner](https://github.com/affaan-m/everything-claude-code/blob/main/agents/planner.md) | 36 | 71 | 143 |
|
||||
| [Spec Kit](https://github.com/github/spec-kit) | 84k |    | <img src="!/tags/c.svg" height="14"> [speckit.plan](https://github.com/github/spec-kit/blob/main/templates/commands/plan.md) | 0 | 9+ | 0 |
|
||||
| [gstack](https://github.com/garrytan/gstack) | 59k |    | <img src="!/tags/s.svg" height="14"> [autoplan](https://github.com/garrytan/gstack/tree/main/autoplan) | 0 | 0 | 32 |
|
||||
| [gstack](https://github.com/garrytan/gstack) | 60k |    | <img src="!/tags/s.svg" height="14"> [autoplan](https://github.com/garrytan/gstack/tree/main/autoplan) | 0 | 0 | 33 |
|
||||
| [Get Shit Done](https://github.com/gsd-build/get-shit-done) | 46k |    | <img src="!/tags/a.svg" height="14"> [gsd-planner](https://github.com/gsd-build/get-shit-done/blob/main/agents/gsd-planner.md) | 18 | 57 | 0 |
|
||||
| [BMAD-METHOD](https://github.com/bmad-code-org/BMAD-METHOD) | 43k |    | <img src="!/tags/s.svg" height="14"> [bmad-create-prd](https://github.com/bmad-code-org/BMAD-METHOD/tree/main/src/bmm-skills/2-plan-workflows/bmad-create-prd) | 0 | 0 | 43 |
|
||||
| [OpenSpec](https://github.com/Fission-AI/OpenSpec) | 36k |    | <img src="!/tags/c.svg" height="14"> [opsx:propose](https://github.com/Fission-AI/OpenSpec/blob/main/src/commands/workflow/new-change.ts) | 0 | 11 | 0 |
|
||||
| [Compound Engineering](https://github.com/EveryInc/compound-engineering-plugin) | 12k |    | <img src="!/tags/s.svg" height="14"> [ce-plan](https://github.com/EveryInc/compound-engineering-plugin/tree/main/plugins/compound-engineering/skills/ce-plan) | 48 | 4 | 42 |
|
||||
| [Compound Engineering](https://github.com/EveryInc/compound-engineering-plugin) | 12k |    | <img src="!/tags/s.svg" height="14"> [ce-plan](https://github.com/EveryInc/compound-engineering-plugin/tree/main/plugins/compound-engineering/skills/ce-plan) | 48 | 3 | 40 |
|
||||
| [HumanLayer](https://github.com/humanlayer/humanlayer) | 10k |    | <img src="!/tags/c.svg" height="14"> [create_plan](https://github.com/humanlayer/humanlayer/blob/main/.claude/commands/create_plan.md) | 6 | 27 | 0 |
|
||||
|
||||
### Others
|
||||
|
||||
@@ -214,7 +214,7 @@ These startup-only environment variables are set in your shell before launching
|
||||
| `DISABLE_AUTOUPDATER=1` | Disable auto-updates |
|
||||
| `CLAUDE_CODE_EFFORT_LEVEL` | Control thinking depth — see [Settings Reference](./claude-settings.md#environment-variables-via-env) |
|
||||
| `USE_BUILTIN_RIPGREP=0` | Use system ripgrep instead of built-in (Alpine Linux) |
|
||||
| `CLAUDE_CODE_SIMPLE` | Enable simple mode (Bash + Edit tools only) |
|
||||
| `CLAUDE_CODE_SIMPLE` | Enable simple mode (Bash + Edit tools only). Also configurable via `env` key — see [Settings Reference](./claude-settings.md#environment-variables-via-env) |
|
||||
| `CLAUDE_BASH_NO_LOGIN=1` | Skip login shell for BashTool |
|
||||
|
||||
For environment variables configurable via the `"env"` key in `settings.json` (including `MAX_THINKING_TOKENS`, `CLAUDE_CODE_SHELL`, `CLAUDE_CODE_ENABLE_TASKS`, `CLAUDE_CODE_DISABLE_BACKGROUND_TASKS`, `CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS`, and more), see the [Claude Settings Reference](./claude-settings.md#environment-variables-via-env).
|
||||
|
||||
@@ -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.
|
||||
@@ -83,7 +83,7 @@ Claude Code commands — frontmatter fields and official built-in slash commands
|
||||
| 43 | `/plan [description]` |  | Enter plan mode directly from the prompt. Pass an optional description to enter plan mode and immediately start with that task, for example `/plan fix the auth bug` |
|
||||
| 44 | `/add-dir <path>` |  | Add a new working directory to the current session |
|
||||
| 45 | `/diff` |  | Open an interactive diff viewer showing uncommitted changes and per-turn diffs. Use left/right arrows to switch between the current git diff and individual Claude turns, and up/down to browse files |
|
||||
| 46 | `/init` |  | Initialize project with a `CLAUDE.md` guide. Set `CLAUDE_CODE_NEW_INIT=true` for an interactive flow that also walks through skills, hooks, and personal memory files |
|
||||
| 46 | `/init` |  | Initialize project with a `CLAUDE.md` guide. Set `CLAUDE_CODE_NEW_INIT=1` for an interactive flow that also walks through skills, hooks, and personal memory files |
|
||||
| 47 | `/pr-comments [PR]` |  | Fetch and display comments from a GitHub pull request. Automatically detects the PR for the current branch, or pass a PR URL or number. Requires the `gh` CLI |
|
||||
| 48 | `/review` |  | Deprecated. Install the `code-review` plugin instead: `claude plugin install code-review@claude-plugins-official` |
|
||||
| 49 | `/security-review` |  | Analyze pending changes on the current branch for security vulnerabilities. Reviews the git diff and identifies risks like injection, auth issues, and data exposure |
|
||||
|
||||
@@ -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 v2.1.88, 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 v2.1.89, Claude Code exposes **60+ settings** and **170+ environment variables** (use the `"env"` field in `settings.json` to avoid wrapper scripts).
|
||||
|
||||
<table width="100%">
|
||||
<tr>
|
||||
@@ -68,7 +68,7 @@ Within the managed tier, precedence is: server-managed > MDM/OS-level policies >
|
||||
| `model` | string | `"default"` | Override default model. Accepts aliases (`sonnet`, `opus`, `haiku`) or full model IDs |
|
||||
| `agent` | string | - | Set the default agent for the main conversation. Value is the agent name from `.claude/agents/`. Also available via `--agent` CLI flag |
|
||||
| `language` | string | `"english"` | Claude's preferred response language |
|
||||
| `cleanupPeriodDays` | number | `30` | Sessions inactive longer than this are deleted at startup. Setting to `0` deletes all existing transcripts and disables session persistence entirely (no `.jsonl` files written, `/resume` shows no conversations, hooks receive an empty `transcript_path`) |
|
||||
| `cleanupPeriodDays` | number | `30` | Sessions inactive longer than this are deleted at startup. As of v2.1.89, setting to `0` is rejected with a validation error *(note: official settings page still describes the old `0`-value behavior — "deletes all existing transcripts and disables session persistence entirely" — but the changelog confirms this is now invalid)* |
|
||||
| `autoUpdatesChannel` | string | `"latest"` | Release channel: `"stable"` or `"latest"` |
|
||||
| `alwaysThinkingEnabled` | boolean | `false` | Enable extended thinking by default for all sessions |
|
||||
| `skipWebFetchPreflight` | boolean | `false` | Skip WebFetch blocklist check before fetching URLs *(in JSON schema, not on official settings page)* |
|
||||
@@ -79,6 +79,7 @@ Within the managed tier, precedence is: server-managed > MDM/OS-level policies >
|
||||
| `voiceEnabled` | boolean | - | Enable push-to-talk voice dictation. Written automatically when you run `/voice`. Requires a Claude.ai account |
|
||||
| `showClearContextOnPlanAccept` | boolean | `false` | Show the "clear context" option on the plan accept screen. Set to `true` to restore the option (hidden by default since v2.1.81) |
|
||||
| `disableDeepLinkRegistration` | string | - | Set to `"disable"` to prevent Claude Code from registering the `claude-cli://` protocol handler with the operating system on startup. Deep links let external tools open a Claude Code session with a pre-filled prompt via `claude-cli://open?q=...`. Useful in environments where protocol handler registration is restricted or managed separately |
|
||||
| `showThinkingSummaries` | boolean | `false` | Show thinking summaries in interactive sessions. As of v2.1.89, thinking summaries are no longer generated by default — set to `true` to restore them *(in v2.1.89 changelog, not yet on official settings page)* |
|
||||
| `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:**
|
||||
@@ -221,6 +222,7 @@ Control what tools and operations Claude can perform.
|
||||
| `permissions.additionalDirectories` | array | Extra directories Claude can access |
|
||||
| `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 |
|
||||
| `permissions.skipDangerousModePermissionPrompt` | boolean | Skip the confirmation prompt shown before entering bypass permissions mode via `--dangerously-skip-permissions` or `defaultMode: "bypassPermissions"`. Ignored when set in project settings (`.claude/settings.json`) to prevent untrusted repositories from auto-bypassing the prompt |
|
||||
| `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 — official permissions page states "Access to Remote Control and web sessions is not controlled by a managed settings key." On Team and Enterprise plans, admins enable/disable via [Claude Code admin settings](https://claude.ai/admin-settings/claude-code))* |
|
||||
| `autoMode` | object | Customize what the [auto mode](/en/permission-modes#eliminate-prompts-with-auto-mode) classifier blocks and allows. Contains `environment` (trusted infrastructure descriptions), `allow` (exceptions to block rules), and `soft_deny` (block rules) — all arrays of prose strings. **Not read from shared project settings** (`.claude/settings.json`) to prevent repo injection. Available in user, local, and managed settings. Setting `allow` or `soft_deny` **replaces** the entire default list for that section. Run `claude auto-mode defaults` to see built-in rules before customizing |
|
||||
@@ -237,7 +239,7 @@ Control what tools and operations Claude can perform.
|
||||
| `"dontAsk"` | Auto-denies tools unless pre-approved via `/permissions` or `permissions.allow` rules |
|
||||
| `"viewOnly"` | Read-only mode, no modifications *(not in official docs — unverified)* |
|
||||
| `"bypassPermissions"` | Skip all permission checks (dangerous) |
|
||||
| `"auto"` | Background classifier replaces manual prompts. Research preview — requires Team plan + Sonnet/Opus 4.6. Classifier auto-approves read-only and file edits; sends everything else through a safety check. Falls back to prompting after 3 consecutive or 20 total blocks. Configure with `autoMode` setting |
|
||||
| `"auto"` | Background classifier replaces manual prompts (`--enable-auto-mode`). Research preview — requires Team plan + Sonnet/Opus 4.6. Classifier auto-approves read-only and file edits; sends everything else through a safety check. Falls back to prompting after 3 consecutive or 20 total blocks. Configure with `autoMode` setting |
|
||||
| `"plan"` | Read-only exploration mode |
|
||||
|
||||
### Tool Permission Syntax
|
||||
@@ -677,6 +679,10 @@ Set environment variables for all Claude Code sessions.
|
||||
| `ANTHROPIC_API_KEY` | API key for authentication |
|
||||
| `ANTHROPIC_AUTH_TOKEN` | OAuth token |
|
||||
| `ANTHROPIC_BASE_URL` | Custom API endpoint |
|
||||
| `ANTHROPIC_BEDROCK_BASE_URL` | Override Bedrock endpoint URL |
|
||||
| `ANTHROPIC_VERTEX_BASE_URL` | Override Vertex AI endpoint URL |
|
||||
| `ANTHROPIC_BETAS` | Comma-separated Anthropic beta header values |
|
||||
| `ANTHROPIC_VERTEX_PROJECT_ID` | GCP project ID for Vertex AI |
|
||||
| `ANTHROPIC_CUSTOM_MODEL_OPTION` | Model ID to add as a custom entry in the `/model` picker. Use to make a non-standard or gateway-specific model selectable without replacing built-in aliases |
|
||||
| `ANTHROPIC_CUSTOM_MODEL_OPTION_NAME` | Display name for the custom model entry in the `/model` picker. Defaults to the model ID when not set |
|
||||
| `ANTHROPIC_CUSTOM_MODEL_OPTION_DESCRIPTION` | Display description for the custom model entry in the `/model` picker. Defaults to `Custom model (<model-id>)` when not set |
|
||||
@@ -696,6 +702,7 @@ Set environment variables for all Claude Code sessions.
|
||||
| `DISABLE_TELEMETRY` | Disable telemetry (`1` to disable) |
|
||||
| `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 |
|
||||
| `API_TIMEOUT_MS` | Timeout in ms for API requests (default: 600000) |
|
||||
| `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` |
|
||||
@@ -706,12 +713,19 @@ Set environment variables for all Claude Code sessions.
|
||||
| `DISABLE_PROMPT_CACHING_HAIKU` | Disable Haiku prompt caching |
|
||||
| `DISABLE_PROMPT_CACHING_SONNET` | Disable Sonnet prompt caching |
|
||||
| `DISABLE_PROMPT_CACHING_OPUS` | Disable Opus prompt caching |
|
||||
| `ENABLE_PROMPT_CACHING_1H_BEDROCK` | Request 1-hour cache TTL on Bedrock (`1` to enable) |
|
||||
| `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_GLOB_HIDDEN` | Include dotfiles in Glob results (`1` to enable) |
|
||||
| `CLAUDE_CODE_GLOB_NO_IGNORE` | Make Glob ignore `.gitignore` patterns (`1` to enable) |
|
||||
| `CLAUDE_CODE_GLOB_TIMEOUT_SECONDS` | Timeout in seconds for Glob file discovery |
|
||||
| `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_SIMPLE` | Set to `1` to run with a minimal system prompt and only the Bash, file read, and file edit tools |
|
||||
| `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_THINKING` | Force-disable extended thinking (`1` to disable) |
|
||||
| `DISABLE_INTERLEAVED_THINKING` | Prevent interleaved-thinking beta header from being sent (`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 |
|
||||
@@ -728,7 +742,13 @@ Set environment variables for all Claude Code sessions.
|
||||
| `CLAUDE_CODE_MAX_OUTPUT_TOKENS` | Max output tokens per response. Default: 32,000 (64,000 for Opus 4.6 as of v2.1.77). Upper bound: 64,000 (128,000 for Opus 4.6 and Sonnet 4.6 as of v2.1.77) |
|
||||
| `CLAUDE_CODE_DISABLE_FAST_MODE` | Disable fast mode entirely (`1` to disable) |
|
||||
| `CLAUDE_CODE_DISABLE_NONSTREAMING_FALLBACK` | Set to `1` to disable the non-streaming fallback when a streaming request fails mid-stream. Streaming errors propagate to the retry layer instead. Useful when a proxy or gateway causes the fallback to produce duplicate tool execution (v2.1.83) |
|
||||
| `CLAUDE_ENABLE_STREAM_WATCHDOG` | Abort stalled streams (`1` to enable) |
|
||||
| `CLAUDE_CODE_ENABLE_FINE_GRAINED_TOOL_STREAMING` | Enable fine-grained tool streaming (`1` to enable) |
|
||||
| `CLAUDE_CODE_DISABLE_AUTO_MEMORY` | Disable auto memory (`1` to disable) |
|
||||
| `CLAUDE_CODE_DISABLE_FILE_CHECKPOINTING` | Disable file checkpointing for `/rewind` (`1` to disable) |
|
||||
| `CLAUDE_CODE_DISABLE_ATTACHMENTS` | Disable attachment processing (`1` to disable) |
|
||||
| `CLAUDE_CODE_DISABLE_CLAUDE_MDS` | Prevent loading CLAUDE.md files (`1` to disable) |
|
||||
| `CLAUDE_CODE_RESUME_INTERRUPTED_TURN` | Auto-resume if previous session ended mid-turn (`1` to enable) |
|
||||
| `CLAUDE_CODE_USER_EMAIL` | Provide user email synchronously for authentication |
|
||||
| `CLAUDE_CODE_ORGANIZATION_UUID` | Provide organization UUID synchronously for authentication |
|
||||
| `CLAUDE_CONFIG_DIR` | Custom config directory (overrides default `~/.claude`) |
|
||||
@@ -750,22 +770,50 @@ Set environment variables for all Claude Code sessions.
|
||||
| `CLAUDE_CODE_CLIENT_KEY` | Client private key path for mTLS |
|
||||
| `CLAUDE_CODE_CLIENT_KEY_PASSPHRASE` | Passphrase for encrypted mTLS key |
|
||||
| `CLAUDE_CODE_PLUGIN_GIT_TIMEOUT_MS` | Plugin marketplace git clone timeout in ms (default: 120000) |
|
||||
| `CLAUDE_CODE_PLUGIN_CACHE_DIR` | Override the plugins root directory |
|
||||
| `CLAUDE_CODE_DISABLE_OFFICIAL_MARKETPLACE_AUTOINSTALL` | Skip auto-adding the official marketplace (`1` to disable) |
|
||||
| `CLAUDE_CODE_SYNC_PLUGIN_INSTALL` | Wait for plugin install to complete before first query (`1` to enable) |
|
||||
| `CLAUDE_CODE_SYNC_PLUGIN_INSTALL_TIMEOUT_MS` | Timeout in ms for synchronous plugin install |
|
||||
| `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_FEEDBACK_COMMAND` | Disable the `/feedback` command. The older name `DISABLE_BUG_COMMAND` is also accepted |
|
||||
| `DISABLE_DOCTOR_COMMAND` | Hide the `/doctor` command (`1` to disable) |
|
||||
| `DISABLE_LOGIN_COMMAND` | Hide the `/login` command (`1` to disable) |
|
||||
| `DISABLE_LOGOUT_COMMAND` | Hide the `/logout` command (`1` to disable) |
|
||||
| `DISABLE_UPGRADE_COMMAND` | Hide the `/upgrade` command (`1` to disable) |
|
||||
| `DISABLE_EXTRA_USAGE_COMMAND` | Hide the `/extra-usage` command (`1` to disable) |
|
||||
| `DISABLE_INSTALL_GITHUB_APP_COMMAND` | Hide the `/install-github-app` command (`1` to disable) |
|
||||
| `DISABLE_NON_ESSENTIAL_MODEL_CALLS` | Disable flavor text and non-essential model calls *(not in official docs — unverified)* |
|
||||
| `CLAUDE_CODE_DEBUG_LOGS_DIR` | Override debug log file directory path |
|
||||
| `CLAUDE_CODE_DEBUG_LOG_LEVEL` | Minimum debug log level |
|
||||
| `CLAUDE_AUTO_BACKGROUND_TASKS` | Force auto-backgrounding of long tasks (`1` to enable) |
|
||||
| `CLAUDE_CODE_DISABLE_LEGACY_MODEL_REMAP` | Prevent remapping Opus 4.0/4.1 to newer models (`1` to disable) |
|
||||
| `FALLBACK_FOR_ALL_PRIMARY_MODELS` | Trigger fallback model for all primary models, not just default (`1` to enable) |
|
||||
| `CLAUDE_CODE_GIT_BASH_PATH` | Windows Git Bash executable path (startup-only) |
|
||||
| `DISABLE_COST_WARNINGS` | Disable cost warning messages |
|
||||
| `CLAUDE_CODE_SUBAGENT_MODEL` | Override model for subagents (e.g., `haiku`, `sonnet`) |
|
||||
| `CLAUDE_CODE_SUBPROCESS_ENV_SCRUB` | Set to `1` to strip Anthropic and cloud provider credentials from subprocess environments (Bash tool, hooks, MCP stdio servers). Use for defense-in-depth when subprocesses should not inherit API keys (v2.1.83) |
|
||||
| `CLAUDE_CODE_MAX_RETRIES` | Override API request retry count (default: 10) |
|
||||
| `CLAUDE_CODE_MAX_TOOL_USE_CONCURRENCY` | Max parallel read-only tools (default: 10) |
|
||||
| `CLAUDE_AGENT_SDK_DISABLE_BUILTIN_AGENTS` | Disable built-in subagent types in SDK mode (`1` to disable) |
|
||||
| `CLAUDE_AGENT_SDK_MCP_NO_PREFIX` | Skip `mcp__<server>__` prefix for MCP tools in SDK mode (`1` to enable) |
|
||||
| `MCP_CONNECTION_NONBLOCKING` | Set to `true` in `-p` mode to skip the MCP connection wait entirely. Bounds `--mcp-config` server connections at 5s instead of blocking on the slowest server *(in v2.1.89 changelog, not yet on official env-vars page)* |
|
||||
| `CLAUDE_CODE_SESSIONEND_HOOKS_TIMEOUT_MS` | SessionEnd hook timeout in ms (replaces hard 1.5s limit) |
|
||||
| `CLAUDE_CODE_DISABLE_FEEDBACK_SURVEY` | Disable feedback survey prompts (`1` to disable) |
|
||||
| `CLAUDE_CODE_DISABLE_TERMINAL_TITLE` | Disable terminal title updates (`1` to disable) |
|
||||
| `CLAUDE_CODE_NO_FLICKER` | Set to `1` to enable flicker-free alt-screen rendering. Eliminates visual flicker during fullscreen redraws (v2.1.88) |
|
||||
| `CLAUDE_CODE_SCROLL_SPEED` | Mouse wheel scroll multiplier for fullscreen rendering. Increase for faster scrolling, decrease for finer control |
|
||||
| `CLAUDE_CODE_DISABLE_MOUSE` | Set to `1` to disable mouse tracking in fullscreen rendering. Useful when mouse events interfere with terminal multiplexers or accessibility tools |
|
||||
| `CLAUDE_CODE_ACCESSIBILITY` | Set to `1` to keep native terminal cursor visible for screen readers and accessibility tools |
|
||||
| `CLAUDE_CODE_SYNTAX_HIGHLIGHT` | Set to `0` to disable syntax highlighting in diff output |
|
||||
| `CLAUDE_CODE_IDE_SKIP_AUTO_INSTALL` | Skip automatic IDE extension installation (`1` to skip) |
|
||||
| `CLAUDE_CODE_AUTO_CONNECT_IDE` | Override auto IDE connection behavior |
|
||||
| `CLAUDE_CODE_IDE_HOST_OVERRIDE` | Override IDE host address for connection |
|
||||
| `CLAUDE_CODE_IDE_SKIP_VALID_CHECK` | Skip IDE lockfile validation (`1` to skip) |
|
||||
| `CLAUDE_CODE_OTEL_HEADERS_HELPER_DEBOUNCE_MS` | Debounce interval in ms for OTel headers helper script |
|
||||
| `CLAUDE_CODE_OTEL_FLUSH_TIMEOUT_MS` | Timeout in ms for OpenTelemetry flush |
|
||||
| `CLAUDE_CODE_OTEL_SHUTDOWN_TIMEOUT_MS` | Timeout in ms for OpenTelemetry shutdown |
|
||||
| `CLAUDE_STREAM_IDLE_TIMEOUT_MS` | Timeout in ms before the streaming idle watchdog closes a stalled connection. Default: `90000` (90 seconds). Increase if long-running tools or slow networks cause premature timeout errors |
|
||||
| `OTEL_LOG_TOOL_DETAILS` | Set to `1` to include `tool_parameters` in OpenTelemetry events. Omitted by default for privacy *(in v2.1.85 changelog, not yet on official env-vars page)* |
|
||||
| `CLAUDE_CODE_MCP_SERVER_NAME` | Name of the MCP server, passed as an environment variable to `headersHelper` scripts so they can generate server-specific authentication headers *(in v2.1.85 changelog, not yet on official env-vars page)* |
|
||||
@@ -780,6 +828,8 @@ Set environment variables for all Claude Code sessions.
|
||||
| `ANTHROPIC_DEFAULT_SONNET_MODEL_SUPPORTED_CAPABILITIES` | Override capability detection for a pinned Sonnet model. Comma-separated values (e.g., `effort,thinking`). Required when the pinned model supports features the auto-detection cannot confirm |
|
||||
| `MAX_THINKING_TOKENS` | Maximum extended thinking tokens per response |
|
||||
| `CLAUDE_CODE_AUTO_COMPACT_WINDOW` | Set the context capacity in tokens used for auto-compaction calculations. Defaults to the model's context window (200K standard, 1M for extended context models). Use a lower value (e.g., `500000`) on a 1M model to treat it as 500K for compaction. Capped at actual context window. `CLAUDE_AUTOCOMPACT_PCT_OVERRIDE` is applied as a percentage of this value. Setting this decouples the compaction threshold from the status line's `used_percentage` |
|
||||
| `DISABLE_AUTO_COMPACT` | Disable automatic context compaction (`1` to disable). Manual `/compact` still works |
|
||||
| `DISABLE_COMPACT` | Disable all compaction — both automatic and manual (`1` to disable) |
|
||||
| `CLAUDE_CODE_ENABLE_PROMPT_SUGGESTION` | Enable prompt suggestions |
|
||||
| `CLAUDE_CODE_PLAN_MODE_REQUIRED` | Require plan mode for sessions |
|
||||
| `CLAUDE_CODE_TEAM_NAME` | Team name for agent teams |
|
||||
@@ -833,6 +883,7 @@ Set environment variables for all Claude Code sessions.
|
||||
"cleanupPeriodDays": 30,
|
||||
"autoUpdatesChannel": "stable",
|
||||
"alwaysThinkingEnabled": true,
|
||||
"showThinkingSummaries": true,
|
||||
"includeGitInstructions": true,
|
||||
"defaultShell": "bash",
|
||||
"plansDirectory": "./plans",
|
||||
|
||||
@@ -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.
|
||||
|
||||
@@ -149,3 +149,11 @@ No priority action items — report is fully in sync with official documentation
|
||||
| # | Priority | Type | Action | Status |
|
||||
|---|----------|------|--------|--------|
|
||||
| 1 | MED | Description Sync | Synced all 43 command descriptions to match official docs — behavioral clarifications (`/vim` toggle, `/sandbox` toggle, `/hooks` view), expanded detail (`/effort` persistence, `/copy` SSH write, `/model` effort arrows), and wording alignment across Auth, Config, Context, Debug, Export, Extensions, Model, Project, Remote, and Session tags | ✅ COMPLETE (all 64 descriptions now match official docs at code.claude.com/docs/en/commands) |
|
||||
|
||||
---
|
||||
|
||||
## [2026-04-01 12:26 PM PKT] Claude Code v2.1.89
|
||||
|
||||
| # | Priority | Type | Action | Status |
|
||||
|---|----------|------|--------|--------|
|
||||
| 1 | LOW | Changed Description | Update `/init` — official docs now use `CLAUDE_CODE_NEW_INIT=1` instead of `=true` | ✅ COMPLETE (updated env var value from `=true` to `=1` to match official docs) |
|
||||
|
||||
@@ -270,4 +270,19 @@
|
||||
| 4 | HIGH | Broken Link | Fix `https://www.eesel.ai/blog/settings-json-claude-code` in Sources — returns CSS-only content, no readable blog post | ✅ COMPLETE (removed broken link from Sources section) |
|
||||
| 5 | MED | Settings Hierarchy | Add `managed-mcp.json` to file-based managed delivery methods — official settings page lists it alongside `managed-settings.json` for MCP server configuration | ✅ COMPLETE (added to File delivery method bullet in Settings Hierarchy) |
|
||||
| 6 | MED | Plugin Source Types | Annotate `url`, `npm`, `file` marketplace source types as "not in official docs — unverified" (only `github`, `git`, `directory`, `hostPattern`, `settings` confirmed) | ✅ COMPLETE (added unverified annotations to all 3 source types) |
|
||||
| 7 | LOW | Header Count | Update header from "60+ settings" to match actual table count after any additions | ❌ INVALID (count is accurate — 60+ settings and 125 env vars, both within stated ranges) |
|
||||
| 7 | LOW | Header Count | Update header from "60+ settings" to match actual table count after any additions | ❌ INVALID (count is accurate — 60+ settings and 125 env vars, both within stated ranges) |
|
||||
|
||||
---
|
||||
|
||||
## [2026-04-01 12:32 PM PKT] Claude Code v2.1.89
|
||||
|
||||
| # | Priority | Type | Action | Status |
|
||||
|---|----------|------|--------|--------|
|
||||
| 1 | HIGH | Missing Setting | Add `skipDangerousModePermissionPrompt` to Permission Keys table — boolean, skip bypass-mode confirmation prompt. Ignored in project settings. Confirmed on official settings page | ✅ COMPLETE (added after disableBypassPermissionsMode in Permission Keys table) |
|
||||
| 2 | HIGH | New Setting | Add `showThinkingSummaries` to General Settings — boolean, default `false`. Thinking summaries no longer generated by default; set `true` to restore. v2.1.89 changelog — not yet on official settings page | ✅ COMPLETE (added before feedbackSurveyRate with changelog annotation) |
|
||||
| 3 | HIGH | Changed Behavior | Update `cleanupPeriodDays` description — v2.1.89 changelog says `0` is now rejected with a validation error. CONTRADICTION: official settings page still describes `0` as valid. Flag for user | ✅ COMPLETE (updated description with contradiction note between changelog and docs page) |
|
||||
| 4 | HIGH | Missing Env Vars | Add ~46 missing env vars confirmed on official /en/env-vars page: `ANTHROPIC_BEDROCK_BASE_URL`, `ANTHROPIC_VERTEX_BASE_URL`, `ANTHROPIC_BETAS`, `ANTHROPIC_VERTEX_PROJECT_ID`, `CLAUDE_CODE_DISABLE_THINKING`, `DISABLE_INTERLEAVED_THINKING`, `ENABLE_PROMPT_CACHING_1H_BEDROCK`, `DISABLE_AUTO_COMPACT`, `DISABLE_COMPACT`, `CLAUDE_CODE_DISABLE_FILE_CHECKPOINTING`, `CLAUDE_CODE_DISABLE_ATTACHMENTS`, `CLAUDE_CODE_DISABLE_CLAUDE_MDS`, `CLAUDE_CODE_GLOB_HIDDEN`, `CLAUDE_CODE_GLOB_NO_IGNORE`, `CLAUDE_CODE_GLOB_TIMEOUT_SECONDS`, `CLAUDE_CODE_DISABLE_OFFICIAL_MARKETPLACE_AUTOINSTALL`, `CLAUDE_CODE_SYNC_PLUGIN_INSTALL`, `CLAUDE_CODE_SYNC_PLUGIN_INSTALL_TIMEOUT_MS`, `CLAUDE_CODE_AUTO_CONNECT_IDE`, `CLAUDE_CODE_IDE_HOST_OVERRIDE`, `CLAUDE_CODE_IDE_SKIP_VALID_CHECK`, `CLAUDE_CODE_MAX_RETRIES`, `API_TIMEOUT_MS`, `CLAUDE_CODE_OTEL_FLUSH_TIMEOUT_MS`, `CLAUDE_CODE_OTEL_SHUTDOWN_TIMEOUT_MS`, `CLAUDE_ENABLE_STREAM_WATCHDOG`, `CLAUDE_CODE_ENABLE_FINE_GRAINED_TOOL_STREAMING`, `CLAUDE_CODE_DEBUG_LOGS_DIR`, `CLAUDE_CODE_DEBUG_LOG_LEVEL`, `CLAUDE_CODE_ACCESSIBILITY`, `CLAUDE_CODE_SYNTAX_HIGHLIGHT`, `CLAUDE_CODE_RESUME_INTERRUPTED_TURN`, `CLAUDE_CODE_MAX_TOOL_USE_CONCURRENCY`, `CLAUDE_CODE_DISABLE_LEGACY_MODEL_REMAP`, `FALLBACK_FOR_ALL_PRIMARY_MODELS`, `CLAUDE_CODE_GIT_BASH_PATH`, `CLAUDE_AUTO_BACKGROUND_TASKS`, `CLAUDE_AGENT_SDK_DISABLE_BUILTIN_AGENTS`, `CLAUDE_AGENT_SDK_MCP_NO_PREFIX`, `DISABLE_DOCTOR_COMMAND`, `DISABLE_LOGIN_COMMAND`, `DISABLE_LOGOUT_COMMAND`, `DISABLE_UPGRADE_COMMAND`, `DISABLE_EXTRA_USAGE_COMMAND`, `DISABLE_INSTALL_GITHUB_APP_COMMAND`, `CLAUDE_CODE_PLUGIN_CACHE_DIR`, `CLAUDE_CODE_SIMPLE` | ✅ COMPLETE (added all 46 env vars to table near related vars) |
|
||||
| 5 | HIGH | Version Bump | Update report version badge from v2.1.88 to v2.1.89 | ✅ COMPLETE (badge and header updated in Phase 2.6) |
|
||||
| 6 | MED | New Env Var | Add `MCP_CONNECTION_NONBLOCKING` to env vars table — set to `true` in `-p` mode to skip MCP connection wait. v2.1.89 changelog only, not yet on official /en/env-vars page | ✅ COMPLETE (added after CLAUDE_AGENT_SDK_MCP_NO_PREFIX with changelog annotation) |
|
||||
| 7 | MED | Ownership Boundary | `CLAUDE_CODE_SIMPLE` is in CLI startup flags file as startup-only, but official /en/env-vars page lists it as configurable. Reconcile ownership | ✅ COMPLETE (added to settings report env table; updated CLI file to cross-reference settings report) |
|
||||
| 8 | MED | Example Update | Update Quick Reference example to include `showThinkingSummaries` if added | ✅ COMPLETE (added showThinkingSummaries: true to example) |
|
||||
@@ -93,3 +93,9 @@ No drift detected — frontmatter fields (13) and bundled skills (5) are fully s
|
||||
## [2026-03-31 06:51 PM PKT] Claude Code v2.1.88
|
||||
|
||||
No drift detected — frontmatter fields (13) and bundled skills (5) are fully synchronized with official docs.
|
||||
|
||||
---
|
||||
|
||||
## [2026-04-01 12:27 PM PKT] Claude Code v2.1.89
|
||||
|
||||
No drift detected — frontmatter fields (13) and bundled skills (5) are fully synchronized with official docs.
|
||||
|
||||
@@ -122,3 +122,9 @@ No drift detected — report is fully in sync with official docs. All 16 frontma
|
||||
## [2026-03-28 06:00 PM PKT] Claude Code v2.1.86
|
||||
|
||||
No drift detected — report is fully in sync with official docs. All 16 frontmatter fields (15 official + 1 unofficial `color`) and 6 built-in agents match.
|
||||
|
||||
---
|
||||
|
||||
## [2026-04-01 12:26 PM PKT] Claude Code v2.1.89
|
||||
|
||||
No drift detected — report is fully in sync with official docs. All 16 frontmatter fields (15 official + 1 unofficial `color`) and 6 built-in agents match.
|
||||
|
||||
@@ -244,3 +244,20 @@ Tracks drift between the README CONCEPTS table and official Claude Code document
|
||||
| 8 | LOW | Verification | Auto Mode anchor `#eliminate-prompts-with-auto-mode` confirmed on /permission-modes page | ✅ COMPLETE (section heading exists) |
|
||||
| 9 | LOW | Verification | Bundled Skills anchor `#bundled-skills` confirmed on /skills page | ✅ COMPLETE (section heading exists) |
|
||||
| 10 | LOW | Verification | All CONCEPTS descriptions checked against official docs — no drift detected | ✅ COMPLETE (all descriptions accurate except Plugins LSP note — see #3) |
|
||||
|
||||
---
|
||||
|
||||
## [2026-04-01 12:33 PM PKT] Claude Code v2.1.89
|
||||
|
||||
| # | Priority | Type | Action | Status |
|
||||
|---|----------|------|--------|--------|
|
||||
| 1 | HIGH | Missing Concept | Add Computer Use row to Hot table — screen control on macOS via built-in MCP server (research preview, v2.1.85+) | ✅ COMPLETE (row added after Fullscreen Rendering with beta badge and Desktop inline link) |
|
||||
| 2 | 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) |
|
||||
| 3 | MED | Missing Concept | Add Fullscreen Rendering row to Hot table — flicker-free alt-screen rendering with mouse support (research preview, v2.1.88+) | ✅ COMPLETE (row added as first Hot entry with CLAUDE_CODE_NO_FLICKER=1 location) |
|
||||
| 4 | LOW | Verification | All 38 external docs URLs validated — no broken links found | ✅ COMPLETE (all URLs return valid pages including /slash-commands redirect) |
|
||||
| 5 | LOW | Verification | All local badge file paths validated — no missing files | ✅ COMPLETE (all 20+ badge targets exist on filesystem) |
|
||||
| 6 | LOW | Verification | Memory anchor `#organize-rules-with-clauderules` confirmed on /memory page | ✅ COMPLETE (section heading exists) |
|
||||
| 7 | LOW | Verification | Git Worktrees anchor `#run-parallel-claude-code-sessions-with-git-worktrees` confirmed on /common-workflows page | ✅ COMPLETE (section heading exists) |
|
||||
| 8 | LOW | Verification | Auto Mode anchor `#eliminate-prompts-with-auto-mode` confirmed on /permission-modes page | ✅ COMPLETE (section heading exists) |
|
||||
| 9 | LOW | Verification | Bundled Skills anchor `#bundled-skills` confirmed on /skills page | ✅ COMPLETE (section heading exists) |
|
||||
| 10 | LOW | Verification | All CONCEPTS descriptions checked against official docs — no drift detected | ✅ COMPLETE (all descriptions accurate) |
|
||||
|
||||
@@ -195,3 +195,17 @@
|
||||
| 8 | MED | Count Update | Update BMAD skills from 40 to 43 (32 bmm-skills + 11 core-skills; 3 new bmm-skills added including PRFAQ) | COMPLETE (updated README table) |
|
||||
| 9 | LOW | Count Verify | ECC commands 63→3, skills 135→30 — research agent only checked .claude/ dirs, missed root commands/ and .agents/skills/ breadth | INVALID (agent undercounting — keeping current values 63 commands, 135 skills) |
|
||||
| 10 | LOW | Count Verify | Superpowers agents 5→8 — agent counted 1 explicit + 7 implicit sub-agents, but v5.0.6 replaced subagent review loops with inline self-review | ON HOLD (contradictory signals — v5.0.6 reduced review agents while brainstorm added new ones, needs manual verification) |
|
||||
|
||||
---
|
||||
|
||||
## [2026-04-01 12:35 PM PKT] Development Workflows Update
|
||||
|
||||
| # | Priority | Type | Action | Status |
|
||||
|---|----------|------|--------|--------|
|
||||
| 1 | HIGH | Star Update | Update Superpowers ★ from 127k to 129k (128,925 actual) | COMPLETE (updated README table) |
|
||||
| 2 | HIGH | Star Update | Update ECC ★ from 124k to 129k (128,606 actual — neck-and-neck with Superpowers) | COMPLETE (updated README table) |
|
||||
| 3 | HIGH | Count Update | Update ECC agents 30→36, commands 63→71, skills 135→143 (6 new agents incl. gan-evaluator/generator/planner, cpp/kotlin/flutter reviewers; 8 new commands; 8 new skills) | COMPLETE (updated README table) |
|
||||
| 4 | MED | Star Update | Update gstack ★ from 59k to 60k (60,036 actual — v0.15.0 /checkpoint, /health, cross-session timeline) | COMPLETE (updated README table) |
|
||||
| 5 | MED | Count Update | Update gstack skills 32→33 (v0.15.0 added /checkpoint and /health, but some consolidated — net +1) | COMPLETE (updated README table) |
|
||||
| 6 | LOW | Count Update | Update CE commands 4→3 (.claude/commands/ now empty; 3 coding-tutor commands remain), skills 42→40 (39 CE + 1 CT) | COMPLETE (updated README table) |
|
||||
| 7 | LOW | Count Verify | BMAD skills 43→34 — agent counted from module-help.csv (25 bmm + 9 core), previous directory counts found 43 (32 bmm + 11 core) | ON HOLD (agent likely undercounting — module-help.csv may not list all skills; keeping 43 until manual verification) |
|
||||
|
||||
Reference in New Issue
Block a user