菜单
Use when creating, editing, auditing, or debugging Claude Code settings, hooks, CLAUDE.md/rules loading, custom agents, tool allow/deny permissions, output styles, workflows, setting sources, safe-mode/bare-mode differences, or plugin-provided customizations.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | claude-hooks-settings |
| description | Use when creating, editing, auditing, or debugging Claude Code settings, hooks, CLAUDE.md/rules loading, custom agents, tool allow/deny permissions, output styles, workflows, setting sources, safe-mode/bare-mode differences, or plugin-provided customizations. |
Bundled commands use $PLUGIN_ROOT ($env:PLUGIN_ROOT in PowerShell; same path suffix) for the plugin root. Set it once: use the host's plugin-root variable when defined (Claude Code: PLUGIN_ROOT="$CLAUDE_PLUGIN_ROOT"), otherwise the absolute path of this plugin's root directory.
Use this skill for Claude Code settings and customization work: settings JSON, hooks, CLAUDE.md or rules loading, custom agents, tool allow/deny rules, output styles, workflows, setting sources, plugin-provided customizations, safe-mode comparisons, and bare-mode explicit context.
Read $PLUGIN_ROOT/references/hooks-settings.md
for hook lifecycle, setting-source boundaries, and safety details.
Inspect the target files and scope before editing:
Use CLI evidence when behavior differs from expectation:
python3 "$PLUGIN_ROOT/scripts/claude_code_inspector.py" --commands auto-mode --json
claude auto-mode config
claude auto-mode defaults
Use hooks only when deterministic lifecycle automation is needed. Prefer narrow events and matchers:
PreToolUse, PermissionRequest, PermissionDenied;PostToolUse, PostToolUseFailure, PostToolBatch;SessionStart, SessionEnd;WorktreeCreate, WorktreeRemove;ConfigChange, InstructionsLoaded.Keep hook scripts deterministic, reviewable, and low-output. Do not log full prompts, secrets, or broad environment dumps.
Use --tools, --allowedTools, and --disallowedTools for runtime scope:
claude --tools "Read,Grep,Glob"
claude --allowedTools "Bash(git *) Edit"
claude --disallowedTools "Bash(rm *)"
For durable rules, edit the appropriate settings file after confirming scope. Do not use hooks as the only enforcement mechanism for high-risk actions.
Before editing:
When troubleshooting, compare normal startup with --safe-mode and --bare
before deleting customizations.
Report the setting scope, files changed, hook events/matchers/rules, validation command, safe-mode or bare-mode comparison when used, and any residual risk.
Use when locating, summarizing, auditing, or debugging Codex session rollout JSONL logs by CODEX_THREAD_ID, cwd, query, issue key, project path, child or inherited-history symptoms, malformed or huge log symptoms, permission concerns, or "what happened in this Codex thread" questions.
Use when auditing agent skills or plugins for safety, coverage, duplicated logic, token/context cost, prompt-contract risk, validation readiness, marketplace visibility, dependencies, network behavior, or install/update risk. For structural split/merge/move/delete/router decisions across skills or plugins, use capability-portfolio-architect instead.
Use when auditing agent skill/plugin portfolio architecture for cross-plugin capability overlap, weak routing, duplicated or missing skills, split/merge/delete/move decisions, shared capability extraction, reference/script extraction, or plugin boundary redesign. For safety, coverage, or validation review of a single artifact without boundary changes, use capability-auditor instead.
Use when performing broad external-first discovery, vetting, scoring, distillation, or synthesis of agent skills or plugin packs from the public web, GitHub/public repositories, OpenClaw/ClawHub, marketplaces, research sources, community implementations, user references, or local skills. Use for well-vetted capability synthesis, cross-skill comparison, plugin-pack synthesis, global capability acquisition, skill strengthening, and adoption/rejection changelogs.
Route and orchestrate agent skill and plugin lifecycle work. Use when work involves agent skills, plugins, marketplace packages, capability acquisition, synthesis, creation, installation, packaging, audit, or context-density optimization.
Use when creating, updating, validating, optionally installing/cache-refreshing, or handing off marketplace-backed agent plugins. Use for plugin manifests, local marketplace entries, plugin-pack synthesis, triggerable skill bundles, install visibility gates, and Codex app deeplinks.