Agent Setup Health Audit
tw93/Waza
Audits a project's agent configuration, instruction drift, hooks, MCP and AI maintainability, then reports prioritized findings with evidence and next actions.
This skill should be used when working with Claude Code infrastructure including agents, skills, slash commands, hooks, plugins, settings.json, or CLAUDE.md files.
Install Claude Code Expert
$ npx skills add closedloop-ai/claude-plugins --skill claude-code-expert -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install closedloop-ai/claude-plugins claude-code-expert --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/closedloop-ai/claude-plugins.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/platform/skills/claude-code-expert .claude/skills/claude-code-expert && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "claude-code-expert" agent skill from https://github.com/closedloop-ai/claude-plugins/tree/main/plugins/platform/skills/claude-code-expert into .claude/skills/claude-code-expert/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "claude-code-expert", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/closedloop-ai/claude-plugins/tree/main/plugins/platform/skills/claude-code-expertType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add closedloop-ai/claude-plugins --skill claude-code-expert -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install closedloop-ai/claude-plugins claude-code-expert --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/closedloop-ai/claude-plugins.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/platform/skills/claude-code-expert .agents/skills/claude-code-expert && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "claude-code-expert" agent skill from https://github.com/closedloop-ai/claude-plugins/tree/main/plugins/platform/skills/claude-code-expert into .agents/skills/claude-code-expert/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "claude-code-expert", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add closedloop-ai/claude-plugins --skill claude-code-expert -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install closedloop-ai/claude-plugins claude-code-expert --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/closedloop-ai/claude-plugins.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/platform/skills/claude-code-expert .cursor/skills/claude-code-expert && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "claude-code-expert" agent skill from https://github.com/closedloop-ai/claude-plugins/tree/main/plugins/platform/skills/claude-code-expert into .cursor/skills/claude-code-expert/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "claude-code-expert", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/closedloop-ai/claude-plugins.git --path plugins/platform/skills/claude-code-expert--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add closedloop-ai/claude-plugins --skill claude-code-expert -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install closedloop-ai/claude-plugins claude-code-expert --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/closedloop-ai/claude-plugins.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/platform/skills/claude-code-expert .gemini/skills/claude-code-expert && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "claude-code-expert" agent skill from https://github.com/closedloop-ai/claude-plugins/tree/main/plugins/platform/skills/claude-code-expert into .gemini/skills/claude-code-expert/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "claude-code-expert", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install closedloop-ai/claude-plugins claude-code-expertInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add closedloop-ai/claude-plugins --skill claude-code-expert -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/closedloop-ai/claude-plugins.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/platform/skills/claude-code-expert .github/skills/claude-code-expert && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "claude-code-expert" agent skill from https://github.com/closedloop-ai/claude-plugins/tree/main/plugins/platform/skills/claude-code-expert into .github/skills/claude-code-expert/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "claude-code-expert", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add closedloop-ai/claude-plugins --skill claude-code-expert -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install closedloop-ai/claude-plugins claude-code-expert --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/closedloop-ai/claude-plugins.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/platform/skills/claude-code-expert .opencode/skills/claude-code-expert && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "claude-code-expert" agent skill from https://github.com/closedloop-ai/claude-plugins/tree/main/plugins/platform/skills/claude-code-expert into .opencode/skills/claude-code-expert/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "claude-code-expert", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
claude-code-expert- GitHub stars
- 122
- Token cost
- ~1.8k tokens
- SKILL.md length
- 461 words
- Files
- 7 (incl. references)
- Skills in repo
- 41
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
This skill should be used when working with Claude Code infrastructure including agents, skills, slash commands, hooks, plugins, settings.json, or CLAUDE.md files.
- Works in 4 steps: Should Claude remember X automatically?… → Should Claude follow workflow Y… → Do users need shortcut to Z? → Command → …
- YAML frontmatter
- SKILL.md covers When to Use, Core Concepts, File Formats Quick Reference and Hooks Quick Reference, plus 6 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Claude Code Expert is an agent skill from closedloop-ai/claude-plugins. This skill should be used when working with Claude Code infrastructure including agents, skills, slash commands, hooks, plugins, settings.json, or CLAUDE.md files. Triggers on YAML frontmatter, .claude/ directory files, Task tool configuration, or hook debugging. Do NOT use for creating NEW skills from scratch - use claude-creator instead.
Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including reference files (for example `references/agent-patterns.md`, `references/command-patterns.md` and `references/configuration.md`).
It sits in Agent Workflows, covering Hooks and plugins and Agent instruction files. The repository describes itself as: Open-source Claude Code plugins for multi-agent software delivery. Plan-first SDLC workflow, code review, LLM quality judges, and self-learning — grounded in your codebase… The licence is Apache-2.0.
When your agent uses it
- YAML frontmatter
- .claude/ directory files
- Task tool configuration
- Creating NEW skills from scratch - use claude-creator instead
Example prompts
- “/claude-code-expert”
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- Should Claude remember X automatically? → Skill
- Should Claude follow workflow Y step-by-step? → Agent
- Do users need shortcut to Z? → Command
- Should setup be shared/distributed? → Plugin
What it can do on your machine
Read from SKILL.md and the folder at commit 476b54c. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are yaml and json).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Claude Code Expert loads about 1.8k tokens when it runs, and up to ~14k if it reads all its reference files. Until then it costs about 90 tokens; SKILL.md has 461 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from closedloop-ai/claude-plugins at commit 476b54c, republished under its Apache-2.0 licence (© closedloop-ai). 461 words, ~1,806 tokens.
Download SKILL.mdSave it as
.claude/skills/claude-code-expert/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.- name
- claude-code-expert
- description
- This skill should be used when working with Claude Code infrastructure including agents, skills, slash commands, hooks, plugins, settings.json, or CLAUDE.md files. Triggers on YAML frontmatter, .claude/ directory files, Task tool configuration, or hook debugging. Do NOT use for creating NEW skills from scratch - use claude-creator instead.
Claude Code Expert
Comprehensive quick-reference for Claude Code extensibility. For detailed examples, see the reference files linked at the end.
When to Use
- Updating existing skills, agents, slash commands, or plugins
- Creating new agents, slash commands, or plugins (NOT new skills)
- Debugging hook configurations or integration issues
- Reviewing Claude Code file formats for correctness
Do NOT use for: Creating NEW skills from scratch (use claude-creator instead), general coding tasks, or CI/CD unrelated to Claude Code.
Core Concepts
The Four Extension Types
| Type | Invocation | Purpose | Location |
|---|---|---|---|
| Skills | Auto (model-invoked) | Persistent context/knowledge | ~/.claude/skills/, .claude/skills/, <plugin>/skills/ |
| Agents | Explicit (@agent-name) | Multi-step workflows | .claude/agents/, <plugin>/agents/ |
| Commands | User (/command) | Saved prompts/shortcuts | ~/.claude/commands/, .claude/commands/, <plugin>/commands/ |
| Plugins | Package | Bundled distribution | .claude-plugin/plugin.json |
Decision Framework
- Should Claude remember X automatically? → Skill
- Should Claude follow workflow Y step-by-step? → Agent
- Do users need shortcut to Z? → Command
- Should setup be shared/distributed? → Plugin
File Formats Quick Reference
Skill Frontmatter
---
name: skill-name # Required: lowercase, hyphens, max 64 chars
description: This skill should be used when [triggers]. It provides [capabilities]. # Required: max 1024 chars
allowed-tools: Read, Grep, Glob # Optional: tool restrictions
context: fork # Optional: run in forked sub-agent
agent: my-agent # Optional: use agent's config
hooks: # Optional: component-scoped hooks
PreToolUse: [...]
PostToolUse: [...]
Stop: [...]
---Skills hot-reload when modified. See references/skill-triggers.md for trigger optimization.
Agent Frontmatter
---
name: agent-name # Required: kebab-case, match filename
description: What agent does and when to use it. # Required
model: opus # Optional: sonnet, opus, haiku
color: blue # Optional: visual identifier
tools: Read, Grep, Glob, Bash # Optional: tool restrictions
hooks: # Optional: component-scoped hooks
PreToolUse: [...]
PostToolUse: [...]
Stop: [...]
---Disable agents: "disallowed-tools": ["Task(agent-name)"] in settings.json.
Command Frontmatter
---
description: Brief description for autocomplete # Optional
argument-hint: [file] [options] # Optional: shown in picker
model: opus # Optional: override model
allowed-tools: Bash(git *), Read, Grep # Optional: tool restrictions
disable-model-invocation: false # Optional: prevent Skill tool calling
hooks: # Optional: component-scoped hooks
PreToolUse: [...]
Stop: [...]
---Special syntax: $ARGUMENTS, $1/$2, inline bash with exclamation prefix (requires allowed-tools), @path/file
See references/command-patterns.md for patterns and examples.
Plugin Manifest
{
"name": "plugin-name",
"description": "What this plugin provides",
"version": "1.0.0",
"author": "Author Name"
}Hooks Quick Reference
Locations: settings.json (global) or frontmatter (component-scoped)
| Hook | Timing | Frontmatter | settings.json |
|---|---|---|---|
PreToolUse | Before tool runs | ✅ | ✅ |
PostToolUse | After tool completes | ✅ | ✅ |
Stop | When component/agent finishes | ✅ | ✅ |
UserPromptSubmit | When user sends message | ❌ | ✅ |
PermissionRequest | When permission requested | ❌ | ✅ |
SessionStart | Session starts/resumes | ❌ | ✅ |
SessionEnd | Session ends | ❌ | ✅ |
SubagentStart/Stop | Subagent lifecycle | ❌ | ✅ |
Notification | Notification sent | ❌ | ✅ |
PreCompact | Before context compact | ❌ | ✅ |
Matcher patterns: Bash(git commit:*), Write(*.py), Edit(src/**/*.ts), mcp__server_*, *
Hook options: matcher, command, once (run only once per session)
See references/hook-recipes.md for complete schemas and recipes.
Show full SKILL.md (198 more words)Show less
Settings & CLI
Location: .claude/settings.json or ~/.claude/settings.json
| Setting | Description |
|---|---|
agent | Use agent's system prompt, tools, model for main thread |
language | Response language (e.g., "japanese") |
disallowed-tools | Disable tools: Task(AgentName), mcp__server_* |
CLI flags: --agent, --tools, --disable-slash-commands, --session-id, --system-prompt
CLAUDE.md & Rules
CLAUDE.md: Project root or ~/.claude/CLAUDE.md. Keep concise (always loaded).
Rules directory: .claude/rules/*.md - modular alternative to single CLAUDE.md.
Writing Style
CRITICAL: Use imperative/infinitive form, not second person.
| ✅ Correct | ❌ Incorrect |
|---|---|
| "Identify candidate files..." | "You should identify..." |
| "Extract data from..." | "You can extract..." |
Common Issues
| Issue | Cause | Fix |
|---|---|---|
| Skill not triggering | Vague description, >1024 chars | Add specific trigger keywords |
| Hook not executing | Not executable, wrong path | chmod +x, use relative path from root |
| Agent not found | Name mismatch, wrong location | Match name to filename, check .claude/agents/ |
| Inline bash not working | Missing allowed-tools | Add allowed-tools: Bash(...) to frontmatter |
Validation Checklist
- YAML frontmatter has required fields (
name,description) - Names: kebab-case for agents, lowercase-hyphens for skills
- Descriptions include trigger conditions (for skills)
- Imperative writing style throughout
- File locations correct for component type
- Hook scripts executable (
chmod +x)
References
- references/skill-triggers.md - Skill triggers, body structure, frontmatter
- references/agent-patterns.md - Agent body structure, frontmatter, patterns
- references/command-patterns.md - Command patterns, TodoWrite usage
- references/hook-recipes.md - Hook schemas, recipes, debugging
- references/configuration.md - CLAUDE.md, rules, settings, CLI, background agents
© closedloop-ai, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 6 other files (references) in plugins/platform/skills/claude-code-expert of closedloop-ai/claude-plugins.
- SKILL.md
- references/agent-patterns.md
- references/command-patterns.md
- references/configuration.md
- references/hook-recipes.md
- references/skill-triggers.md
- references/sub-agents-config.schema.json
Open the folder on GitHubat commit 476b54c
Compare with similar skills
Claude Code Expert next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Claude Code Expert this skillclosedloop-ai/claude-plugins | 122 | — | ~1.8k | Automated safety check: Pass | Apache-2.0 | |
| Agent Setup Health Audittw93/Waza | 7.2k | — | ~5.2k | Automated safety check: Notes | MIT | |
| Working With Claude Code Docsobra/superpowers-developing-for-claude-code | 142 | — | ~1.5k | Automated safety check: Pass | None | |
| Directional Promptingkingbootoshi/directional-prompting | 143 | — | ~2.3k | Automated safety check: Pass | MIT | |
| Agenticashibing624/agentica | 352 | — | ~1.8k | Automated safety check: Notes | Apache-2.0 | |
| Claude Code Mastery Squadohmyjahh/xquads-squads | 276 | — | ~1.1k | Automated safety check: Pass | MIT |
Similar skills
Working With Claude Code Docs
obra/superpowers-developing-for-claude-code
Looks up official Claude Code documentation stored as reference files instead of guessing about CLI commands, configuration, or plugin APIs.
Directional Prompting
kingbootoshi/directional-prompting
Write prompts, system instructions, agent directives, slash commands, and skill descriptions using two stacked layers — outcome-first (define the destination, success criteria, stopping condition)…
Agentica
shibing624/agentica
How to answer questions about the agentica product you are running inside — CLI flags, config.yaml profiles, API keys, models, sessions, resume, workspace, AGENTS.md standing rules, skills, logs…
Claude Code Mastery Squad
ohmyjahh/xquads-squads
Routes a request to one of eight specialist agents covering hooks, skills, subagents, MCP integration and context engineering for Claude Code.
Vault Setup
earlyaidopters/second-brain
Interactive Obsidian vault configurator. An agent skill from earlyaidopters/second-brain.
More from closedloop-ai/claude-plugins
All 41 skills in this repoCodex Review
closedloop-ai/claude-plugins
Run Codex to review a plan file and return structured feedback with a verdict.
Critic Cache
closedloop-ai/claude-plugins
Check if critic reviews are still valid before re-running Phase 2.5 critics.
Cross Repo Cache
closedloop-ai/claude-plugins
Check if cross-repo coordinator results can be reused, avoiding redundant Sonnet agent launches.
Eval Cache
closedloop-ai/claude-plugins
Check for a cached plan-evaluation.json result before launching the plan-evaluator agent.
Find Plugin File
closedloop-ai/claude-plugins
This skill should be used when needing to locate files within the Claude Code plugins cache directory (~/.claude/plugins/cache).
Gh Monitor PR
closedloop-ai/claude-plugins
Start a detached GitHub pull-request monitor that wakes the exact launching Codex Desktop or CLI root through the managed Codex App Server when review, CI, conflict, merge-queue, closure, readiness…
Related
Categories
Questions about Claude Code Expert
What does Claude Code Expert do?
This skill should be used when working with Claude Code infrastructure including agents, skills, slash commands, hooks, plugins, settings.json, or CLAUDE.md files. Claude Code Expert is an agent skill from closedloop-ai/claude-plugins.md files.
When should I use Claude Code Expert?
Claude Code Expert fits situations like: YAML frontmatter; .claude/ directory files; task tool configuration; creating NEW skills from scratch - use claude-creator instead.
How do I install Claude Code Expert in Claude Code?
Run `npx skills add closedloop-ai/claude-plugins --skill claude-code-expert -a claude-code`. Or copy the skill folder (plugins/platform/skills/claude-code-expert in closedloop-ai/claude-plugins) into .claude/skills/claude-code-expert in your project. Claude Code loads it when a task matches its description.
How do I install Claude Code Expert in Codex?
Run `npx skills add closedloop-ai/claude-plugins --skill claude-code-expert -a codex`. Or copy the skill folder (plugins/platform/skills/claude-code-expert in closedloop-ai/claude-plugins) into .agents/skills/claude-code-expert in your project. Codex loads it when a task matches its description.
Can I use Claude Code Expert in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add closedloop-ai/claude-plugins --skill claude-code-expert -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/claude-code-expert, .gemini/skills/claude-code-expert, .github/skills/claude-code-expert and .opencode/skills/claude-code-expert in your project.
What does Claude Code Expert need to run?
SKILL.md names no scripts, command-line tools or credentials: Claude Code Expert is instructions for the agent only.
Does Claude Code Expert access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Claude Code Expert safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Claude Code Expert use?
Claude Code Expert is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Claude Code Expert use?
About 1.8k tokens (SKILL.md is roughly 7.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 12k tokens, read only when the agent opens those files.
What are the alternatives to Claude Code Expert?
Skills that share tags, products or a category with Claude Code Expert: Agent Setup Health Audit (tw93/Waza, 7.2k stars), Working With Claude Code Docs (obra/superpowers-developing-for-claude-code, 142 stars), Directional Prompting (kingbootoshi/directional-prompting, 143 stars) and Agentica (shibing624/agentica, 352 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Claude Code Expert?
closedloop-ai (a GitHub organization) maintains it in closedloop-ai/claude-plugins, which has 122 GitHub stars. The repository holds 41 skills in this directory. The repository was last updated on October 7, 2026.
Source: closedloop-ai/claude-plugins on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.