New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Agent Context Audit

by AI-Builder-Club in AI-Builder-Club/skills

Audit a repo's agent context — CLAUDE.md files, codebase docs, skills, and tool/MCP designs — against Anthropic's Claude 5 context-engineering guidance ("unhobbling": Anthropic cut ~80% of Claude…

No licenceAuto-check passedAgent Workflows

Install Agent Context Audit

skills CLI
$ npx skills add AI-Builder-Club/skills --skill agent-context-audit -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install AI-Builder-Club/skills agent-context-audit --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/AI-Builder-Club/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/agent-context-audit .claude/skills/agent-context-audit && rm -rf skills-src

Use ~/.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/

Facts

Skill name
agent-context-audit
GitHub stars
1.3k
Token cost
~2.2k tokens
SKILL.md length
1,116 words
Files
1
Skills in repo
11
Repo updated
First seen
Licence
None found

At a glance

Audit a repo's agent context — CLAUDE.md files, codebase docs, skills, and tool/MCP designs — against Anthropic's Claude 5 context-engineering guidance ("unhobbling": Anthropic cut ~80% of Claude…

  • Works in 5 steps: Inventory the context surface → Audit each artifact against the rubric → Probe for unknowns (the gaps docs don't… → …
  • Someone says audit my CLAUDE.md
  • SKILL.md covers The six shifts (the audit…, Step 0 — Inventory the context…, Step 1 — Audit each artifact… and Step 2 — Probe for unknowns…, plus 3 more sections
  • Calls git

What it does

Agent Context Audit is an agent skill from AI-Builder-Club/skills. Audit a repo's agent context — CLAUDE.md files, codebase docs, skills, and tool/MCP designs — against Anthropic's Claude 5 context-engineering guidance ("unhobbling": Anthropic cut ~80% of Claude Code's system prompt with no eval loss). Finds overconstraint, conflicting instructions, redundancy, stale facts, and missing "unknown knowns"; produces a scored findings report with concrete rewrites, then applies approved fixes. Use when someone says "audit my CLAUDE.md", "context audit", "unhobble this repo", "review…

Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Codebase knowledge for agents, Prompt engineering and Agent instruction files. It works with Model Context Protocol. The repository describes itself as: Codebase harness + loop engineer.

When your agent uses it

  • Someone says audit my CLAUDE.md
  • Unhobble this repo
  • Review our agent docs/skills/tools
  • After upgrading to Claude 5-generation models

Example prompts

  • “s Claude 5 context-engineering guidance (”
  • “: Anthropic cut ~80% of Claude Code”
  • “unknown knowns”
  • “/agent-context-audit”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Inventory the context surface
  2. Audit each artifact against the rubric
  3. Probe for unknowns (the gaps docs don't show)
  4. Report
  5. Apply (with approval)

What it can do on your machine

Read from SKILL.md and the folder at commit 917780c. 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

    Shell commands in SKILL.md call:

    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    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

Agent Context Audit loads about 2.2k tokens when it runs. Until then it costs about 154 tokens; SKILL.md has 1,116 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~154
When it runs · the whole SKILL.md, loaded when a task matches
~2.2k

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

Without a licence we can't republish the file, so here is its outline and opening line. It has 1,116 words (~2,170 tokens).

“Goal: find where this repo's context (CLAUDE.md, docs, skills, tool designs) hobbles a Claude 5-generation model — overconstrains it, contradicts itself, repeats itself, or hides context the model actually needs — and leave behind a findings report plus approved fixes.”

— opening of SKILL.md by AI-Builder-Club
name
agent-context-audit
user_invocable
true

Read the full SKILL.md on GitHub

Files

Just SKILL.md in skills/agent-context-audit of AI-Builder-Club/skills.

Open the folder on GitHubat commit 917780c

Compare with similar skills

Agent Context Audit 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.

Agent Context Audit compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Agent Context Audit this skillAI-Builder-Club/skills1.3k—~2.2kAutomated safety check: PassNone
Context Engineeringabashev/vfs-s31069 repos~2.6kAutomated safety check: NotesApache-2.0
MCP Code Search Tool SelectionContext-Engine-AI/Context-Engine402—~1.3kAutomated safety check: PassMIT
Dotagents Standardgetknit/knit133—~4.1kAutomated safety check: PassMIT
Entroly Context Controljuyterman1000/entroly474—~501Automated safety check: PassApache-2.0
Claude Code Mastery Squadohmyjahh/xquads-squads277—~1.1kAutomated safety check: PassMIT

Similar skills

  • Context Engineering

    abashev/vfs-s3

    Optimizes agent context setup. An agent skill from abashev/vfs-s3.

    106 GitHub starsUsed in 9 repos~2.6k tokens
    Agent WorkflowsAuto-check: notes

  • MCP Code Search Tool Selection

    Context-Engine-AI/Context-Engine

    Rules for choosing Qdrant-Indexer semantic search over grep or file reads when exploring code, debugging or asking where and why questions.

    402 GitHub stars~1.3k tokensUpdated 3 mo ago
    Agent WorkflowsAuto-check passed

  • Dotagents Standard

    getknit/knit

    Set up, author, and navigate the dotagents standard — a slim AGENTS.md "router" at the repository root plus a hidden .agents/ directory (rules, context, memory, personas, skills, specs, logs, tasks)…

    133 GitHub stars~4.1k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

  • Entroly Context Control

    juyterman1000/entroly

    Surgically select, compress, and recover codebase context using Entroly's MCP tools.

    474 GitHub stars~501 tokensUpdated today
    Agent WorkflowsAuto-check passed

  • 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.

    277 GitHub stars~1.1k tokensUpdated 11 days ago
    Agent WorkflowsAuto-check passed

  • Agentic Readiness

    CodeAlive-AI/ai-driven-development

    Audit and improve repositories for reliable agentic work across Codex and Codex App, Claude Code, and OpenCode.

    159 GitHub stars~1.2k tokensUpdated 2 days ago
    Agent WorkflowsAuto-check passed

More from AI-Builder-Club/skills

All 11 skills in this repo

  • Visual Flow Gif

    AI-Builder-Club/skills

    Create animated flow diagrams from articles, workflow notes, architecture sketches, or process descriptions using a JSON specification and a local Python/Pillow renderer.

    1.3k GitHub stars~845 tokensUpdated 25 days ago
    Auto-check passed

  • Karaoke Captions

    AI-Builder-Club/skills

    Generate TikTok/Shorts-style karaoke captions using MLX Whisper, ASS subtitles, and FFmpeg libass.

    1.3k GitHub stars~850 tokensUpdated 25 days ago
    Auto-check passed

  • Open Agent Teams

    AI-Builder-Club/skills

    Delegate tasks to ANY CLI agent (claude, codex, aider, ...) running in a detached tmux session, with a race-safe done-signal protocol and multi-turn iteration.

    1.3k GitHub stars~1.4k tokensUpdated 25 days ago
    Auto-check passed

  • New Loop

    AI-Builder-Club/skills

    Spin up a new loop (domain) in a file-based knowledge base — bootstrap the substrate if it's missing, gather the loop's charter, scaffold domains/<loop/README.md, then do ONE real test run and…

    1.3k GitHub stars~1.2k tokensUpdated 25 days ago
    Auto-check: notes

  • Crabbox Setup

    AI-Builder-Club/skills

    Scaffold an isolated CLOUD dev box per agent (via crabbox + Daytona) for any codebase — the parallel-safe counterpart to dev-local-setup.

    1.3k GitHub stars~1.9k tokensUpdated 25 days ago
    Auto-check: notes

  • SEO Growth

    AI-Builder-Club/skills

    A skill your agent uses when deciding WHERE to point SEO effort, not how to write a page.

    1.3k GitHub stars~1.9k tokensUpdated 25 days ago
    Auto-check passed

Works with

Categories

Questions about Agent Context Audit

What does Agent Context Audit do?

Audit a repo's agent context — CLAUDE.md files, codebase docs, skills, and tool/MCP designs — against Anthropic's Claude 5 context-engineering guidance ("unhobbling": Anthropic cut ~80% of Claude…. Agent Context Audit is an agent skill from AI-Builder-Club/skills.md files, codebase docs, skills, and tool/MCP designs — against Anthropic's Claude 5 context-engineering guidance ("unhobbling": Anthropic cut ~80% of Claude Code's system prompt with no eval loss).

When should I use Agent Context Audit?

Agent Context Audit fits situations like: someone says audit my CLAUDE.md; unhobble this repo; review our agent docs/skills/tools; after upgrading to Claude 5-generation models.

How do I install Agent Context Audit in Claude Code?

Run `npx skills add AI-Builder-Club/skills --skill agent-context-audit -a claude-code`. Or copy the skill folder (skills/agent-context-audit in AI-Builder-Club/skills) into .claude/skills/agent-context-audit in your project. Claude Code loads it when a task matches its description.

How do I install Agent Context Audit in Codex?

Run `npx skills add AI-Builder-Club/skills --skill agent-context-audit -a codex`. Or copy the skill folder (skills/agent-context-audit in AI-Builder-Club/skills) into .agents/skills/agent-context-audit in your project. Codex loads it when a task matches its description.

Can I use Agent Context Audit 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 AI-Builder-Club/skills --skill agent-context-audit -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agent-context-audit, .gemini/skills/agent-context-audit, .github/skills/agent-context-audit and .opencode/skills/agent-context-audit in your project.

What does Agent Context Audit need to run?

Going by SKILL.md and its folder, Agent Context Audit needs the command-line tools its instructions call (git).

Does Agent Context Audit access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Agent Context Audit 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 Agent Context Audit use?

No licence was found for Agent Context Audit or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Agent Context Audit use?

About 2.2k tokens (SKILL.md is roughly 8.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Agent Context Audit?

Skills that share tags, products or a category with Agent Context Audit: Context Engineering (abashev/vfs-s3, 106 stars), MCP Code Search Tool Selection (Context-Engine-AI/Context-Engine, 402 stars), Dotagents Standard (getknit/knit, 133 stars) and Entroly Context Control (juyterman1000/entroly, 474 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Agent Context Audit?

AI-Builder-Club (a GitHub organization) maintains it in AI-Builder-Club/skills, which has 1,288 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on September 15, 2026.

Source: AI-Builder-Club/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.