Agent Context Audit

by AI-Builder-Club

Agent Context Audit is an AI Engineering skill for Claude Code, published by AI-Builder-Club in skills.

1.2K stars153 forkson AI-Builder-Club/skillsAdded 2026/08/20Repository updated 2026/07/27

View source on GitHub Download repo ZIP

agent-harnessagent-skillsai-agentsclaudeclaude-codedeveloper-toolsloop-engineering

Install in seconds

Install Agent Context Audit

Copy Agent Context Audit into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/AI-Builder-Club/skills/tree/main/skills/agent-context-audit ~/.claude/skills/agent-context-audit

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/AI-Builder-Club/skills.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: skills/agent-context-audit/SKILL.md in AI-Builder-Club/skills
Installs to: ~/.claude/skills/agent-context-audit
Collection: One of 10 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What Agent Context Audit does

Agent Context Audit audits a repository's agent context—CLAUDE.md files, codebase docs, skills, and tool/MCP designs—against Anthropic's Claude 5 context-engineering guidance to find overconstraint, conflicts, redundancy, stale facts, and missing unknown knowns. It produces a scored findings report with concrete rewrites and applies approved fixes, used when someone says 'audit my CLAUDE.md' or

Agent Context Audit is cataloged under AI Engineering on DirSkills. Agent Context Audit comes from a repository tagged agent-harness, agent-skills, ai-agents, claude and claude-code.

Documentation

README

Excerpt

agent-context-audit — unhobble this repo's agent context

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.

Background: Anthropic removed over 80% of Claude Code's system prompt for Claude 5 models with no measurable loss on coding evals. Older context was written for models that needed rules; newer models need judgment, good interfaces, and the facts they can't infer. This skill audits against that shift, plus the "finding your unknowns" framework (the gap between the map — your prompts/docs — and the territory — the actual codebase).

This is the opening of the README. Read the full README on GitHub.

Commands Agent Context Audit provides

Slash commands named in this skill’s SKILL.md, listed in the order they first appear.

/doctor

Frequently asked about Agent Context Audit

What else does AI-Builder-Club publish alongside Agent Context Audit?
Agent Context Audit is one of 10 skills that DirSkills catalogs from AI-Builder-Club/skills, the repository it ships in. Its siblings there include Codebase Harness Setup, Crabbox Setup and Dev Local Setup. Each one is a separate skill with its own page in this directory, installs the same way Agent Context Audit does, and is maintained by AI-Builder-Club in that same repository. The rest of the collection is listed on the AI-Builder-Club/skills page.
How does Agent Context Audit compare to other AI Engineering skills?
Agent Context Audit ranks #1169 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Agent Context Audit against them. Open each page to compare what they document and how they install.