Agent context · Checked 4 August 2026

context-audit: Find stale and conflicting agent rules

Audit the instructions loaded into every agent task.

context-audit is an agent skill that finds conflicts, duplication, obvious rules, and outdated constraints across AGENTS.md files, skills, hooks, and tool descriptions.

Type
skill
Works on
Claude Code, Codex, Cursor, Kimi Code CLI

Open context-audit ↗︎

Audit all the instructions together

context-audit tells an agent to inventory the guidance it receives from AGENTS.md, CLAUDE.md, skills, hooks, tool descriptions, and harness prompts. It reads those layers together, then classifies rules as conflicts, duplicates, obvious guidance, outdated blanket constraints, or project-specific gotchas.

Use it when an agent ignores rules or a project instruction file keeps growing. The output is a proposed diff with before-and-after line counts, not an automatic rewrite.

Keep the human approval step

The skill explicitly says to propose deletions rather than apply them. That matters because an awkward rule may be scar tissue from a real production incident. Ask the agent to quote both sides of every conflict and flag the one deletion it is least confident about, then approve or reject each change.

This is a community skill distilled from public context-engineering ideas, not an official Anthropic tool. Installation behaviour also differs by agent; the repository documents those differences.

Featured in Swipe

Sources

Swipe the best AI skills, prompts, and workflows.

The newsletter to learn AI by stealing the cool ideas, skills, and tools you didn't know you needed.

One more step.

Check your inbox to confirm your subscription. Can't find it? Check your spam or junk folder.