Agents Md Lint

Audit and trim AI agent instruction files (AGENTS.md, CLAUDE.md, CONVENTIONS.md, .cursorrules, etc.) by testing which facts an AI agent can discover from code alone. Use when asked to lint, audit, optimize, prune, or trim any agent instruction file in a repository. Removes redundant documentation that wastes context tokens. Supports a dry-run mode that reports findings without modifying files.

9 starsAI, LLMs & Agents Plugin marketplace

Install

Claude Code plugin
/plugin marketplace add borkweb/skills

The repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add borkweb/skills --skill agents-md-lint
Manual install
git clone --depth 1 https://github.com/borkweb/skills.git /tmp/skills
mkdir -p ~/.claude/skills
cp -r /tmp/skills/skills/core/agents-md-lint ~/.claude/skills/agents-md-lint

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# agents-md-lint

Audit AI agent instruction files by spawning a blind sub-agent that tries to rediscover each documented fact from code search alone. Test descriptive facts for practical discovery cost. Preserve normative instructions even when examples of compliance are visible in code.

This works on any file whose purpose is to give an AI agent context about a codebase: AGENTS.md, CLAUDE.md, CONVENTIONS.md, .cursorrules, or similar. The workflow refers to these collectively as "instruction files."

## Modes

**Default (rewrite):** Produces a report and rewrites the instruction files with only the surviving facts.

**Dry-run:** Produces the report but does not modify any files. Use this when the user wants to see what would change before committing, or says things like "just show me," "report only," or "what's redundant." Ask which mode the user wants if it's ambiguous, in the same question as Step 1's extra/excluded files check.

## Workflow

### 1. Discover and normalize instruction files

Scan the repo for instruction files. Common names: `AGENTS.md`, `CLAUDE.md`, `CONVENTIONS.md`, `.cursorrules`, `.github/copilot-instructions.md`. Ask the user if there are others, or if any should be excluded — together with the mode question when mode is ambiguous, so the user answers once.

Rename or symlink instruction files only when separately requested; trimming does not change their discovery paths.

### 2. Extract facts
Read the full skill on GitHub

Details

Skill name
agents-md-lint
Repository
borkweb/skills
Path
skills/core/agents-md-lint/SKILL.md
License
MIT
Repo updated
18 November 2026

FAQ

What does the Agents Md Lint skill do?

Audit and trim AI agent instruction files (AGENTS.md, CLAUDE.md, CONVENTIONS.md, .cursorrules, etc.) by testing which facts an AI agent can discover from code alone. Use when asked to lint, audit, optimize, prune, or trim any agent instruction file in a repository. Removes redundant documentation that wastes context tokens. Supports a dry-run mode that reports findings without modifying files.

How do I install the Agents Md Lint skill?

Claude Code plugin: /plugin marketplace add borkweb/skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Agents Md Lint popular?

It lives in borkweb/skills, which has 9 GitHub stars and 0 forks.

Related skills

Prototype

9

borkweb/skills

Build a throwaway prototype to flesh out a design before committing to it. Routes between two branches — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route. Use when the user wants to prototype, sanity-check a data model or state machine, mock up a UI, explore design options, or says "prototype this", "let me play with it", "try a few designs".

Frontend & DesignIn 1 list

Auto Scope

9

borkweb/skills

Scopes a coding task before implementation — names the handful of files actually relevant (read/edit these), the areas to leave alone, and any open scope questions, so work doesn't start by reading the whole repo. Fires proactively at the start of substantive, multi-file, or unfamiliar-area work; stays silent on single-file edits, one-line fixes, questions, and continued work in an area already scoped this session. Use when beginning a feature, bug fix, or refactor that could plausibly touch several files or an area not yet seen this session.

Software Development

Caveman

9

borkweb/skills

Speak in a terse caveman style only when explicitly requested by name. Supports lite, full and ultra; persists until stopped. Ordinary brevity or token-efficiency requests do not activate it.

Other

Cmd Agent Persona Set

9

Olshansk/agent-skills

Prime the agent with a behavioral persona for the conversation

AI, LLMs & Agents

Cdp Skills

5

realsigridjin/interview-copilot-with-skills

Claude Developer Platform Skills feature. Custom knowledge packages for agents, curated playbooks, and versioned expertise domains.

AI, LLMs & Agents

Cmd Latest Msg

9

Olshansk/agent-skills

Store or retrieve the latest agent message to /tmp/agents/{agent}/

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.