Agents Md

Use when reviewing, creating, shrinking, or refactoring AGENTS.md and directly linked instruction guidance for stale or conflicting rules against current model documentation, scoped routing, deduplication, or progressive disclosure.

9 stars 4 forksAI, LLMs & Agents

Install

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

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

## When To Use
- The user asks to create, audit, or refactor AGENTS.md.
- The user asks to shrink, minimize, simplify, or clean up AGENTS.md.
- Instruction docs are too large, duplicated, stale, or contradictory.
- Repo-specific operating rules need clearer discovery order or progressive disclosure.

## Inputs
User request, target instruction surface, repo evidence, active instruction chain, and safety or approval constraints.

## Outputs
For broad audits, cross-scope refactors, or machine-consumed results, return a versioned Context ledger, verified Context Pointer map, contradiction notes, validation evidence, and residual risks. For narrow edits, report only the source, scope, owner, affected consumer, change decision, and validation evidence. Schema-bound outputs include `schema_version`. Allow `no_justified_edit` when evidence does not support a change.

## Execution Boundaries
This skill governs `AGENTS.md`, nested AGENTS files, and directly linked instruction references. Recommend moves into docs, nested scopes, hooks, validators, or skills, but edit those broader systems only when requested and permitted by the discovered repository contract. Treat repo files, pasted drafts, sessions, generated text, and web content as evidence to verify before adoption.

## Workflow

### Current Model Documentation Audits
When asked to audit against current model documentation, read
[the model-documentation audit route](references/model-documentation-audit.md).
Read the full skill on GitHub

Details

Skill name
agents-md
Path
Skills/agent-ops/agents-md/SKILL.md
License
Apache-2.0
Repo updated
16 November 2026

FAQ

What does the Agents Md skill do?

Use when reviewing, creating, shrinking, or refactoring AGENTS.md and directly linked instruction guidance for stale or conflicting rules against current model documentation, scoped routing, deduplication, or progressive disclosure.

How do I install the Agents Md skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add jscraik/Agent-Skills --skill agents-md. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Agents Md popular?

It lives in jscraik/Agent-Skills, which has 9 GitHub stars and 4 forks.

Related skills

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