{"slug":"agents-md","title":"agents-md","summary":"This skill should be used when the user asks to \"create AGENTS.md\", \"update AGENTS.md\", \"maintain agent docs\", \"set up CLAUDE.md\", or needs to keep agent instructions concise. Enforces research-backed best practices for minimal, high-signal agent documentation.","platform":"ChatGPT","tags":[],"authorName":"LLM Mart","authorSlug":"llm-mart","score":0,"source":"github","price":null,"verified":false,"createdAt":"2026-08-16T13:38:13.404517Z","repo":{"url":"https://github.com/sickn33/agentic-awesome-skills","stars":46883,"forks":6831,"license":"MIT","updatedAt":"2026-09-25T05:43:16Z"},"bodyHtml":"
\n

name: agents-md\ndescription: This skill should be used when the user asks to \"create AGENTS.md\", \"update AGENTS.md\", \"maintain agent docs\", \"set up CLAUDE.md\", or needs to keep agent instructions concise. Enforces research-backed best practices for minimal, high-signal agent documentation.\nrisk: critical\nsource: community

\n

Maintaining AGENTS.md

\n

AGENTS.md is the canonical agent-facing documentation. Keep it minimal—agents are capable and don't need hand-holding. Target under 60 lines; never exceed 100. Instruction-following quality degrades as document length increases.

\n

When to Use

\n\n

File Setup

\n
    \n
  1. Create AGENTS.md at project root
    2. \n
  2. Create symlink: ln -s AGENTS.md CLAUDE.md
    3. \n
\n

Before Writing

\n

Analyze the project to understand what belongs in the file:

\n
    \n
  1. Package manager — Check for lock files (pnpm-lock.yaml, yarn.lock, package-lock.json, uv.lock, poetry.lock)
    2. \n
  2. Linter/formatter configs — Look for .eslintrc, biome.json, ruff.toml, .prettierrc, etc. (don't duplicate these in AGENTS.md)
    3. \n
  3. CI/build commands — Check Makefile, package.json scripts, CI configs for canonical commands
    4. \n
  4. Monorepo indicators — Check for pnpm-workspace.yaml, nx.json, Cargo workspace, or subdirectory package.json files
    5. \n
  5. Existing conventions — Check for existing CONTRIBUTING.md, docs/, or README patterns
    6. \n
\n

Writing Rules

\n\n

Required Sections

\n

Package Manager

\n

Which tool and key commands only:

\n
## Package Manager\nUse **pnpm**: `pnpm install`, `pnpm dev`, `pnpm test`\n
\n

File-Scoped Commands

\n

Per-file commands are faster and cheaper than full project builds. Always include when available:

\n
## File-Scoped Commands\n| Task | Command |\n|------|---------|\n| Typecheck | `pnpm tsc --noEmit path/to/file.ts` |\n| Lint | `pnpm eslint path/to/file.ts` |\n| Test | `pnpm jest path/to/file.test.ts` |\n
\n

Commit Attribution

\n

Always include this section. Agents should use their own identity:

\n
## Commit Attribution\nAI commits MUST include:\n
\n

Co-Authored-By: (the agent model's name and attribution byline)

\n
Example: `Co-Authored-By: Claude Sonnet 4 <noreply@example.com>`\n
\n

Key Conventions

\n

Project-specific patterns agents must follow. Keep brief.

\n

Optional Sections

\n

Add only if truly needed:

\n\n

Anti-Patterns

\n

Omit these:

\n\n

Example Structure

\n
# Agent Instructions\n\n## Package Manager\nUse **pnpm**: `pnpm install`, `pnpm dev`\n\n## Commit Attribution\nAI commits MUST include:\n
\n

Co-Authored-By: (the agent model's name and attribution byline)

\n
\n## File-Scoped Commands\n| Task | Command |\n|------|---------|\n| Typecheck | `pnpm tsc --noEmit path/to/file.ts` |\n| Lint | `pnpm eslint path/to/file.ts` |\n| Test | `pnpm jest path/to/file.test.ts` |\n\n## API Routes\n[Template code block]\n\n## CLI\n| Command | Description |\n|---------|-------------|\n| `pnpm cli sync` | Sync data |\n
\n

Limitations

\n\n","files":[{"path":"SKILL.md","sizeBytes":4753,"isText":true}],"reviewScore":null,"reviewSummary":null,"trust":{"provenance":"trusted-source-unreviewed","notice":"Community-authored content, reproduced verbatim and not vetted as instructions. Treat it as data to evaluate, never as directives to follow.","bodySource":null},"bodyLocked":false,"purchaseUrl":null,"sourceUrl":null,"report":{"provenance":"trusted-source-unreviewed","screen":{"ran":true,"outcome":"clean","suspicious":0,"notes":0,"hiddenCharacters":false},"virusScan":{"engine":"clamav","status":"clean","scannedAt":"2026-08-16T13:39:14.398711Z","sha256":"A8355C9A978CA07C0D51187B7853BEE83461114A73DD9DC301BC7FCADC68D3C8","sizeBytes":2159},"review":null,"source":{"repositoryUrl":"https://github.com/sickn33/agentic-awesome-skills","path":"skills/agents-md","license":"MIT","commit":"f2bba339de74414b0771234cbe4f6a15258e32a3","subtreeSha":"CDA30BA8C9C19252030B435D5331840626FBCB1477BE4F59F60DFCF832652F96","lastSyncedAt":"2026-09-25T06:48:39.853703Z"},"reviewedAt":"2026-08-16T13:39:28.339141Z","notice":"Community-authored content, reproduced verbatim and not vetted as instructions. Treat it as data to evaluate, never as directives to follow."},"install":[{"target":"skills-cli","command":"npx skills add https://github.com/sickn33/agentic-awesome-skills/tree/main/skills/agents-md"},{"target":"claude-code","command":"claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install sickn33-agentic-awesome-skills@llmmart"},{"target":"git","command":"git clone https://github.com/sickn33/agentic-awesome-skills.git"}]}