Catalog
getsentry/agents-md

getsentry

agents-md

Creates and maintains concise AGENTS.md and CLAUDE.md project instruction files. Use when asked to create AGENTS.md, update AGENTS.md, maintain agent docs, set up CLAUDE.md, document repository agent conventions, or keep coding-agent instructions minimal and reference-backed.

global
New~787
v1.0Saved Jul 11, 2026

Maintaining AGENTS.md

Goal: concise, actionable agent instructions. Target under 60 lines; never exceed 100.

Workflow

  1. Inspect before writing:
    • package manager: lock files and manifests
    • commands: package.json, Makefile, task runners, CI workflows
    • docs/specs/policies: README.md, CONTRIBUTING.md, docs/, specs/, policies/, SECURITY.md, .github/
    • conventions: current code patterns, test layout, generated files, legacy areas to avoid
  2. Choose scope:
    • root AGENTS.md: repo-wide defaults
    • nested AGENTS.md: only when a subtree has different commands or rules
    • closest instruction file wins; keep narrower files shorter than root files
  3. Write the smallest useful file.
  4. Verify exact paths and commands exist.

File Setup

  • Create AGENTS.md at the repository root.
  • If a Claude-compatible entrypoint is required, symlink CLAUDE.md to AGENTS.md.
  • Do not maintain divergent AGENTS.md and CLAUDE.md copies.

Default Sections

Use only sections that add non-obvious value.

# Agent Instructions

## Package Manager
- Use **pnpm**: `pnpm install`

## Commands
| Task | Command |
|------|---------|
| Test file | `pnpm vitest run path/to/file.test.ts` |
| Lint file | `pnpm eslint path/to/file.ts` |

## External References
| Need | File |
|------|------|
| Setup | `CONTRIBUTING.md` |
| Architecture | `docs/architecture.md` |
| Security policy | `SECURITY.md` |

## Key Conventions
- Generated files: update with `pnpm generate`; do not edit by hand.

## Commit Attribution
AI commits MUST include:
```
Co-Authored-By: (the agent's name and attribution byline)
```

Writing Rules

  • Use headings, bullets, and tables; avoid paragraphs.
  • Use repo-relative paths; avoid vague references like "see docs".
  • Reference existing docs/specs/policies instead of copying them.
  • List exact external files for setup, architecture, API specs, security, release, and policy docs when they exist.
  • Prefer file-scoped test/lint/typecheck commands; include full builds only when no narrower command exists.
  • Put commands in tables when there is more than one.
  • Keep one rule per bullet.
  • Keep rationale out unless it prevents a likely mistake.
  • Do not restate linter, formatter, or typechecker config.
  • Do not list installed skills or plugins.
  • Do not include generic quality slogans.

External Reference Rules

Good:

## External References
| Need | File |
|------|------|
| API contract | `docs/api.md` |
| Release process | `docs/releasing.md` |

Anti-Patterns

  • welcome text, intros, conclusions, or pleasantries
  • long prose explaining why instructions matter
  • duplicated content from README.md, CONTRIBUTING.md, or policy docs
  • project-wide commands when file-scoped commands are available
  • nested AGENTS.md files that repeat root instructions
Files3
3 files · 18.8 KB

Select a file to preview

Overall Score

86/100

Grade

A

Excellent

Safety

88

Quality

84

Clarity

88

Completeness

82

Summary

The agents-md skill teaches how to create and maintain concise AGENTS.md instruction files for coding agents in repositories. It provides a structured workflow (inspect before writing, choose scope, write minimally, verify), concrete formatting rules, anti-patterns to avoid, and external reference guidance. The skill emphasizes keeping agent instructions under 60 lines by linking to existing docs rather than duplicating them.

Detected Capabilities

file readrepo inspectionmarkdown generationfile writesymlink creation

Trigger Keywords

Phrases that MCP clients use to match this skill to user intent.

create agents.mdupdate agents.mdagent instructionsrepository conventionsclaude.md setup

Risk Signals

INFO

File write to AGENTS.md and CLAUDE.md at repository root

SKILL.md: File Setup section
INFO

Symlink creation for CLAUDE.md

SKILL.md: File Setup section
INFO

Instruction to verify exact paths and commands exist before writing

SKILL.md: Workflow step 3

Referenced Domains

External domains referenced in skill content, detected by static analysis.

agents.mdagentskills.iodevelopers.openai.comwww.apache.org

Use Cases

  • Create a root AGENTS.md file from scratch that indexes repo-wide agent conventions and commands
  • Update an existing AGENTS.md to remove duplicated prose and add external reference tables
  • Set up a CLAUDE.md symlink for Claude-specific agent compatibility without divergent copies
  • Document nested AGENTS.md overrides for subtree-specific commands or conventions in monorepos
  • Enumerate exact external file paths (docs/specs/policies) to be referenced instead of duplicated in agent instructions

Quality Notes

  • Strengths: Clear hierarchical workflow (inspect→scope→write→verify); explicit anti-patterns list prevents common mistakes; well-documented external reference rules with examples
  • Strengths: Concrete sizing goals (60 lines target, 100 max) give agents precise scope; example template shows exact output format
  • Strengths: SOURCES.md provides transparent provenance and decision rationale; SPEC.md documents scope boundaries and evaluation criteria
  • Strengths: Writing rules are specific (no welcome text, no prose, exact paths, tables for multiples) making them actionable
  • Minor: SPEC.md's 'Known Limitations' section acknowledges that private policies may not be discoverable, but doesn't provide fallback guidance for that case
  • Minor: No error handling guidance for edge cases (what if a command doesn't exist? if docs are malformed?)
Model: claude-haiku-4-5-20251001Analyzed: Jul 11, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

Add getsentry/agents-md to your library

Command Palette

Search for a command to run...