SkillHub

Skills getsentry skills

agents-md

Use it when:
You're creating or updating a repo's AGENTS.md or CLAUDE.md and want it short and accurate.
It does:
Inspects lock files, scripts, CI, docs and code conventions first, picks root or nested scope, writes the smallest useful file and checks every path and command exists.
You get:
An AGENTS.md under 60 lines, never over 100, of command tables, key conventions and pointers to existing docs, with CLAUDE.md as a symlink rather than a copy.
Leaves out:
Intros, rationale, quality slogans, restated linter config, lists of installed skills, and content copied from the README or CONTRIBUTING.
Unlike claude-md-improver:
That one, Anthropic's, grades existing CLAUDE.md files against a rubric; this one writes a minimal file from what the repo shows.

TL;DR

Sentry's skill for the instruction files coding agents read. Before writing, the agent inspects the package manager's lock files and manifests, the commands in package.json, Makefiles, task runners and CI workflows, the README, CONTRIBUTING, docs, specs and security policy, and the code's own conventions, generated files and legacy areas. Repo-wide defaults go in a root AGENTS.md; a nested file is added only where a subtree has different commands or rules, and stays shorter than the root. When a Claude-compatible entry point is needed, CLAUDE.md becomes a symlink, never a second copy that can drift. The file keeps only sections that add non-obvious value: the package manager, a table of file-scoped test and lint commands, a table naming the exact files for setup, architecture and policies, key conventions, and a commit-attribution line for AI commits. Its writing rules favor bullets and tables, one rule per bullet, repo-relative paths, and file-scoped commands over full builds.

Summarizes the skill at e94f222.

npx skills add https://github.com/getsentry/skills --skill agents-md

skills.sh pageSource on GitHubAll skills from getsentry/skills

Total Downloads
7,500 on skills.sh, Nov 9, 2026
Repo stars
1,135 getsentry/skills
First seen
Jan 20, 2026 on skills.sh
Weekly Downloads
235
-22% over the 8 weeks to Nov 9
Weekly values
Week toInstalls
Sep 21303
Sep 28254
Oct 5511
Oct 12209
Oct 19257
Oct 26206
Nov 2217
Nov 9235
Category
category:agentscategory:software-engineering

Build agents, orchestrate workers and give agents memory.

Everything for building software: planning, coding, debugging, design, frameworks, cloud, agents and skills.
Type
type:workflow

A multi-step process the agent follows: interview, debug, run a TDD loop, review.
Effect
effect:local

Its own steps create or change files, git state or local tools.
Needs
needs:none

Instructions only. Works in any agent that supports skills.
Publisher
by:official

A verified publisher on skills.sh, or the company or maintainer behind the product the skill operates.
Topics
memorydocs-writing

SKILL.md

From getsentry/skills at e94f222. Checked daily, last changed Nov 6, 2026.

Frontmatter
name: agents-md
description: 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.

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