agentleFS
Sign inStart free
OneByJorahOneByJorah/offivo/AGENTS.md

offivo

AGENTS.md24 starsChanged 26 days agoMITView on GitHub

Instructions for AI coding agents (OpenCode, Freebuff/Codebuff, Hermes workers, and others). Humans: see CONTRIBUTING.md. Reusable procedures live in .agents/skills/: repo-polish, readme-writer, dockerize, screenshot-capture, security-scrub, pr-workflow, release-checklist. Load the one that matches your task.

  • Reads credentials

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 1

    1. OneByJorah/VirtOffice★ 24100% same

    Edited · 0

    None found.

    Wrote their own version · 0

    None found.

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.

    Of the AGENTS.md files we read, the 31,774 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.

  • In this repository7 other files it gives its agents.

The file

We split this AGENTS.md into the rules it gives an agent

5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Very specific:

    Commit messages use Conventional Commits (feat:, fix:, docs:, chore:).

    line 26
  2. Very specific:

    Never read, print, or commit secrets.

    line 27
  3. Distinctive:

    Do not invent facts. If a command, flag, or API is unverified, check the official docs or ask.

    line 30
  4. Distinctive:

    Verify before reporting done: run the build, run the tests, open the page.

    line 31
  5. Distinctive:

    Ask before: creating releases or tags, changing repo visibility, deleting files outside your task, or adding dependencies with a …

    line 32

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
AGENTS.md

AGENTS.md

Instructions for AI coding agents (OpenCode, Freebuff/Codebuff, Hermes workers, and others). Humans: see CONTRIBUTING.md.

Project

  • What it is: replace with one sentence.
  • Stack: replace (language, framework, runtime).
  • Run locally: cp .env.example .env && docker compose up -d --build, then open http://127.0.0.1:8080.
  • Health check: GET /healthz must return 200.

Commands

TaskCommand
Build imagedocker build .
Start / stopdocker compose up -d --build / docker compose down -v
Lint markdownmarkdownlint-cli2 "**/*.md"
Lint Dockerfilehadolint Dockerfile
Scan for secretsgitleaks detect --redact --no-banner
Screenshotsstart the stack, then node scripts/screenshots.mjs

Rules

  1. Work on a branch named agent/<task>. Never push to main. Open a pull request.
  2. Commit messages use Conventional Commits (feat:, fix:, docs:, chore:).
  3. Never read, print, or commit secrets. Do not open .env files. Use .env.example for documentation.
  4. Bind services to 127.0.0.1. Never publish ports to 0.0.0.0 in compose files.
  5. Screenshots use demo data only. No real hostnames, IPs, usernames, emails, school or client names.
  6. Do not invent facts. If a command, flag, or API is unverified, check the official docs or ask.
  7. Verify before reporting done: run the build, run the tests, open the page. Paste real output.
  8. Ask before: creating releases or tags, changing repo visibility, deleting files outside your task, or adding dependencies with a network-heavy footprint.

Style

  • Match the existing code style. .editorconfig is authoritative.
  • README voice: calm, direct, specific. No hype, no filler.
  • Design language for any UI: background #0a0a09, accent #FFB300, font JetBrains Mono.

Skills

Reusable procedures live in .agents/skills/: repo-polish, readme-writer, dockerize, screenshot-capture, security-scrub, pr-workflow, release-checklist. Load the one that matches your task.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free