agentleFS
rpraharajrpraharaj/ai-engineer/AGENTS.md

ai-engineer

AGENTS.md1 starsChanged 15 days agoMITView on GitHub

This repository is ai-engineer, a portable skill pack (home: https://rajeshpraharaj.com/). Skills must work in any coding agent that loads a SKILL.md folder (name + description frontmatter, markdown body).

The file

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

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Do not add host-only frontmatter (when-to-use, argument-hint, disable-model-invocation, model, allowed-tools).

    line 10
  2. Distinctive:

    Do not name host products, host tools, or host slash commands in skill bodies.

    line 11
  3. Distinctive:

    Write procedures for one agent with a filesystem, a shell, and (usually) git.

    line 12
  4. Very specific:

    Keep each SKILL.md under 500 lines.

    line 13
  5. Very specific:

    Always-on defaults live in templates/AGENTS.md.

    line 18

≈ “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

Working on this pack

This repository is ai-engineer, a portable skill pack (home: https://rajeshpraharaj.com/). Skills must work in any coding agent that loads a SKILL.md folder (name + description frontmatter, markdown body).

Format

  • One directory per skill under skills/<name>/.
  • name in frontmatter must match the directory name.
  • Frontmatter fields allowed: name, description, license, metadata. Optional compatibility only for real environment needs (e.g. git).
  • Do not add host-only frontmatter (when-to-use, argument-hint, disable-model-invocation, model, allowed-tools).
  • Do not name host products, host tools, or host slash commands in skill bodies.
  • Write procedures for one agent with a filesystem, a shell, and (usually) git.
  • Keep each SKILL.md under 500 lines. Put long checklists and copy-templates in references/.
  • description must say what the skill does and when to use it (max 1024 characters).

One home per fact

  • Always-on defaults live in templates/AGENTS.md. Keep skills/explore-codebase/references/agents-template.md byte-identical (python3 scripts/validate.py checks).
  • Quality checks and secret-file patterns live in skills/engineering-bar/SKILL.md.
  • Other skills point at those by name. Do not paste them in full.

Validation

python3 scripts/validate.py
python3 -m unittest discover -s tests -v

Install locally

./scripts/install.sh

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.

Reviews can't be read right now.

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.