agentleFS
house-of-giantshouse-of-giants/projectskills/AGENTS.md

projectskills

AGENTS.md2 starsChanged 6 months agoMITView on GitHub

Guidelines for AI agents working in this repository. This repository contains Project Skills: installable Agent Skills for preserving project context from meetings through decisions, requirements, tickets, PRs, and delivery closeout. The repo follows the cross-agent skill layout: Skills are intended to work with .agents/skills/ consumers and be portable across Claude Code, Codex, Cursor, Windsurf, Hermes, and other agents that support markdown skills. Every skill must live at: Required frontmatter: Before committing, check: Do not expand the catalog until the first…

  • 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 32,671 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 repository6 other files it gives its agents.

The file

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

8 rules. About 1 is common, 6 are distinctive, and 1 is very specific to this project.

  • ≈1

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    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. Distinctive:

    Keep client/project examples fake or sanitized.

    line 23
  2. Common:

    Do not commit secrets, credentials, raw private transcripts, or real client data.

    line 24
  3. Distinctive:

    Every skill must live at:

    line 28
  4. Distinctive:

    Use lowercase letters, numbers, and hyphens only.

    line 48
  5. Very specific:

    Keep SKILL.md focused. Move long references into references/ later if needed.

    line 50
  6. Distinctive:

    Use checklists and output formats.

    line 71
  7. Distinctive:

    Avoid hype inside skill bodies.

    line 72
  8. Distinctive:

    Do not expand the catalog until the first vertical slice is useful:

    line 77

≈ “Common” is an estimate: at least 1 in 5 of the 41,581 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

Guidelines for AI agents working in this repository.

Repository overview

This repository contains Project Skills: installable Agent Skills for preserving project context from meetings through decisions, requirements, tickets, PRs, and delivery closeout.

The repo follows the cross-agent skill layout:

skills/<skill-name>/SKILL.md

Skills are intended to work with .agents/skills/ consumers and be portable across Claude Code, Codex, Cursor, Windsurf, Hermes, and other agents that support markdown skills.

Product principles

  • Lead with practical project workflows and strictly formatted markdown, not protocol mechanics.
  • project-context is the foundation skill. Other skills should read .agents/project-context.md before acting.
  • Preserve source references. Do not invent decisions, requirements, owners, or execution evidence.
  • Distinguish candidate decisions from accepted decisions.
  • Keep client/project examples fake or sanitized.
  • Do not commit secrets, credentials, raw private transcripts, or real client data.

Skill format

Every skill must live at:

skills/<skill-name>/SKILL.md

Required frontmatter:

---
name: skill-name
description: When to use this skill. Include trigger phrases and scope boundaries.
metadata:
  version: 0.1.0
---

Rules:

  • name must match the directory name exactly.
  • Use lowercase letters, numbers, and hyphens only.
  • Description should explain when the agent should use the skill.
  • Keep SKILL.md focused. Move long references into references/ later if needed.

Validation

Run:

./validate-skills.sh

Before committing, check:

git status --short
git diff --check

Writing style

  • Direct and instructional.
  • Concrete workflows over generic advice.
  • Use checklists and output formats.
  • Avoid hype inside skill bodies.
  • Make the agent's next action obvious.

Current v0.1 cutline

Do not expand the catalog until the first vertical slice is useful:

  1. README and repo scaffold.
  2. project-context skill.
  3. Basic fake example.
  4. Review and patch.
  5. Then add decision/requirement/execution skills.

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.