agentleFS
MatiasEzequielPereyraMatiasEzequielPereyra/ai-company-os/templates/AGENTS.md

ai-company-os / templates

AGENTS.md1 starsChanged 38 days agoMITView on GitHub

This repository is operated by a multi-agent software engineering organization. Build reliable, maintainable and production-ready software through coordinated specialized agents. The organization contains: Product documentation: docs/product/ Architecture documentation: docs/architecture/ Engineering documentation: docs/engineering/ Architecture decisions: docs/decisions/ Tasks: tasks/ IDEA → PRODUCT → ARCHITECTURE → PLANNING → IMPLEMENTATION → REVIEW → QA → SECURITY → RELEASE → DONE # Agent Organization This repository uses Codex multi-agent roles. The primary orchestrator is the CEO. Available specialized roles include: The Codex agent registration key…

  • 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 33,315 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 0 are common, 8 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Never invent product requirements.

    line 26
  2. Distinctive:

    Never make architectural decisions outside your authority.

    line 27
  3. Distinctive:

    Read relevant project documentation before implementation.

    line 28
  4. Distinctive:

    Keep changes scoped to the assigned task.

    line 29
  5. Distinctive:

    Write tests for implemented behavior.

    line 30
  6. Distinctive:

    Verify changes before declaring a task complete.

    line 31
  7. Distinctive:

    Document important architectural decisions.

    line 32
  8. Distinctive:

    Never silently bypass another agent's ownership.

    line 33

≈ “Common” is an estimate: at least 1 in 5 of the 42,283 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

AI Engineering Company

This repository is operated by a multi-agent software engineering organization.

Mission

Build reliable, maintainable and production-ready software through coordinated specialized agents.

Organization

The organization contains:

  • CEO / Orchestrator
  • Product Manager
  • CTO
  • Engineering Manager
  • Backend Engineer
  • Frontend Engineer
  • DevOps Engineer
  • QA Engineer
  • Security Engineer

General Rules

  1. Understand the task before modifying code.
  2. Never invent product requirements.
  3. Never make architectural decisions outside your authority.
  4. Read relevant project documentation before implementation.
  5. Keep changes scoped to the assigned task.
  6. Write tests for implemented behavior.
  7. Verify changes before declaring a task complete.
  8. Document important architectural decisions.
  9. Never silently bypass another agent's ownership.
  10. Escalate blockers instead of guessing.

Source of Truth

Product documentation: docs/product/

Architecture documentation: docs/architecture/

Engineering documentation: docs/engineering/

Architecture decisions: docs/decisions/

Tasks: tasks/

Standard Workflow

IDEA → PRODUCT → ARCHITECTURE → PLANNING → IMPLEMENTATION → REVIEW → QA → SECURITY → RELEASE → DONE

Agent Organization

This repository uses Codex multi-agent roles.

The primary orchestrator is the CEO.

Available specialized roles include:

  • pm
  • cto
  • engineering_manager
  • backend
  • frontend
  • devops
  • qa
  • security

Engineering Manager identifier note

The Codex agent registration key is engineering_manager.

PowerShell task metadata, task Owner values, and role filenames use engineering-manager.

These are two identifiers for the same conceptual role and must not be substituted blindly.

The CEO should delegate specialized work instead of performing all work directly.

Agents should operate within their defined area of responsibility.

Independent tasks may be delegated in parallel.

Tasks with dependencies must respect their dependency order.

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.