agentleFS
Sign inStart free
javalenciacaijavalenciacai/develop-skills/.agents/agents.md

develop-skills

AGENTS.md0 starsChanged 9 months agoMITView on GitHub

This file coordinates the AI agent system for the project. It learns and adapts according to project evolution. Each agent has its configuration in .agents/skills/[role]/agents.md and .agents/skills/[role]/SKILL.md. See complete structure in SKILL.md at the root of the project.

The file

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

6 rules. About 0 are common, 3 are distinctive, and 3 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.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Single entry point: All tasks enter through the CTO

    line 7
  2. Distinctive:

    Skills restriction: No agent can execute a task without a specific skill

    line 8
  3. Very specific:

    If the skill doesn't exist → use find-skills to search

    line 9
  4. Very specific:

    If not found → use skill-creator to create

    line 10
  5. Distinctive:

    Only then execute the task

    line 11
  6. Very specific:

    Create skills: https://skills.sh/anthropics/skills/skill-creator

    line 107

≈ “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

Agent Orchestrator

This file coordinates the AI agent system for the project. It learns and adapts according to project evolution.

Fundamental Rules

  1. Single entry point: All tasks enter through the CTO
  2. Skills restriction: No agent can execute a task without a specific skill
    • If the skill doesn't exist → use find-skills to search
    • If not found → use skill-creator to create
    • Only then execute the task
  3. Strict hierarchy: Tasks flow according to organizational structure
  4. Project learning: This file is updated with project-specific patterns and conventions

Agent Structure

CTO (Entry point)
├── PM (Product)
│   ├── PO (Requirements)
│   └── UX (Design)
├── QAL (Quality)
│   ├── QA (Testing)
│   └── SecOps (Security)
├── TL (Technical)
│   ├── Architect (Architecture)
│   └── Dev (Development)
├── InfraLead (Infrastructure)
│   ├── DevOps (CI/CD)
│   └── DBA (Databases)
└── DataLead (Data/AI)
    ├── DataEng (Pipelines)
    └── AIEng (AI/ML Models)

Project Learning

Detected Technology Stack

<!-- Automatically updated according to project analysis -->
  • Frontend: (to be detected)
  • Backend: (to be detected)
  • Database: (to be detected)
  • Infrastructure: (to be detected)

Patterns and Conventions

<!-- Agents add detected project patterns here -->
  • File structure: (to be detected)
  • Code standards: (to be detected)
  • Workflows: (to be detected)

Skills Installed by Domain

<!-- Record of added skills, organized by domain -->

Product

  • find-skills ✓
  • skill-creator ✓

Development

  • find-skills ✓
  • skill-creator ✓

Infrastructure

  • find-skills ✓
  • skill-creator ✓

Quality

  • find-skills ✓
  • skill-creator ✓

Data/AI

  • find-skills ✓
  • skill-creator ✓

Delegation Flow

sequenceDiagram
    User->>CTO: Request
    CTO->>CTO: Analyze domain
    CTO->>Sub-orchestrator: Delegate
    Sub-orchestrator->>Executor: Assign task
    Executor->>Executor: Skill exists?
    alt Skill doesn't exist
        Executor->>find-skills: Search skill
        alt Skill found
            Executor->>Executor: Install skill
        else Skill doesn't exist
            Executor->>skill-creator: Create skill
        end
    end
    Executor->>Executor: Execute with skill
    Executor->>Sub-orchestrator: Report result
    Sub-orchestrator->>CTO: Consolidate
    CTO->>User: Respond

Agent Configuration

Each agent has its configuration in .agents/skills/[role]/agents.md and .agents/skills/[role]/SKILL.md.

See complete structure in SKILL.md at the root of the project.

References

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