agentleFS
kucherenkokucherenko/gangsta/AGENTS.md

gangsta

AGENTS.md85 starsChanged 20 days agoMITView on GitHub

Gangsta is an AI agentic skills framework for spec-driven development. Skills are behavior-shaping code, not documentation. They must be tested rigorously. Every skill change requires: 1. Baseline testing: Run a pressure scenario WITHOUT the change, document behavior 2. Change testing: Run the same scenario WITH the change, document improvement 3. Include both results in your PR Active Negative Constraints in docs/gangsta/constitution.md are binding on contributors. Adding or modifying a Negative Constraint requires Don approval through a Heist; do not edit…

The file

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

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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:

    Every skill change requires:

    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

Contributing to Gangsta

What This Is

Gangsta is an AI agentic skills framework for spec-driven development. Skills are behavior-shaping code, not documentation. They must be tested rigorously.

What Will NOT Be Accepted

  • Third-party dependencies (this is a zero-dependency package)
  • Changes that weaken Omerta governance rules
  • Skills without adversarial pressure testing
  • Bulk PRs with unrelated changes bundled together
  • "Improvements" that add complexity without clear value
  • Narrative storytelling in skill content (skills are instructions, not blog posts)

Skill Changes

Every skill change requires:

  1. Baseline testing: Run a pressure scenario WITHOUT the change, document behavior
  2. Change testing: Run the same scenario WITH the change, document improvement
  3. Include both results in your PR

The Laws Apply to Contributors Too

  • Omerta Law 3 (Rule of Truth): Every claim in a PR must be verifiable
  • Omerta Law 5 (Spec is Law): Changes must align with the framework design spec

The Constitutional Floor

Active Negative Constraints in docs/gangsta/constitution.md are binding on contributors. Adding or modifying a Negative Constraint requires Don approval through a Heist; do not edit docs/gangsta/constitution.md directly in a PR without an associated Heist.

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.