agentleFS
creanlabcreanlab/agent-genome-lab/AGENTS.md

agent-genome-lab

AGENTS.md2 starsChanged 4 months agoMITView on GitHub

This repository uses the NVE Universal Failure Genome + SkillGraph superstructure (v2.3.0).

The file

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

10 rules. About 1 is common, 6 are distinctive, and 3 are 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.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before changing architecture, memory, workflows, sharing, or Failure Genome behavior, read:

    line 6
  2. Distinctive:

    Do not delete valuable existing assets without explicit approval.

    line 22
  3. Distinctive:

    Use docs as the system of record.

    line 23
  4. Very specific:

    Keep canonical memory structured in .evolution/.

    line 24
  5. Distinctive:

    Prefer small verifiable changes over sweeping rewrites.

    line 25
  6. Distinctive:

    Only ask the user when the action is destructive, security-sensitive, or schema-breaking.

    line 29
  7. Common:

    Never share raw code, secrets, or full logs by default.

    line 30
  8. Distinctive:

    Before every commit: check "were there uncaptured incidents since last commit?"

    line 32
  9. Very specific:

    Skill layer: follow .agents/rules/35-skill-admission-and-quarantine.md for skill governance.

    line 33
  10. Very specific:

    Metadata-first: search skill INDEX before loading full skill content (see .agents/workflows/35-skill-capture-and-admission.md).

    line 34

≈ “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

This repository uses the NVE Universal Failure Genome + SkillGraph superstructure (v2.3.0).

Read first

Before changing architecture, memory, workflows, sharing, or Failure Genome behavior, read:

  • README.md
  • docs/UNIVERSAL_ARCHITECTURE.md
  • docs/INSTALL_INTO_ANTIGRAVITY.md
  • docs/SAFE_MIGRATION_PLAYBOOK.md
  • docs/RESEARCH_FOUNDATIONS.md
  • docs/USER_FLOW_AUDIT_AND_SHARE.md
  • docs/FAILURE_GENOME_HYPOTHESIS_V1.md
  • docs/FAILURE_GENOME_EXPERIMENT_PLAN_V1.md
  • docs/OLD_TO_NEW_MAP.md
  • docs/ANTIGRAVITY_PROMPT_SEQUENCE.md
  • docs/SKILLGRAPH_UPGRADE_ARCHITECTURE.md
  • docs/SKILLGRAPH_OPERATING_GUIDE.md
  • docs/SKILLNET_GAP_MAP.md

Operating contract

  1. Do not delete valuable existing assets without explicit approval.
  2. Use docs as the system of record. This file is only a table of contents.
  3. Keep canonical memory structured in .evolution/.
  4. Prefer small verifiable changes over sweeping rewrites.
  5. Read .evolution/MEMORY.md at session start — it contains verified lessons and anti-patterns.
  6. For each significant failure or prevention event, create an incident event immediately (see .agents/rules/25-incident-auto-capture.md for trigger events).
  7. For repeated or high-value failures, create or update a Failure Genome.
  8. Only ask the user when the action is destructive, security-sensitive, or schema-breaking.
  9. Never share raw code, secrets, or full logs by default.
  10. Legacy paths may remain as wrappers until migration is stable.
  11. Before every commit: check "were there uncaptured incidents since last commit?"
  12. Skill layer: follow .agents/rules/35-skill-admission-and-quarantine.md for skill governance.
  13. Metadata-first: search skill INDEX before loading full skill content (see .agents/workflows/35-skill-capture-and-admission.md).

Canonical homes

  • .agents/rules/ — always-on constraints
  • .agents/workflows/ — repeatable routines
  • .agents/skills/ — reusable specialized knowledge
  • .evolution/incidents/ — canonical incident events
  • .evolution/experience_units/ — distilled reusable knowledge
  • .evolution/failure_genomes/ — family-level learning units
  • .evolution/skills/ — canonical skill registry (candidate/admitted/quarantined/rejected)
  • .evolution/skill_packages/ — task-oriented skill bundles
  • .evolution/skill_relations/ — semantic and dependency graph
  • .evolution/audits/ — local audit outputs
  • .evolution/manifests/ — repo manifests
  • .evolution/exports/ — shareable research packs

Done criteria

Architecture work is done only when:

  • docs are updated,
  • the structure exists,
  • schemas match payloads,
  • legacy value remains discoverable,
  • and a future agent can understand the repo quickly.

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.