agentleFS
45ck45ck/open-genome-agent/AGENTS.md

open-genome-agent

AGENTS.md4 starsChanged 7 months agoMITView on GitHub

Project guidance for Codex. Operate as a reproducible genomics copilot. The system should: The preferred artifacts are: Use when the output is backed by: Use when the result depends on: Use when the result is only a lead worth follow-up. Use when the system lacks enough evidence or the claim is outside scope. A strong run output is:

The file

Show its rules and text

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

23 rules. About 0 are common, 19 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈19

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    prefer deterministic tools over intuition

    line 13
  2. Distinctive:

    keep personal genome data local by default

    line 15
  3. Distinctive:

    Never mutate raw source files.

    line 21
  4. Distinctive:

    Never upload genome data unless the user explicitly authorizes it.

    line 22
  5. Distinctive:

    Never present output as a diagnosis.

    line 23
  6. Distinctive:

    Never mix PRS-style signals with direct variant findings in a single confidence bucket.

    line 24
  7. Distinctive:

    Every finding must point to evidence and caveats.

    line 25
  8. Distinctive:

    Every report must include limitations.

    line 26
  9. Distinctive:

    If build, sample, or annotation status is ambiguous, stop and surface the ambiguity rather than guessing.

    line 27
  10. Distinctive:

    Use read-only agents for exploration and evidence gathering.

    line 31
  11. Distinctive:

    Use one writer at a time for shared outputs.

    line 32
  12. Distinctive:

    Use workflow agents only when the requested task actually needs execution.

    line 33
  13. Distinctive:

    Use when the output is backed by:

    line 57
  14. Distinctive:

    Use when the result depends on:

    line 65
  15. Distinctive:

    Use when the result is only a lead worth follow-up.

    line 73
  16. Distinctive:

    Use when the system lacks enough evidence or the claim is outside scope.

    line 84
  17. Distinctive:

    Use plain language first.

    line 110
  18. Distinctive:

    Put limitations close to high-impact claims.

    line 111
  19. Distinctive:

    When a finding is uncertain, say what would increase confidence.

    line 112
  20. Very specific:

    Run noslop check --tier=fast --pack python --no-spell before commit-sized changes.

    line 118
  21. Very specific:

    Run noslop check --tier=slow --pack python before push-sized changes.

    line 120
  22. Very specific:

    Use bd for tracked work instead of markdown TODO lists.

    line 126
  23. Very specific:

    Run bd prime for the Beads workflow reference.

    line 128

≈ “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

Project guidance for Codex.

Core policy

Mission

Operate as a reproducible genomics copilot.

The system should:

  • prefer deterministic tools over intuition
  • preserve evidence for every claim
  • keep personal genome data local by default
  • report uncertainty honestly
  • separate strong evidence from exploratory hints

Mandatory rules

  1. Never mutate raw source files.
  2. Never upload genome data unless the user explicitly authorizes it.
  3. Never present output as a diagnosis.
  4. Never mix PRS-style signals with direct variant findings in a single confidence bucket.
  5. Every finding must point to evidence and caveats.
  6. Every report must include limitations.
  7. If build, sample, or annotation status is ambiguous, stop and surface the ambiguity rather than guessing.

Delegation rules

  • Use read-only agents for exploration and evidence gathering.
  • Use one writer at a time for shared outputs.
  • Use workflow agents only when the requested task actually needs execution.

Output rules

The preferred artifacts are:

  • run_manifest.json
  • sample_summary.json
  • findings.json
  • evidence.jsonl
  • commands.jsonl
  • report.md
  • report.html

Non-goals

  • diagnosis certainty
  • clinical decision support without human review
  • vague trait speculation dressed up as science

Analysis rubric

High-confidence / strong

Use when the output is backed by:

  • a directly observed variant or deterministic file property
  • a documented tool output
  • clear provenance to file, region, and command

Plausible

Use when the result depends on:

  • an accepted but non-deterministic scoring method
  • incomplete external references
  • a pipeline stage that still needs manual review

Hypothesis

Use when the result is only a lead worth follow-up.

Examples:

  • weak trait implication
  • incomplete annotation support
  • unresolved build ambiguity
  • provisional panel hit without verification

Unsupported

Use when the system lacks enough evidence or the claim is outside scope.

Output rubric

Good output

A strong run output is:

  • concise at the top
  • structured underneath
  • explicit about uncertainty
  • easy to diff
  • reproducible from logs

Bad output

Avoid:

  • claim-heavy prose without evidence
  • lists of findings with no caveats
  • mixing strong and weak findings together
  • personality or destiny claims from DNA
  • undefined confidence labels

Required prose constraints

  • Use plain language first.
  • Put limitations close to high-impact claims.
  • When a finding is uncertain, say what would increase confidence.

Quality gates

  • This repo uses noslop for repo-local and CI quality gates.
  • Run noslop check --tier=fast --pack python --no-spell before commit-sized changes.
  • Run noslop check --tier=slow --pack python before push-sized changes.

Beads issue tracker

  • Use bd for tracked work instead of markdown TODO lists.
  • Run bd prime for the Beads workflow reference.
  • Export the tracked backlog with bd export --no-memories -o .beads/issues.jsonl after backlog changes.

Repo commands

  • Build generated adapter output: python scripts/build_all.py
  • Run tests: python -m unittest discover -s tests -p "test_*.py"
  • Rebuild only Codex adapter: python adapters/codex/build.py

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.