agentleFS
ianshankianshank/Agents/corpora/AGENTS.md

Agents / corpora

AGENTS.md1 starsChanged 58 days agoApache-2.0View on GitHub

Frozen, generated eval data. Protected, because swapping a corpus is how you fake a pass. Four versioned corpora the harness loads directly, each regenerable byte-for-byte from a seeded generator. README.md documents what each corpus contains and the properties it measures rather than asserts. This file is the handling contract: what you may change, what regenerates, and why a human has to look. - Never hand-edit a corpus file. Every item is hashed in its manifest.json, so a hand edit fails…

The file

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

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Never hand-edit a corpus file: Every item is hashed in its manifest.json, so a hand edit fails make corpus-check rather than quietly …

    line 57

≈ “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

AGENTS.md — corpora

Frozen, generated eval data. Protected, because swapping a corpus is how you fake a pass.

Four versioned corpora the harness loads directly, each regenerable byte-for-byte from a seeded generator. README.md documents what each corpus contains and the properties it measures rather than asserts. This file is the handling contract: what you may change, what regenerates, and why a human has to look.

Map

PathRole
<name>/<version>/manifest.jsonSchema version, generator seed, split counts, a hash per item
<name>/<version>/items.jsonThe corpus itself
<name>/<version>/eval/The harness-loadable records a config points its dataset at
testgen/v1/Sixty synthetic focal methods, seeded mutants, gold obligations
rca/v1/Root-cause-analysis corpus (ADR 0046)
requirements/v1/Twenty-five epics with gold acceptance criteria and an evidence store
answer_quality/v1/Fourteen question and answer envelopes replayed by the replay target

Diagram

flowchart LR
  accTitle: corpus lifecycle from generator to gate
  accDescr: A seeded generator writes a corpus and its manifest, the corpus check regenerates and compares bytes, an eval config loads it, and any change needs the approval label.

  GEN["scripts/gen_*_corpus.py<br/>seeded generator"]

  subgraph CO["corpora/ (you are here)"]
    MAN["manifest.json<br/>seed + per-item hash"]
    ITEMS["items.json"]
    EV["eval/ records"]
  end

  CHECK["make corpus-check<br/>byte-identical or fail"]
  CFG["config/*_eval.yaml"]
  RUN["eval-harness run"]
  LABEL["eval-change-approved"]

  GEN --> MAN
  GEN --> ITEMS
  GEN --> EV
  MAN --> CHECK
  ITEMS --> CHECK
  EV --> CFG
  CFG --> RUN
  ITEMS --> LABEL

  classDef here fill:#e8f0fe,stroke:#1a73e8,stroke-width:2px
  class CO here

Rules that bite here

  • Never hand-edit a corpus file. Every item is hashed in its manifest.json, so a hand edit fails make corpus-check rather than quietly changing a score. Change the generator in ../scripts/, regenerate with make corpus-write, and commit both.
  • This directory is protected, and the reason is specific. Swapping a corpus for an easier one moves every number in a matrix without touching a scorer, a threshold or a gate rule. It is the cheapest possible way to make a failing eval pass, so it requires the eval-change-approved label and a code owner.
  • A version directory is frozen. New material goes in <name>/v2/, never on top of v1; the configs and the reported numbers name a version and must stay comparable.
  • The seed is part of the data. Regeneration is only meaningful because the seed and the split keying live in the manifest. Do not change a seed to make a run look better, and do not reshuffle a holdout: the split is keyed by hash, not shuffled.
  • Nothing host-specific or scraped belongs here. Real internal source would collide with the charter invariant that nothing host-specific is committed; generation avoids the question and buys reproducible difficulty strata instead.

Verify

make corpus-check

Subagents

Task in this directoryAgentWhy
Find which configs, scorers and docs name a corpus before adding a versionexplorerRead-only; a corpus path is referenced from configs, tests and prose at once
Regenerate and confirm the bytes still matchtest-runnerHas Bash; make corpus-check runs four generators and names the one that drifted
Review a generator change before requesting the labelnarrow-criticA tie-break or seed change silently restates every score and is not lintable

See also

DocRead it when
README.mdYou need what a corpus contains and which properties it measures rather than asserts
../config/AGENTS.mdYou are pointing an eval config at a corpus, or changing which one it loads
../docs/decisions/0043-testgen-evaluation-seam.mdYou are working on testgen/v1/ and need the seam it was built for
../docs/decisions/0047-requirements-eval-matrix.mdYou are working on requirements/v1/ or its evidence store
../scripts/AGENTS.mdYou are editing a generator and need its gate and coverage obligations

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.