agentleFS
EricSanchezokEricSanchezok/repo-seed/docs/AGENTS.md

repo-seed

AGENTS.md10 starsChanged 32 days agoMITView on GitHub

This file defines document structure, Markdown tiers, writing rules, and the hygiene checklist for this repository. Use the repo-review skill for semantic review and the repo-decisions skill for decision records. Every human-facing document belongs to a tier. A document's subject and tree position fix its scope: describe its own subject at appropriate detail, direct children only by purpose and responsibility, and link to the owning descendant for lower-level detail. Testing mechanisms belong at the lowest owning level. Each fact has…

  • Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.

    Of the AGENTS.md files we read, the 33,315 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.

  • In this repository6 other files it gives its agents.

The file

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

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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:

    Document current state, not change history.

    line 33
  2. Distinctive:

    No fill-in tokens may remain in any doc that ships.

    line 37

≈ “Common” is an estimate: at least 1 in 5 of the 42,283 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 — Documentation standard

This file defines document structure, Markdown tiers, writing rules, and the hygiene checklist for this repository. Use the repo-review skill for semantic review and the repo-decisions skill for decision records.

Document structure

Every human-facing document belongs to a tier. A document's subject and tree position fix its scope: describe its own subject at appropriate detail, direct children only by purpose and responsibility, and link to the owning descendant for lower-level detail. Testing mechanisms belong at the lowest owning level.

The tier taxonomy: one home per fact

Each fact has one home; everywhere else, link there.

TierJobDoes NOT belong there
Root AGENTS.mdManagement identity, skill router, and standing orders needed in every sessionStories, worked examples, restated procedures
docs/AGENTS.mdThe documentation standardRepo-wide rules the root file carries
docs/architecture.mdOrdered map: composition, modules, seamsPer-module detail, decision rationale
docs/development.mdContributor setup, daily workflow, commandsRuntime rationale
docs/testing.mdTest mission, risk-to-layer selection, topology, evidence, maintenance budgetPer-case walkthroughs or drifting command inventories
docs/specs/Risk-triggered Intent, Contract, Plan, Verification, and Evidence for a changeDurable alternative rationale or routine-change ceremony
docs/decisions/Durable choices with genuine alternatives (MADR + Class extension)Change logs, implementation plans, product contracts
docs/postmortems/Incident write-ups linked to permanent guardrails (the only war-story tier)—
In-repo skillsReusable workflows and decision proceduresProduct contracts

Placement: change contract → specs; durable alternative rationale → decisions; procedures → skills or development; incident stories → postmortems; standing orders → root AGENTS.md with a link.

Tutorial or reference

Classify every in-scope document as a tutorial or a reference. A tutorial follows an ordered path to an outcome. A reference defines a lookup scope and current behavior without a teaching sequence. Separate substantial mixed forms; label a small secondary form clearly.

Writing rules

  • Document current state, not change history. Avoid "previously/now/no longer", PRs, commits, and stack positions in durable prose; name the live mechanism.
  • One physical line per paragraph.
  • State complete contracts, not reasoning transcripts.
  • Cross-reference with machine-checkable relative Markdown links. Links must resolve.
  • No fill-in tokens may remain in any doc that ships.
  • Comments and JSDoc state contracts or provenance; do not restate code.

Hygiene checklist

Hunt these in any doc:

  • The same rule stated in more than one home. Keep one home and link the rest.
  • Narrated history or war stories.
  • Implementation-status annotations ("implemented!", "future: …"). Status rots.
  • Hand-restated catalogs or inventories when source or a generator is authoritative.
  • Reasoning transcripts: step-by-step narration, test walkthroughs, rejected alternatives.
  • Rationale repeated beside sibling methods instead of once at the owning place.
  • Paragraph walls. Split or demote.
  • Emphasis inflation. Reserve emphasis for the clause that changes behavior.
  • Spec-speak in shipped decisions ("should", migration plans, acceptance checklists).

Budget

Root AGENTS.md has a soft budget of 100 lines. When it grows past that, relocate content to its tier home and leave a one-line link.

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.