agentleFS
dartmouthdartmouth/dartmouth-skills/AGENTS.md

dartmouth-skills

AGENTS.md0 starsChanged 34 days agoBSD-3-ClauseView on GitHub

Rules for agents adding, editing, or reviewing skills in the dartmouth-skills repo.

  • 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 32,671 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

6 rules. About 1 is common, 1 is distinctive, and 4 are very specific to this project.

  • ≈1

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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. Very specific:

    Only a human review adds verified: { by: human:<netid>, at: <timestamp> } and sets status: stable.

    line 30
  2. Distinctive:

    All timestamps are ISO 8601 with an explicit UTC offset.

    line 31
  3. Very specific:

    Every sources entry has an id and a resource.

    line 33
  4. Very specific:

    When a file is past stale_after, re-check its sources before trusting it.

    line 38
  5. Common:

    Public information only: No internal infrastructure details, secrets, keys, or non-public vendor terms.

    line 40
  6. Very specific:

    Record every change: Add an entry to skills/log.md (newest first, ## YYYY-MM-DD).

    line 41

≈ “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

Rules (in priority order)

  1. One skill per directory: skills/<name>/SKILL.md. name must equal <name>: lowercase letters, digits and hyphens, at most 64 characters.
  2. description tells agents when to use the skill. Say what it does and when to use it, in one line under 1024 characters. It also serves as the OKF description.
  3. Every .md needs OKF frontmatter with a type. The only exceptions are index.md, log.md and the root README.md (kept clean for GitHub). Use:
    • Agent Skill for SKILL.md
    • Reference for references/*.md
    • Agent Instructions for repo docs such as this file
  4. Provenance and trust fields:
    • generated: { by: <actor>, at: <timestamp> }. by is required. Actors are <agent>/<model> for agents, human:<netid> for people, process:<id> for automation.
    • New or agent-edited content is status: draft and has no verified key (no key means unverified).
    • Only a human review adds verified: { by: human:<netid>, at: <timestamp> } and sets status: stable. verified is a mapping or a list of such mappings, never a plain name, and the human: prefix is what marks content as human-reviewed.
    • All timestamps are ISO 8601 with an explicit UTC offset.
  5. Sources:
    • Every sources entry has an id and a resource.
    • Cite key claims with footnotes keyed by that id ([^rc-faq]).
    • Set last_modified to the source page's own "last modified" date. Omit it if the page shows none.
  6. Freshness:
    • stale_after is an absolute timestamp. Set it no more than 3 months out for content that names models or prices.
    • When a file is past stale_after, re-check its sources before trusting it.
  7. Keep the SKILL.md body lean (target under 300 lines, excluding frontmatter). Move long configs and walkthroughs into references/ and link to them by relative path.
  8. Public information only. No internal infrastructure details, secrets, keys, or non-public vendor terms. Skills dealing with internal APIs or data belong in the Dartmouth-only sibling repo https://github.com/dartmouth/dartmouth-internal-skills, not here.
  9. Record every change. Add an entry to skills/log.md (newest first, ## YYYY-MM-DD). Update skills/index.md when adding a skill.

Validate

uv run --with pyyaml python3 scripts/validate.py

The script needs PyYAML, so uv run --with pyyaml avoids installing it globally.

# alternative if PyYAML is already installed
python3 scripts/validate.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.