agentleFS
Sign inStart free
andresthorandresthor/skills/skills/handoff/templates/AGENTS.md

skills / templates

AGENTS.md2 starsChanged 44 days agoMITView on GitHub

These are the rules for writing documentation for this project. Note: use useful slugs and use good judgement when dividing up work.

  • 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 31,542 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 repository13 other files it gives its agents.

The file

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

6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    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:

    Always read this file (AGENTS.md/CLAUDE.md) before writing anything in this directory.

    line 7
  2. Distinctive:

    If you notice inconsistencies or conflicting information:

    line 10
  3. Distinctive:

    Scripts and code: should generally never be included in these directories unless as examples.

    line 24
  4. Distinctive:

    Agents read these docs: Use bullets, one fact per line, no prose.

    line 30
  5. Distinctive:

    Add little per session: only what the next session needs.

    line 32
  6. Distinctive:

    One fact lives in one place: Check the other docs before writing.

    line 33

≈ “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

Project documentation

These are the rules for writing documentation for this project.

Invariants

  1. Always read this file (AGENTS.md/CLAUDE.md) before writing anything in this directory.
  2. This file can only be edited by the user OR on explicit command from the user.
  3. Each of the main documents has guidance/rules in its header that override any skill instructions that might conflict.
  4. If you notice inconsistencies or conflicting information:
    • Fix them if you know that they are the result of a decision made within your session
    • Surface them to the user otherwise
  5. Bloat is bad. Progressive disclosure is king.
    • See the rest of this document for what this means.
  6. A session that is starting up and/or doing a /pickup must read the primary documents prefixed with 00- in this directory.

Directory structure

  • Primary documents live in the root: 00-decisions.md, 00-handoff.md, 00-notes.md, 00-state.md
  • Additional documentation is created as either:
    1. A root document with a numbered prefix, starting at 01- and taking the next free number, f.ex. 01-architecture.md, 02-dev-process.md, 03-implementation-plan.md
    2. A subdirectory numbered the same way, f.ex. 04-figma-designs/<files>, 05-ux-changes/{research,results}/<files>
  • Root documents and subdirectories share one numbering sequence.
  • Scripts and code should generally never be included in these directories unless as examples. Results and logs may be collected under appropriate subdirectories.

Note: use useful slugs and use good judgement when dividing up work.

Writing docs and decisions

  • Agents read these docs. Use bullets, one fact per line, no prose.
  • Use file and path references to avoid bloat and encourage progressive disclosure. Agents should know upfront what exists but not be forced to ingest everything upfront.
  • Add little per session: only what the next session needs. Edit or delete before appending.
  • One fact lives in one place. Check the other docs before writing. On a conflict, ask; never contradict silently.
  • Decisions go only in the project's 00-decisions.md, tagged [user], [agent], [inferred] or [<team>]. Follow that file's header rules.
  • Never record a call as [user] unless the user stated it in chat.

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.

Check your setup, free