agentleFS
Sign inStart free
tmussertmusser/context-to-action-skills/AGENTS.md

context-to-action-skills

AGENTS.md2 starsChanged 58 days agoMITView on GitHub

This repo turns messy workplace context into conversation state and then into context-aware responses. Default route: reduce-to-facts -> clear-ask / decision-brief / meeting-to-actions -> follow-up-draft / status-update / brief-me

  • 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 repository7 other files it gives its agents.

The file

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

8 rules. About 0 are common, 6 are distinctive, and 2 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.

  • 2

    Very specific

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

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

    Default route: reduce-to-facts -> clear-ask / decision-brief / meeting-to-actions -> follow-up-draft / status-update / brief-me

    line 7
  2. Very specific:

    Start with reduce-to-facts for dense or ambiguous source.

    line 12
  3. Distinctive:

    Do not send, publish, update tickets, create events, or mutate systems unless explicitly asked.

    line 14
  4. Distinctive:

    Keep the pasted-context validation boundary intact.

    line 15
  5. Distinctive:

    Prefer conversation state over long summaries.

    line 19
  6. Distinctive:

    Use the smallest useful output.

    line 21
  7. Distinctive:

    Prefer action-oriented artifacts over long summaries.

    line 22
  8. Distinctive:

    Keep the seven visible skills stable unless scope is explicitly changing.

    line 23

≈ “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

Repo model

This repo turns messy workplace context into conversation state and then into context-aware responses.

Default route: reduce-to-facts -> clear-ask / decision-brief / meeting-to-actions -> follow-up-draft / status-update / brief-me

Safety rules

  • Read before write.
  • Start with reduce-to-facts for dense or ambiguous source.
  • Preserve uncertainty instead of smoothing it away.
  • Do not send, publish, update tickets, create events, or mutate systems unless explicitly asked.
  • Keep the pasted-context validation boundary intact.

Output rules

  • Prefer conversation state over long summaries.
  • Label facts, assumptions, source gaps, stakeholder sensitivities, and uncertainty.
  • Use the smallest useful output.
  • Prefer action-oriented artifacts over long summaries.
  • Keep the seven visible skills stable unless scope is explicitly changing.

Validation commands

python scripts/validate_repo.py
python scripts/validate_examples.py
python scripts/validate_schemas.py
git diff --check

Docs-only edits: do not change

  • skill names or count
  • safety boundaries
  • validation boundaries
  • example semantics just for style
  • connector or mutation claims

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