agentleFS
ryanbaumannryanbaumann/fieldwork/agent-scripts/AGENTS.md

fieldwork / agent-scripts

AGENTS.md2 starsChanged 28 days agoMITView on GitHub

This directory contains instructions for software agents, not executable shell scripts. - Every script lives in one kebab-case folder with README.md and SYSTEM_PROMPT.md. - Keep evergreen prompts vendor-neutral. Put volatile model IDs, pricing, and harness-specific settings in optional adapters or runtime configuration. - Add or update behavioral regression cases before tuning behavior-changing instructions. Record evaluation limits honestly. - Role overlays may narrow authority but never expand the shared prompt or user authorization. - Treat prompt changes like code: preserve user…

The file

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

4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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:

    Every script lives in one kebab-case folder with README.md and SYSTEM_PROMPT.md.

    line 6
  2. Distinctive:

    Keep evergreen prompts vendor-neutral.

    line 8
  3. Distinctive:

    Add or update behavioral regression cases before tuning behavior-changing instructions.

    line 10
  4. Distinctive:

    Treat prompt changes like code: preserve user work, review the diff, run the relevant contract cases, and use a reviewer that did not write …

    line 14

≈ “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

Agent script guidance

This directory contains instructions for software agents, not executable shell scripts.

  • Every script lives in one kebab-case folder with README.md and SYSTEM_PROMPT.md.
  • Keep evergreen prompts vendor-neutral. Put volatile model IDs, pricing, and harness-specific settings in optional adapters or runtime configuration.
  • Add or update behavioral regression cases before tuning behavior-changing instructions. Record evaluation limits honestly.
  • Role overlays may narrow authority but never expand the shared prompt or user authorization.
  • Treat prompt changes like code: preserve user work, review the diff, run the relevant contract cases, and use a reviewer that did not write the candidate.
  • Surface publishable entries through portfolio/content/scripts/; do not duplicate the canonical prompt in portfolio prose.

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.