agentleFS
Sign inStart free
paruffparuff/uFawkesAI/opencode/AGENTS.md

uFawkesAI / opencode

AGENTS.md2 starsChanged 24 days agoMITView on GitHub

Baked into the image's ~/.config/opencode/AGENTS.md by opencode/bake.sh from paruff/uFawkesAI. Loaded into every OpenCode session in every repo, so it holds only what is true everywhere; each repo's own AGENTS.md wins on specifics. - Superpowers skills are the development loop (brainstorming → writing-plans → executing-plans / test-driven-development → verification-before-completion → requesting-code-review; systematic-debugging for failures). - .agents/ is hidden from glob search — open files there by explicit path.

  • 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 31,439 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 repository10 other files it gives its agents.

The file

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

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Very specific:

    Read the repo's AGENTS.md first and follow its pointers to the task's intent, spec and plan.

    line 9
  2. Distinctive:

    Verify against main before saying "done": content check + CI green.

    line 10
  3. Very specific:

    Never commit secrets; never bypass hooks (--no-verify).

    line 13
  4. Very specific:

    Use ruff for Python formatting/linting.

    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

Global agent stance (all repos) — DORA AI Capability 1: Clear and communicated AI stance

Baked into the image's ~/.config/opencode/AGENTS.md by opencode/bake.sh from paruff/uFawkesAI. Loaded into every OpenCode session in every repo, so it holds only what is true everywhere; each repo's own AGENTS.md wins on specifics.

Hard rules

  • Read the repo's AGENTS.md first and follow its pointers to the task's intent, spec and plan. If it names none, find the nearest intent.md (any case; uFawkes repos use docs/ai-sdlc/<feature>/intent.md) and ask if more than one could apply.
  • Verify against main before saying "done": content check + CI green.
  • One PR per change, small batches (< 400 lines).
  • Agents never merge — a human reviews and merges.
  • Never commit secrets; never bypass hooks (--no-verify).
  • Use ruff for Python formatting/linting.

Methodology

  • Superpowers skills are the development loop (brainstorming → writing-plans → executing-plans / test-driven-development → verification-before-completion → requesting-code-review; systematic-debugging for failures).
  • .agents/ is hidden from glob search — open files there by explicit path.

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