agentleFS
Sign inStart free
juanquijandriajuanquijandria/prisma-harness/CLAUDE.md

prisma-harness

CLAUDE.md2 starsChanged 35 days agoMITView on GitHub

This repository is a Claude Code plugin and the written method it enforces. Read METHOD.md before changing anything under hooks/ or skills/, and STYLE.md before writing any page.

The file

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

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    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 deciding hook has a --selftest or a control script under tests/.

    line 5

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.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
CLAUDE.md

Prisma Harness

This repository is a Claude Code plugin and the written method it enforces. Read METHOD.md before changing anything under hooks/ or skills/, and STYLE.md before writing any page.

  • Every deciding hook has a --selftest or a control script under tests/. Run tests/run-selftests.sh before and after a change; a gate whose tests never fail is decoration.
  • A gate is proven by a positive control, not by silence. Reintroduce the defect it exists for and watch it block, then remove it and watch it pass.
  • Code, error and log messages, file names and commits in English. That rule is about the repository, and the conversation with the person stays in their language. No comments in code, except the shebang and the one-line header pointing to the README section.
  • The canonical block in docs/es/METHOD.md is the reference every registered copy is compared against. Do not edit it casually.

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