agentleFS
Sign inStart free
hiddayhidday/AgentForge/CLAUDE.md

AgentForge

CLAUDE.md0 starsChanged 5 months agoMITView on GitHub

Guidance for AI agents working in this repository. Monorepo with two packages: Every implementation change must include tests as part of the same cycle. Writing the tests is not a follow-up task — a change is not complete until it ships with tests covering the new or modified behavior. The configured coverage reports (v8 provider, settings in each package's vitest.config.ts) are the source of truth for coverage. The project's target is 100% coverage in both packages. In foundry/, also run…

The file

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

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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:

    All added or modified tests must pass before the work is considered done.

    line 16
  2. Distinctive:

    Never weaken or delete existing tests, lower coverage thresholds, or add coverage exclusions to make a change pass.

    line 18

≈ “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

CLAUDE.md

Guidance for AI agents working in this repository.

Project layout

Monorepo with two packages:

  • foundry/ — Node backend orchestrator (TypeScript, Fastify, Prisma). Package manager: pnpm. Tests in foundry/tests/.
  • ui/ — React + Vite frontend. Package manager: npm. Tests colocated in ui/src/.

Testing policy (required)

Every implementation change must include tests as part of the same cycle. Writing the tests is not a follow-up task — a change is not complete until it ships with tests covering the new or modified behavior.

  • All added or modified tests must pass before the work is considered done. Run the relevant suite and confirm it is green; never hand off with failing tests.
  • Tests must assert meaningful outcomes, failure paths, and boundary conditions — not merely execute lines.
  • Never weaken or delete existing tests, lower coverage thresholds, or add coverage exclusions to make a change pass. Coverage exclusions are only for genuinely untestable entrypoint/generated code, each with a justifying comment in the vitest config.

Running tests

# foundry (requires Node >= 22.12; DATABASE_URL must be set — a dummy value
# works, tests use mocks and never contact a real database)
cd foundry && DATABASE_URL="postgresql://test:test@localhost:5432/test" pnpm test

# foundry with coverage
cd foundry && DATABASE_URL="postgresql://test:test@localhost:5432/test" pnpm run test:coverage

# ui
cd ui && npm test

# ui with coverage
cd ui && npm run test:coverage

The configured coverage reports (v8 provider, settings in each package's vitest.config.ts) are the source of truth for coverage. The project's target is 100% coverage in both packages.

Before committing

In foundry/, also run pnpm typecheck and pnpm lint — CI enforces both. In ui/, also run npm run lint and npm run build.

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