lepresklepresk/groundwork/CLAUDE.md

groundwork

CLAUDE.md0 starsChanged 50 days agoMITView on GitHub

Reads credentials

In this repository15 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .github/copilot-instructions.mdCopilot instructions
- .cursor/rules/000-project.mdcCursor rule
- .cursor/rules/010-typescript.mdcCursor rule
- .cursor/rules/020-api.mdcCursor rule
- .cursor/rules/030-web.mdcCursor rule
- .cursor/rules/040-database.mdcCursor rule
- .cursor/rules/050-worker.mdcCursor rule
- .cursor/rules/060-testing.mdcCursor rule
- llms.txtllms.txt
- add-endpointSkill
- db-migrationSkill
- new-moduleSkill
- verifySkill
- write-testsSkill

The file

We found no rules to list in this file: it reads as prose or reference rather than instructions.

Create a free account to mount

Files

CLAUDE.md

<!--
SCOPE: whole repository
DOC_KIND: agent-rules
DOC_ROLE: derived (Claude Code entry point)
READ_WHEN: always, loaded automatically by Claude Code
-->

Claude Code

@AGENTS.md

Claude Code specifics

Skills (.claude/skills/): new-module, add-endpoint, db-migration, write-tests, verify. Use them instead of improvising the workflow they describe.
Subagents (.claude/agents/): code-reviewer for a rules-based review of a diff, security-reviewer for auth, input, and data exposure concerns. Run code-reviewer before declaring a non-trivial change done.
Hooks (.claude/settings.json): every file you write is formatted with Prettier and checked for em dashes and emoji. A hook failure means the file violates a rule: fix it, do not work around it.
Permissions: reading .env files is denied on purpose. Configuration shape lives in .env.example and */config/env.ts.
MCP (.mcp.json): context7 serves current library documentation. Query it before using an API you are not certain about (NestJS 11, Next.js 16, Zod 4, Drizzle, BullMQ).
Each workspace has its own CLAUDE.md that imports its AGENTS.md; it loads when you work in that folder.

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