How real projects brief Claude Code: the commands, conventions and warnings they put in CLAUDE.md.
JeffallanCLAUDE.mdJeffallan/claude-skills/CLAUDE.md
description:** ```yaml description: Use for debugging. First investigate root cause, then analyze patterns, test hypotheses, and implement fixes with tests. ``` **GOOD - Capability + trigger:** ```yaml description: Diagnoses bugs through root cause
Hugging FaceCLAUDE.mdhuggingface/chat-ui/CLAUDE.md
formatting (Prettier) and linting (ESLint) npm run format # Auto-format with Prettier npm run test # Run all tests (Vitest) ``` ### Running a Single Test ```bash npx vitest run path/to/file.spec.ts # Run specific
zubair-trabzadaCLAUDE.mdzubair-trabzada/geo-seo-claude/CLAUDE.md
documentation (keep in sync with code) | | `examples/` | Sample audit outputs, proposals, demo CRM data | | `tests/` | Test suite (see [Testing](#testing)) | | `white-label/` | Agency rebranding config (`brand_config.py`, `brand.example.json`) | | `install.sh` / `install-win.sh` / `uninstall.sh
JetBrainsCLAUDE.mdJetBrains/ideavim/CLAUDE.md
with IdeaVim. ## Quick Reference Essential commands: - `./gradlew runIde` - Start dev IntelliJ with IdeaVim - `./gradlew test -x :tests:property-tests:test -x :tests:long-running-tests:test` - Run standard tests Avoid
unicity-sphereCLAUDE.mdunicity-sphere/sphere/CLAUDE.md
server npm run build # TypeScript compile + Vite build npm run lint # ESLint npm run test # Vitest watch mode npm run test:run # Vitest single run npm run preview # Preview production
frankbriaCLAUDE.mdfrankbria/ralph-claude-code/CLAUDE.md
priority + dependency order), runs the loop via `RALPH_LOOP_CMD` (default `ralph_loop.sh`; overridable for tests), commits `Fix #N: ` per issue, skips failures (or halts), and writes `.ralph/logs/queue_processing.log`. Single branch
olisticCLAUDE.mdolistic/warriorjs/CLAUDE.md
bash pnpm install # Install dependencies pnpm build # Build all packages (Turborepo handles ordering) pnpm test # Run all tests pnpm lint # Check linting/formatting (Biome) pnpm lint:fix # Auto-fix linting/formatting
AnthropicCLAUDE.mdanthropics/claude-for-legal/ai-governance-legal/CLAUDE.md
WARN issue (Cal. Lab. Code §1400) — California requires 60 days notice before large layoffs." Test: could the reader take the output to their boss and explain it without a lawyer
AnthropicCLAUDE.mdanthropics/claude-for-legal/commercial-legal/CLAUDE.md
item issue list, a memo, a redline, a client letter. Use judgment — the test is "would a reader struggle to see the shape of this in text." **Dashboard outputs escape
AnthropicCLAUDE.mdanthropics/claude-for-legal/corporate-legal/CLAUDE.md
WARN issue (Cal. Lab. Code §1400) — California requires 60 days notice before large layoffs." Test: could the reader take the output to their boss and explain it without a lawyer
AnthropicCLAUDE.mdanthropics/claude-for-legal/employment-legal/CLAUDE.md
WARN issue (Cal. Lab. Code §1400) — California requires 60 days notice before large layoffs." Test: could the reader take the output to their boss and explain it without a lawyer
AnthropicCLAUDE.mdanthropics/claude-for-legal/ip-legal/CLAUDE.md
item issue list, a memo, a redline, a client letter. Use judgment — the test is "would a reader struggle to see the shape of this in text." **Dashboard outputs escape
AnthropicCLAUDE.mdanthropics/claude-for-legal/law-student/CLAUDE.md
item issue list, a memo, a redline, a client letter. Use judgment — the test is "would a reader struggle to see the shape of this in text." **Dashboard outputs escape
AnthropicCLAUDE.mdanthropics/claude-for-legal/legal-builder-hub/CLAUDE.md
WARN issue (Cal. Lab. Code §1400) — California requires 60 days notice before large layoffs." Test: could the reader take the output to their supervising attorney and explain it without
AnthropicCLAUDE.mdanthropics/claude-for-legal/legal-clinic/CLAUDE.md
item issue list, a memo, a redline, a client letter. Use judgment — the test is "would a reader struggle to see the shape of this in text." **Dashboard outputs escape
AnthropicCLAUDE.mdanthropics/claude-for-legal/litigation-legal/CLAUDE.md
item issue list, a memo, a redline, a client letter. Use judgment — the test is "would a reader struggle to see the shape of this in text." **Dashboard outputs escape
AnthropicCLAUDE.mdanthropics/claude-for-legal/privacy-legal/CLAUDE.md
item issue list, a memo, a redline, a client letter. Use judgment — the test is "would a reader struggle to see the shape of this in text." **Dashboard outputs escape
AnthropicCLAUDE.mdanthropics/claude-for-legal/product-legal/CLAUDE.md
item issue list, a memo, a redline, a client letter. Use judgment — the test is "would a reader struggle to see the shape of this in text." **Dashboard outputs escape
AnthropicCLAUDE.mdanthropics/claude-for-legal/regulatory-legal/CLAUDE.md
item issue list, a memo, a redline, a client letter. Use judgment — the test is "would a reader struggle to see the shape of this in text." **Dashboard outputs escape
JetBrainsCLAUDE.mdJetBrains/Exposed/CLAUDE.md
migrations - **exposed-spring-boot-starter**: Spring Boot integration - **spring-transaction**: Spring Framework transaction manager ### Test Modules - **exposed-tests**: Main JDBC-based test suite - **exposed-r2dbc-tests**: R2DBC-specific test suite
A file Claude Code reads at the start of every session. It holds the commands, conventions and warnings the agent needs for this project.
At the repository root. Claude Code also reads CLAUDE.md files in subdirectories when it works there.
Build and test commands, the project's layout, conventions that aren't obvious from the code, and mistakes to avoid. Short files tend to work better than long ones.
Claude Code reads CLAUDE.md; most other agents read AGENTS.md. Many projects keep one and point the other at it.
