How real projects brief Claude Code: the commands, conventions and warnings they put in CLAUDE.md.
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.
mantinedevCLAUDE.mdmantinedev/mantine/CLAUDE.md
seconds: ```bash npx oxlint -c oxlint.config.mjs path/to/changed/files npm run format:write:files path/to/changed/files # Run tests for specific path related to your changes npm run jest @mantine/charts npm run jest path/to/changed/file.test.ts
Steady10 mentions in 2 weeks
No other project uses it yet
heroui-incCLAUDE.mdheroui-inc/heroui/CLAUDE.md
React**: v19+ - **Tailwind CSS**: v4.3.3 - **TypeScript**: v5.9.3 - **Turborepo**: Build orchestration - **Storybook**: Component development - **Vitest**: Testing framework Use the workspace manifests and lockfile as the source of truth for exact dependency
Steady16 mentions in 2 weeks
No other project uses it yet
tobiCLAUDE.mdtobi/qmd/CLAUDE.md
aliases ``` ## Development ```sh bun src/cli/qmd.ts # Run from source bun link # Install globally as 'qmd' ``` ## Tests All tests live in `test/`. Run everything: ```sh npx vitest run --reporter=verbose test
Steady2 mentions in 2 weeks
No other project uses it yet
tobiCLAUDE.mdtobi/qmd/finetune/CLAUDE.md
reward.py` is the single source of truth for scoring: ```bash uv run reward.py # Self-test ``` See `SCORING.md` for the full rubric. ## Experiments Experimental training configurations live in `experiments/`: ``` experiments/ ├── lfm2
Steady2 mentions in 2 weeks
2 projects use a version of this
gavrielcReads credentialsCLAUDE.mdgavrielc/nanoclaw/CLAUDE.md
replays carry the approval row as a grant and re-run the checks. Conformance test: `src/guard/conformance.test.ts` | | `src/modules/permissions/access.ts` | `canAccessAgentGroup` — owner / global admin / scoped admin / member resolution against `user_roles` + `agent_group
trailofbitsReads credentialsCLAUDE.mdtrailofbits/algo/CLAUDE.md
Vultr, Hetzner, local deployment ### Philosophy - Stability over features - Security over convenience - Clarity over cleverness - Test everything - Stay in scope - solve exactly what the issue asks, nothing more - Test assumptions
No other project uses it yet
jitsiReads credentialsCLAUDE.mdjitsi/jitsi-meet/CLAUDE.md
Build production bundles - `make clean` - Clean build directory - `make all` - Full build (compile + deploy) ### Testing - `npm run test:unit` - Run unit tests using Vitest - `npm test` - Run full test suite
Genesis-Embodied-AICLAUDE.mdGenesis-Embodied-AI/Genesis/CLAUDE.md
aligning with public getter conventions. This applies to engine code only, unit tests being exempt. - **Hoist conversions before loops.** Call `qd_to_numpy` / `qd_to_torch` once, then index
1 project uses a version of this
simstudioaiCLAUDE.mdsimstudioai/sim/CLAUDE.md
Global Standards, Architecture (incl. the Application Operation Boundary), Code Conventions, API Contracts and Routes, Testing, Integrations, and How your work is checked (the local gate to run before calling
modularCLAUDE.mdmodular/modular/CLAUDE.md
Build everything ./bazelw build //... # Build specific targets ./bazelw build //max/kernels/... ./bazelw build //Mojo/stdlib/... # Run tests ./bazelw test //... ./bazelw test //max/kernels/test/linalg:test_matmul # Find targets ./bazelw query '//max/...' ./bazelw query 'tests
No other project uses it yet
alirezarezvaniCLAUDE.mdalirezarezvani/claude-skills/agents/CLAUDE.md
Agile product ownership and backlog management | | [cs-ux-researcher](product/cs-ux-researcher.md) | Product | UX research, usability testing, design insights | | [cs-product-analyst](product/cs-product-analyst.md) | Product | Product analytics, KPI design, experiment design | | [cs-engineering
Steady28 mentions in 2 weeks
No other project uses it yet
alirezarezvaniReads credentialsCLAUDE.mdalirezarezvani/claude-skills/CLAUDE.md
coverage expansion** — public audit record `audit/productivity-2026-07/` (all 7 legacy skills scored, 24/24 scripts smoke-tested, coverage map vs the personal-productivity canon) + 3 gap-filling plugins, each with
alirezarezvaniCLAUDE.mdalirezarezvani/claude-skills/c-level-advisor/CLAUDE.md
board-prep` | Board meeting preparation | | `/executive-mentor:hard-call` | Framework for hard decisions | | `/executive-mentor:stress-test` | Stress-test any assumption | | `/executive-mentor:postmortem` | Honest retrospective | ## Key Design Decisions - **Two-layer memory
Steady28 mentions in 2 weeks
No other project uses it yet
alirezarezvaniCLAUDE.mdalirezarezvani/claude-skills/engineering-team/CLAUDE.md
zones - **gcp-cloud-architect** — GCP infrastructure design, Terraform modules, cloud-native patterns - **security-pen-testing** — Penetration testing methodology, vulnerability assessment, exploit analysis - **snowflake-development** — Snowflake data warehouse development, SQL optimization
alirezarezvaniCLAUDE.mdalirezarezvani/claude-skills/finance/CLAUDE.md
preferred equity, hard money / bridge funds, and private credit, pasted from any source. Stress-tests returns against public benchmarks plus an illiquidity premium, converts the fee stack to gross
Steady28 mentions in 2 weeks
No other project uses it yet
alirezarezvaniCLAUDE.mdalirezarezvani/claude-skills/product-team/CLAUDE.md
Sample Size Calculator (`experiment-designer/scripts/sample_size_calculator.py`) **Purpose:** Statistical sample size planning for A/B tests and experiments **Features:** - Minimum detectable effect (MDE) calculation - Absolute and relative effect size modes - Power analysis
Steady28 mentions in 2 weeks
No other project uses it yet
alirezarezvaniCLAUDE.mdalirezarezvani/claude-skills/standards/CLAUDE.md
standards/` **Available Standards:** 1. **communication/** - Communication principles and response protocols 2. **quality/** - Code quality, testing, and validation standards 3. **git/** - Git workflow, conventional commits, branching strategy 4. **documentation/** - Markdown quality
alirezarezvaniCLAUDE.mdalirezarezvani/claude-skills/templates/CLAUDE.md
agents/domain/cs-new-agent.md # 2. Customize for your agent vim agents/domain/cs-new-agent.md # 3. Follow template structure exactly # 4. Test relative paths and integrations # 5. Commit with conventional commit git commit -m "feat(agents): implement
chroma-coreCLAUDE.mdchroma-core/chroma/CLAUDE.md
rust-client): Fix connection timeout on retry [TST](gc): Add MCMR hard delete integration test [DOC](api): Update embeddings endpoint docs [CHORE](deps): Bump reqwest to 0.13 ``` Common types
No other project uses it yet
AgriciDanielReads credentialsCLAUDE.mdAgriciDaniel/claude-seo/CLAUDE.md
/scripts/claude-seo" run`; plugin state uses `CLAUDE_PLUGIN_DATA` - Manual Python dependencies install into `~/.claude/skills/seo/.venv/` - Test with `python3 -m pytest tests/` after changes (if applicable) ## Security Rules - **Never commit credentials
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.
