How real projects brief Claude Code: the commands, conventions and warnings they put in CLAUDE.md.
piominCLAUDE.mdpiomin/claude-ai-spring-boot/CLAUDE.md
your changes when relevant - Ask yourself: "Would a staff engineer approve this?" - Run tests, check logs, demonstrate correctness ### 4. Demand Elegance (Balanced) - For non-trivial changes: pause
d-kimusonCLAUDE.mdd-kimuson/claude-code-viewer/CLAUDE.md
messages should be in English **NEVER**: - Use `as` type casting in ANY context including test code (explain the problem to the user instead) - Use raw `fetch` or bypass TanStack Query
nduckminkCLAUDE.mdnduckmink/arkon/CLAUDE.md
Files needing format only (70%) rtk next build # Next.js build with route metrics (87%) ``` ### Test (60-99% savings) ```bash rtk cargo test # Cargo test failures only (90%) rtk go test
kbwoCLAUDE.mdkbwo/ccmanager/CLAUDE.md
domain logic in `src/services/`, shared hooks in `src/hooks/`, and utilities/constants in their respective folders. - Tests sit beside the code they cover (e.g., `Menu.tsx` and `Menu.test.tsx`), enabling focused updates. - Built artifacts
conorluddyCLAUDE.mdconorluddy/ios-simulator-skill/CLAUDE.md
Skill is a production-ready Agent Skill providing 29 scripts for iOS app building, testing, and automation. It wraps Apple's `xcrun simctl` and Facebook's `idb` tools with semantic
SupabaseCLAUDE.mdsupabase/postgres-meta/CLAUDE.md
Build process: TypeScript compilation (tsc) + copying `src/lib/sql/*.sql` files to `dist/lib/sql/` via cpy-cli. ### Testing ```bash npm test # Full test: db:clean -> db:run -> test:run -> db:clean
Taewan-PCLAUDE.mdTaewan-P/gpt_mobile/CLAUDE.md
assembleDebug ``` ### Release Build ```bash ./gradlew assembleRelease ./gradlew bundleRelease # For Google Play Store AAB format ``` ### Testing ```bash ./gradlew test # Unit tests ./gradlew connectedAndroidTest # Instrumented tests ``` ### Code Quality - **Linting**: Handled by GitHub
daaainCLAUDE.mddaaain/claude-code-log/CLAUDE.md
page - `~/.claude/projects/project-name/session-{id}.html` - Individual session pages ## Development See @CONTRIBUTING.md for detailed development setup, testing, architecture, and release process. **Before committing or finishing a session, always run `just ci`.** ### Claude
modu-aiCLAUDE.mdmodu-ai/moai-adk/CLAUDE.md
harness`; high-reasoning consult (E1-E4) → `super-advisor` 6. Design collaboration → `manager-design`; E2E tests → `e2e-tester` 7. Multi-milestone Tier L (≥3 milestones AND ≥10 files) → `manager-lead` (sole
adamlyttleappsCLAUDE.mdadamlyttleapps/claude-skill-app-onboarding-questionnaire/CLAUDE.md
Copy should be conversational, not marketing-speak. "Would I say this to a friend?" test
FranciscoMorettiCLAUDE.mdFranciscoMoretti/chat-js/CLAUDE.md
check the blast radius on shared components, and prove the change with a visual test
MicrosoftCLAUDE.mdmicrosoft/skills-for-fabric/CLAUDE.md
Agents**: Conversational AI over Fabric data sources - Docs: https://learn.microsoft.com/en-us/fabric/data-science/concept-data-agent - **Data Agent Evaluation**: Testing and validating Data Agent accuracy - Docs: https://learn.microsoft.com/en-us/fabric/data-science/fabric-data-agent-sdk ### Variable Library (CI/CD) - **Variable Library**: parameterize
Chorus-AIDLCCLAUDE.mdChorus-AIDLC/Chorus/CLAUDE.md
Prisma ORM 7 - **Cache/Pub-Sub**: Redis 7 (ioredis, optional — falls back to in-memory) - **Testing**: Vitest 4 - **Auth**: OIDC (users), API Keys with `cho_` prefix (agents), SuperAdmin (env-based bcrypt
affaan-mCLAUDE.mdaffaan-m/agentshield/CLAUDE.md
AgentShield Security auditor for AI agent configurations (Claude Code, MCP servers, hooks, agents). ## Build & Test ```bash npm run build # tsc + tsup → dist/ npm test # vitest (912 tests
mattprusakCLAUDE.mdmattprusak/autoresearch-genealogy/CLAUDE.md
Guard, Iterations, Protocol). - Vault templates must have valid YAML frontmatter. - Run `scripts/validate-repo` before submitting. - Test prompts end-to-end when behavior changes
fcakyonCLAUDE.mdfcakyon/claude-codex-settings/.claude/CLAUDE.md
Paths**: pathlib, not os.path. - **Verify before planning**: Run `python -c "..."` to test hypotheses. Never assume. - **Virtual env**: `source .venv/bin/activate` or `uv run python -c "..."` - Integrate into existing code
vm0-aiCLAUDE.mdvm0-ai/vm0/CLAUDE.md
Task Routing Use [the documentation index](docs/docs.md) to select relevant guidance. | Changed surface | Read | | ------------------------------------------ | ----------------------------------------------------------------------------------------------------------- | | Tests or test failures | [Testing](docs/testing.md), then the matching application guide | | React, signals, async ownership | [ccstate
RchGravCLAUDE.mdRchGrav/claudebox/claude/CLAUDE.md
command to activate strict discipline - Follow red-green-refactor cycle rigorously - Never write multiple test cases without implementing each one first - Commit test + implementation + docs together for each test case
RchGravCLAUDE.mdRchGrav/claudebox/CLAUDE.md
Common Development Commands When working on ClaudeBox, ensure Bash 3.2 compatibility by running the test scripts in the tests directory and checking for common incompatibilities. ## High-Level Architecture ClaudeBox
wbopanCLAUDE.mdwbopan/cui/CLAUDE.md
Testing Architecture This directory contains comprehensive test coverage for CUI services. ## Testing Philosophy - **Prefer real implementations** over mocks when testing (per project guidelines) - **Comprehensive unit test coverage** for all services
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.
