How real projects brief Claude Code: the commands, conventions and warnings they put in CLAUDE.md.
AgriciDanielCLAUDE.mdAgriciDaniel/claude-ads/CLAUDE.md
product boundaries, evidence and capability manifests, safety policy, maturity, ecosystem decisions, and release gates. - `tests/` and `evals/`: deterministic and model-facing verification. ## Development - Keep skill entrypoints concise and use progressive
AnthropicCLAUDE.mdanthropics/claude-code-action/base-action/CLAUDE.md
typecheck` - Format code: `bun run format` - Check formatting: `bun run format:check` - Run tests: `bun test` - Install dependencies: `bun install` ### Action Testing - Test action locally: `./test-local.sh` - Test specific file
AnthropicCLAUDE.mdanthropics/claude-code-action/CLAUDE.md
CLAUDE.md ## Commands ```bash bun test # Run tests bun run typecheck # TypeScript type checking bun run format # Format with prettier bun run format:check # Check formatting ``` ## What This Is A GitHub
AppleCLAUDE.mdapple/containerization/CLAUDE.md
guidance to Claude Code (claude.ai/code) when working with code in this repository. ## Build / Test / Format The project is built via `make`, not directly with `swift build`. Two Swift packages
PydanticCLAUDE.mdpydantic/monty/CLAUDE.md
unix)]`-only code in the main crate — all features must work on all platforms - Tests in `crates/*/tests/` should be cross-platform; use helper functions for OS-specific APIs like
PydanticCLAUDE.mdpydantic/monty/crates/monty/src/modules/CLAUDE.md
Verify every message against CPython with the `/python-playground` skill before pinning it in a test. ## Always use `#[derive(FromArgs)]` for function parameters Any function beyond the trivial 0/1/2-positional shapes (covered
AnthropicCLAUDE.mdanthropics/claude-agent-sdk-python/CLAUDE.md
Lint and style # Check for issues and fix automatically python -m ruff check src/ tests/ scripts/ --fix python -m ruff format src/ tests/ scripts/ # Typecheck python -m mypy src/ scripts
GetStreamCLAUDE.mdGetStream/Vision-Agents/CLAUDE.md
into dependency issues, stop and ask. ```bash # Full check (ruff + mypy + unit tests) uv run --no-sync dev.py check # Unit tests only (--no-sync avoids uv panic in sandboxed environments
NVIDIACLAUDE.mdNVIDIA/Isaac-GR00T/CLAUDE.md
format (uses ruff via pre-commit) pre-commit run --all-files # Run CPU tests python -m pytest tests/ -m "not gpu" -v --timeout=300 # Run GPU tests python -m pytest
VercelCLAUDE.mdvercel-labs/deepsec/CLAUDE.md
package: bundled CLI + the `deepsec/config` sub-export + the @vercel/sandbox executor e2e/ End-to-end tests ``` ## Commands ```bash pnpm install pnpm test # all packages, including e2e pnpm test:unit # excludes
OpenCoworkAICLAUDE.mdOpenCoworkAI/open-codesign/CLAUDE.md
declared in `pnpm-workspace.yaml`. - **Build orchestration**: Turborepo. - **Lint + format**: Biome (single tool, no ESLint + Prettier). - **Tests**: Vitest (unit) + Playwright (E2E). New features require at least one Vitest test. - **TypeScript**: `strict: true
UpsonicCLAUDE.mdUpsonic/Upsonic/CLAUDE.md
references `feature.md §4` for shared aspects. - **`documents/ai/guides/bug-fix.md`** — Use when fixing a reported bug, failing test, traceback, or behaviour that contradicts a stated contract. Defines the four mandatory phases (Reproduce → Diagnose
datahaven-xyzCLAUDE.mddatahaven-xyz/datahaven/CLAUDE.md
compatibility - External validators with rewards system ## Pre-requisites - [Kurtosis](https://docs.kurtosis.com/install): For launching test networks - [Bun](https://bun.sh/) v1.2+: TypeScript runtime and package manager - [Docker](https://www.docker.com
AnthropicCLAUDE.mdanthropics/defending-code-reference-harness/CLAUDE.md
each topic are in `docs/`; targets are in `targets/` (canary is the fast smoke test). The rest of this file is the pipeline operator guide. --- # vuln-pipeline Execution-verified vulnerability
TheCraigHewittCLAUDE.mdTheCraigHewitt/seomachine/CLAUDE.md
python3 research_priorities_comprehensive.py python3 research_serp_analysis.py python3 research_topic_clusters.py python3 research_trending.py python3 seo_baseline_analysis.py python3 seo_bofu_rankings.py python3 seo_competitor_analysis.py # Test API connectivity python3 test_dataforseo.py ``` ## Content Pipeline `topics/` (ideas) → `research/` (briefs) → `drafts/` (articles) → `review-required/` (pending
plastic-labsCLAUDE.mdplastic-labs/honcho/CLAUDE.md
stored in `(observer, observed)` collections - **Keys**: Create scoped JWTs - **Webhooks**: Register endpoint, list, delete, test ### Key Features #### Chat Endpoint (Dialectic agent) (`/peers/{peer_id}/chat`) - Provides bespoke responses informed
ShopifyCLAUDE.mdShopify/flash-list/CLAUDE.md
prop on FlashList. Do not use it, suggest it, or add it. ## Build & Test ```bash yarn build # compile TypeScript to dist/ yarn test --forceExit yarn type-check yarn lint ``` **Important
kyegomezCLAUDE.mdkyegomez/swarms/CLAUDE.md
skipped. ``` [TYPE][Function/FileName][Short Description] ``` - `TYPE` in capitals: for example `FEAT`, `FIX`, `DOCS`, `REFACTOR`, `TEST`, `CHORE`. - `Function/FileName`: the function, class, module or file the change is about. - `Short Description
WenyuChiouCLAUDE.mdWenyuChiou/awesome-agentic-ai-zh/CLAUDE.md
OpenAI-compatible default (Path A) - `starter_anthropic.py` = Anthropic SDK version (Path B) - `test.py` = mock-based tests for the Ollama starter (OpenAI-compat response shape) - `test_anthropic.py` = mock-based tests for the Anthropic
enricorosCLAUDE.mdenricoros/big-AGI/CLAUDE.md
clever headings (plain nouns). Cut sentences that carry no information. ## Common Development Tasks ### Testing & Quality - Browser floor: `eslint.config.mjs` hard-bans ES2023 `toSorted/toReversed/toSpliced/with` and `new Intl.Segmenter` via `no-restricted-syntax` (they
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.
