How real projects brief Claude Code: the commands, conventions and warnings they put in CLAUDE.md.
m0n0x41dCLAUDE.mdm0n0x41d/haft/CLAUDE.md
project memory are **V9 CONTRACT** capabilities. Their presence in source, schemas, skills, or local tests is not installed-runtime proof. Any installed-runtime readiness claim requires current **EXACT-CANDIDATE EVIDENCE
peterkrueckCLAUDE.mdpeterkrueck/Claude-Code-Development-Kit/templates/CLAUDE.md
significant changes to keep docs in sync with the code. ## 6. Coding Standards ## 7. Testing ## 8. Privacy & Security
https-deeplearning-aiCLAUDE.mdhttps-deeplearning-ai/sc-agent-skills-files/L6/CLAUDE.md
pyproject.toml + hatchling | | Dependency Management | uv | ## Development ```bash uv run task uv run pytest # run tests ``` ## Architecture ``` src/task/ ├── main.py # Entry point, imports app from commands ├── commands/ │ ├── __init__.py # Creates main
elirantutiaCLAUDE.mdelirantutia/vibeyard/CLAUDE.md
AppImage` (linux), and NSIS installer + portable `.exe` (win). CI covers all three platforms. ## Testing ```bash npm test # Run all tests once npm run test:watch # Watch mode (re-runs
mbaileyCLAUDE.mdmbailey/voicemode/CLAUDE.md
integrating speech-to-text (STT) and text-to-speech (TTS) services. ## Key Commands ### Development & Testing ```bash # Install in development mode with dependencies make dev-install # Run all unit tests make
miscusi-peekCLAUDE.mdmiscusi-peek/cheatengine-mcp-bridge/CLAUDE.md
bash # Install Python deps (Windows only — uses pywin32) pip install -r MCP_Server/requirements.txt # Integration test suite (requires: CE running, ce_mcp_bridge.lua loaded, a process attached) python MCP_Server/test_mcp.py ``` Loading
Team-CommonlyCLAUDE.mdTeam-Commonly/commonly/CLAUDE.md
Ship with proof, and commit what you learned.** Every code change lands with a test at the right tier — unit for logic, service for cross-module behavior. **v2 layout/CSS changes
raroqueCLAUDE.mdraroque/boop-agent/CLAUDE.md
debug scripts under `scripts/` and `debug/` written during a real session. - Test fixtures hand-copied from real responses. - Comments or commit messages quoting real data. - README/docs examples that use real
specstoryaiCLAUDE.mdspecstoryai/getspecstory/specstory-cli/CLAUDE.md
root of the repository. ```zsh # Build for current platform go build -o specstory ``` ### Testing ```zsh # Run all tests go test ./... # Run tests with verbose output go test -v ./... # Run tests
jayminwestCLAUDE.mdjayminwest/overstory/CLAUDE.md
worker overlay hooks.json.tmpl # Template for settings.local.json copilot-hooks.json.tmpl # Template for Copilot hooks config # Tests colocated: src/config.test.ts, src/mail/store.test.ts, etc. ``` ### What `ov init` creates in a target project ``` target-project/ .overstory/ config.yaml # Project
sceneviewCLAUDE.mdsceneview/sceneview/CLAUDE.md
review of a merged PR, a whole-module read to draft an inventory, unit tests and mechanical refactors from a closed brief. Keep with Claude: product decisions, UI validated
first-flukeCLAUDE.mdfirst-fluke/oh-my-agent/CLAUDE.md
source repository itself. - `.agents/` modifications are allowed (this IS the source repo) - `bun run test` runs CLI tests (vitest). - `bun run lint` runs the linter. - `bun run build` builds
first-flukeCLAUDE.mdfirst-fluke/oh-my-agent/cli/CLAUDE.md
cross-vendor fallback via `oma agent spawn`; use the root dispatch configuration. - Select tests from the affected CLI behavior. Run builds only when explicitly requested. ## Workflows Run workflows only when
nvkCLAUDE.mdnvk/llm-wiki/CLAUDE.md
wiki Development Guide ## Testing Run tests before declaring any change to plugin code done. ## GitHub Auth And Transport Agents should use GitHub CLI web login and HTTPS git transport
greyhaven-aiCLAUDE.mdgreyhaven-ai/autocontext/CLAUDE.md
optional analyst/architect) mcp/ # MCP server, tool implementations, sandbox manager server/ # FastAPI dashboard + WebSocket events tests/ # Pytest tests (~7700 tests) migrations/ # SQLite migration SQL files (001-007, applied in filename order
sipyourdrink-ltdCLAUDE.mdsipyourdrink-ltd/bernstein/CLAUDE.md
subtree. Each covers: what the directory is for, key files, invariants, and how to test that subtree. | Path | Covers | |----------------------------------------------|--------| | `src/bernstein/adapters/AGENTS.md` | CLI agent adapters | | `src/bernstein/cli/AGENTS.md` | Click CLI | | `src/bernstein/core/lineage/AGENTS.md` | Lineage: artifact provenance
dohoooCLAUDE.mddohooo/helmor/CLAUDE.md
clippy -- -D warnings bun run lint:fix # biome --write + cargo clippy --fix + cargo fmt ``` Tests are **three targets** — `bun run test` runs all three (frontend -> sidecar -> rust). Pre-commit hook
GanyuanRanCLAUDE.mdGanyuanRan/Aegis/CLAUDE.md
host command prompts ├── agents/ # agent definition prompts ├── hooks/ # Claude Code hooks ├── scripts/ # maintenance scripts ├── tests/ # host and workflow tests ├── .claude-plugin/ # Claude Code plugin manifest ├── .codex-plugin/ # Codex plugin manifest
caliber-ai-orgCLAUDE.mdcaliber-ai-org/ai-setup/CLAUDE.md
Commands ```bash npm run build # tsup → dist/ npm run dev # watch mode npm run test # vitest run npm run lint # eslint src/ npx tsc --noEmit # type check npx vitest
Xiangyue-ZhangCLAUDE.mdXiangyue-Zhang/auto-deep-researcher-24x7/CLAUDE.md
examples (illustrative only in this repo — these endpoint/model combinations have not been live-smoke-tested here): ```yaml # Qwen / DashScope agent: provider: "openai" model: "qwen-plus" base_url: "https://dashscope.aliyuncs.com/compatible-mode/v1
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.
