How real projects brief Claude Code: the commands, conventions and warnings they put in CLAUDE.md.
czlonkowskiCLAUDE.mdczlonkowski/n8n-skills/CLAUDE.md
Write code for the AI-agent-callable Custom Code Tool (`@n8n/n8n-nodes-langchain.toolCode`) - Critical distinction from Code node: return a string (not `[{json:{...}}]`), `$fromAI()` not available, different sandbox - Unstructured (`query` string
jacob-bdCLAUDE.mdjacob-bd/gemini-notebook-mcp-cli/CLAUDE.md
core/ # Low-level API client (no business logic) │ ├── client.py # Internal batchexecute API calls │ ├── constants.py # Code-name mappings (CodeMapper class) │ └── auth.py # AuthManager for profile-based token caching └── utils/ ├── config.py # Configuration
Q00CLAUDE.mdQ00/ouroboros/CLAUDE.md
Seed to GitHub Issues | | `ooo maintain` | `gh` CLI — review and disposition of issues and PRs | | `ooo resume-session` | Restore previous Claude Code session context | ## Agents Loaded on-demand — not preloaded
UfoMiaoCLAUDE.mdUfoMiao/zcf/CLAUDE.md
files, text/mds and tests to the root folder # Multica Agent Runtime You are a coding agent in the Multica platform. Use the `multica` CLI to interact with the platform. ## Background
FlorianBruniauxCLAUDE.mdFlorianBruniaux/claude-code-ultimate-guide/CLAUDE.md
audits, and codebase reviews. ### Public content must be portable Apply this rule to guides, evaluations, examples, changelogs, indexes, exports, and landing content, including code blocks, tables, captions, and link targets
fengshao1227CLAUDE.mdfengshao1227/ccg-workflow/CLAUDE.md
Teams 系列**：新增 4 个独立命令（`team-research`/`team-plan`/`team-exec`/`team-review`） - 🏗️ **并行实施**：利用 Claude Code Agent Teams spawn Builder teammates 并行写代码 - 📋 **完整链路**：需求→约束 → 消除歧义→计划 → 并行实施 → 双模型审查
fengshao1227CLAUDE.mdfengshao1227/ccg-workflow/dsh-ccg/CLAUDE.md
worked. The convention now names that specifically: reviewing what nobody has written is worse than idling, because it also produces findings about code that will not exist. ## The fresh-install
fengshao1227CLAUDE.mdfengshao1227/ccg-workflow/src/CLAUDE.md
修复） - `skipCategories` 参数支持跳过 `impeccable` 分类（用户可选不安装） --- ### utils/mcp.ts 三端同步 MCP 配置需要在三个工具链同步： | 工具 | 配置文件 | 同步函数 | |------|----------|----------| | Claude Code | `~/.claude.json` | `writeClaudeCodeConfig()` / `mergeMcpServers()` | | Codex | `~/.codex/config.toml` | `syncMcpToCodex()`（`installer-mcp.ts`）| | Gemini | `~/.gemini/settings.json` | `syncMcpToGemini()`（`installer-mcp.ts`）| **`installer-mcp.ts:configureMcpInClaude()` 管线**（`src/utils/installer-mcp.ts
fengshao1227CLAUDE.mdfengshao1227/ccg-workflow/templates/CLAUDE.md
spec-impl.md` | `/ccg:spec-impl` | 按规范执行 + 多模型协作 + 归档 | | `spec-review.md` | `/ccg:spec-review` | 双模型交叉审查（独立工具，随时可用） | --- ## commands/agents/（7 个子智能体） 子智能体安装为 Claude Code 的子 Agent，由主命令通过 `Agent(subagent_type=...)` 调用。 | 文件 | name | 描述
epoko77-aiCLAUDE.mdepoko77-ai/im-not-ai/CLAUDE.md
report`면 사람 검토 권고. 수렴 판정은 LLM 재탐지가 아니라 `verify_gates.py`(결정적, exit code)가 내린다. `verify_change_rate.py`는 기존 연동을 위해 보존한다. ## 에이전트 구성 (9개 — 역할 구분 필수) **런타임 3종
Galaxy-DawnCLAUDE.mdGalaxy-Dawn/claude-scholar/CLAUDE.md
writing -> `review-response` - Bound research repo knowledge maintenance -> `obsidian-project-kb-core` For coding, debugging, architecture, review, and verification tasks, prefer the matching development skill instead of improvising. --- ## Bound Repo
breaking-brakeCLAUDE.mdbreaking-brake/cc-wf-studio/CLAUDE.md
becomes the CHANGELOG entry) ``` This writes a `.changeset/ .md` file — commit it alongside your code. **You never hand-edit `CHANGELOG.md`; Changesets generates it.** If a PR genuinely needs no release
CloudflareCLAUDE.mdcloudflare/vibesdk/CLAUDE.md
this repository. ## Communication Style - Be professional, concise, and direct - Do NOT use emojis in code reviews, changelogs, or any generated content. You may use professional visual indicators or favor markdown
weave-osCLAUDE.mdweave-os/router/CLAUDE.md
write. - **Non-tautological tests** — every test must assert behavior that breaks if prod code deleted. ## Layer model and import rules Three concentric layers. Imports flow inward only. ``` +-------------------------------------------------------------------+ | cmd/router/main.go (composition root
SenteLabsAICLAUDE.mdSenteLabsAI/OpenExecutive/CLAUDE.md
default > `./episodic_memory.db` unless the test isolates it. A test module that > exercises audited code (alerts review, sweeps) without monkeypatching > `openexecutive.audit.log_event` (or the audit logger's DB) leaks rows that
SaladDayCLAUDE.mdSaladDay/cc-switch-cli/CLAUDE.md
issues. - Validate every finding against the code. Make minimal fixes for confirmed issues within scope, run the relevant checks, then start another blind review with a new subagent under
entireioCLAUDE.mdentireio/cli/CLAUDE.md
Review architecture](docs/architecture/review-command.md) | | E2E tests | [E2E guide](e2e/README.md) | ## Verification | Task | Command / requirement | | --- | --- | | Unit tests | `mise run test` | | Integration tests | `mise run test:integration`; required when changing integration test code | | Deterministic
clideyCLAUDE.mdclidey/whodb/CLAUDE.md
AGENTS.md ## Claude Code - Use plan mode for multi-file, risky, architectural, or ambiguous changes. - Use subagents only for bounded sidecar work: exploration, review, test triage, or documentation lookup. - Prefer separate
NateBJones-ProjectsCLAUDE.mdNateBJones-Projects/OB1/CLAUDE.md
License:** FSL-1.1-MIT. No commercial derivative works. Keep this in mind when generating code or suggesting dependencies. ## Repo Structure ``` extensions/ — Curated, ordered learning path (6 builds
breferrariCLAUDE.mdbreferrari/obsidian-mind/CLAUDE.md
self-heal guards; don't diagnose it. ### Custom Slash Commands Defined in `.claude/commands/`. Claude Code auto-surfaces every command with its description in the session's skills list — **that injected
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.
