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.
CloudAI-XCLAUDE.mdCloudAI-X/claude-workflow/CLAUDE.md
changes | `orchestrator` | | Code quality check | `code-reviewer` | | Bug investigation | `debugger` | | Update docs | `docs-writer` | | Security review | `security-auditor` | | Clean up code | `refactorer` | | Add tests | `test-architect` | ## Common Patterns ### Hook Script
riba2534Pipes a download into a shellCLAUDE.mdriba2534/feishu-cli/CLAUDE.md
task rollback/add-sign/remind`）、`task my/search/related`、`vc note transcript`、`mail` 写类与管理命令（`send/reply/forward/draft-*/message-modify/message-trash/rule-*/thread-*/template *`）、`drive secure-label/add-comment/search/apply-permission`、`wiki space-create`、`msg flag`、`user search --query`、`user search-bot`、`calendar rsvp/event-reply
No other project uses it yet
quillpadCLAUDE.mdquillpad/quillpad/.claude/CLAUDE.md
Summary → Aggressive → Minimal) - `search` results are capped at Summary level to preserve result quality - Security tools (`detect_security_issues`, `detect_taint_flows`, etc.) are never compressed - `get_code_snippet` passes
autonomous-aiReads credentialsCLAUDE.mdautonomous-ai/autonomous-harness/desktop/CLAUDE.md
# CLAUDE.md This file provides guidance to Claude Code (claude.ai/code) when working with code
leepokaiReads credentialsCLAUDE.mdleepokai/Codync/CLAUDE.md
after-change`, release PRs into `main` follow [GitHub releases](docs/guides/development.md#github-releases)): a security and prompt-injection check comes first, and nothing from the item runs before its whole diff
ChiChouCLAUDE.mdChiChou/grapefruit/CLAUDE.md
server. Exposes all REST API and agent RPC. - `/audit` — Autonomous mobile security audit aligned with OWASP MASTG v2. ## Code Style Do not generate code splitter comments (or code dividers/dividers) Prefer
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.
