How real projects brief Claude Code: the commands, conventions and warnings they put in CLAUDE.md.
MagicCubeCLAUDE.mdMagicCube/agentara/CLAUDE.md
project: Agentara --- > All documents should be written in simple and concise English. @docs/overview.md ## Notes - Use `bun check` to type-check and lint your code after you finish writing. - Always
MagicCubeCLAUDE.mdMagicCube/agentara/user-home/CLAUDE.md
wiki skill) ├── projects/ # Git repos and code projects ├── uploads/ # Uploaded files: images, videos, audio, documents, etc. └── outputs/ # Generated outputs: reports, images, videos; organized in sub-folders ``` > Create if not exists
transilienceaiCLAUDE.mdtransilienceai/communitytools/CLAUDE.md
operations (`DROP`, `rm -rf`, DoS, data corruption) unless strictly necessary. Stay within declared scope. Document findings with complete evidence chains. Report unexpected access or data exposure immediately
intelligencedevCLAUDE.mdintelligencedev/manifold/CLAUDE.md
code and reports suspicious constructs that could be bugs. | | `go doc` | Extracts and generates documentation for Go packages. | | `go get` | Adds, updates, or removes dependencies in the `go.mod` file
madarcoCLAUDE.mdmadarco/agentbox/CLAUDE.md
still shells (`open`, `hub`), update the tray app too** — its own [`CLAUDE.md`](../agentbox-tray/CLAUDE.md) documents exactly which surfaces it depends on. The app's data/action layer sits behind a `BoxSource` protocol
ankitvguptaCLAUDE.mdankitvgupta/exo/CLAUDE.md
regressions against a stored baseline. Update baseline with `npm run eval -- --update-baseline`. ## Documentation - [Architecture](docs/ARCHITECTURE.md) — system diagram, data flows, IPC inventory, extension/agent systems - [Testing](docs/TESTING.md) — test framework, projects, mocking
trailofbitsCLAUDE.mdtrailofbits/skills-curated/CLAUDE.md
Contributing Skills ## Resources **Official Anthropic documentation (always check these first):** - [Claude Code Plugins](https://docs.anthropic.com/en/docs/claude-code/plugins) - [Agent Skills](https://docs.anthropic.com/en/docs/claude-code/skills) - [Best Practices](https://docs.anthropic.com/en/docs/claude-code/skills#best-practices) **Reference skills** - learn
jbarbierCLAUDE.mdjbarbier/CLAUDE.md/CLAUDE.md
whole thing. Do it right. Do it with tests. Do it with documentation. Do it so well that Julien is genuinely impressed — not politely satisfied, actually impressed. Never offer
bvisibleCLAUDE.mdbvisible/mcp-ssh-manager/CLAUDE.md
runtime dependency requiring a newer Node than `engines.node` advertises — that last check carries one documented exception, `@hono/node-server` (needs Node >=20, pulled by the MCP SDK for its HTTP transport, never
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.
