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.
maybe-financeReads credentialsCLAUDE.mdmaybe-finance/maybe/CLAUDE.md
lint:fix` - Fix JavaScript/TypeScript issues - `npm run format` - Format JavaScript/TypeScript code - `bin/brakeman` - Run security analysis ### Database - `bin/rails db:prepare` - Create and migrate database - `bin/rails db:migrate` - Run pending migrations - `bin/rails
CherryHQCLAUDE.mdCherryHQ/cherry-studio/CLAUDE.md
MUST READ**: [docs/dev/references/ipc/README.md](docs/dev/references/ipc/README.md) — paradigm boundary (RPC vs REST), schema/router/preload/facade layering, `IpcContext`, error model, security. Non-data command IPC (window/system/shell/notification/external/file) goes through **IpcApi** — the fifth subsystem alongside BootConfig/Cache/Preference/DataApi, RPC-over
Steady17 mentions in 2 weeks
No other project uses it yet
KeygraphHQReads credentialsCLAUDE.mdKeygraphHQ/shannon/CLAUDE.md
CLAUDE.md AI-powered penetration testing agent for defensive security analysis. Automates vulnerability assessment by combining reconnaissance tools with AI-powered code analysis. ## Commands **Prerequisites:** Docker, AI provider credentials
Steady4 mentions in 2 weeks
No other project uses it yet
abhigyanpatwariCLAUDE.mdabhigyanpatwari/GitNexus/CLAUDE.md
imports, or execution flow.** Graph first; text search only for empty/`UNKNOWN`/literals. - For security review, `explain({target: "fileOrSymbol"})` lists taint findings (source→sink flows; needs `analyze --pdg`). - For control/data
Steady29 mentions in 2 weeks
No other project uses it yet
luongnv89CLAUDE.mdluongnv89/claude-howto/uk/CLAUDE.md
Якість коду ```bash # Lint and format Python code ruff check scripts/ ruff format scripts/ # Security scan bandit -c scripts/pyproject.toml -r scripts/ --exclude scripts/tests/ # Type checking mypy scripts/ --ignore-missing-imports
No other project uses it yet
luongnv89CLAUDE.mdluongnv89/claude-howto/vi/CLAUDE.md
Lượng Code ```bash # Lint và format Python code ruff check scripts/ ruff format scripts/ # Security scan bandit -c scripts/pyproject.toml -r scripts/ --exclude scripts/tests/ # Type checking mypy scripts/ --ignore-missing-imports
No other project uses it yet
ccxtCLAUDE.mdccxt/ccxt/CLAUDE.md
# CCXT — Repository Guide for Contributors and AI Agents CCXT is a unified cryptocurrency trading
Steady7 mentions in 2 weeks
No other project uses it yet
remoteintechCLAUDE.mdremoteintech/remote-jobs/CLAUDE.md
sections. Posts a PR comment with results and blocks merge on errors. - **CodeQL** (`.github/workflows/codeql-analysis.yml`): Security scanning on push/PR and weekly schedule. ## Branch Protection The `main` branch has protection rules: - Requires
No other project uses it yet
AnthropicCLAUDE.mdanthropics/financial-services/CLAUDE.md
named agent) │ └── / │ ├── agent.yaml # system + skills → ../../plugins/agent-plugins/ /... │ ├── subagents/*.yaml # depth-1 leaf workers │ ├── steering-examples.json │ └── README.md # security tier + handoff notes ├── claude-for-msft-365-install/ # admin tooling for the Microsoft
1 project uses a version of this
TriliumNextReads credentialsCLAUDE.mdTriliumNext/Trilium/CLAUDE.md
owning service + a spec. Load the **`developing-electron-desktop` skill** for the recipe, the security model, running/launch errors and testing. ### Flathub packaging `apps/desktop/flatpak/` holds the whole recipe — manifest, `trilium.sh`, `flathub.json
Steady2 mentions in 2 weeks
No other project uses it yet
filebrowserCLAUDE.mdfilebrowser/filebrowser/.claude/CLAUDE.md
test ./...`. Reuse existing test harnesses (e.g. `signToken`, `scopedUserStorage`, `handle`, `customFSUser`, `mockUserStore`). --- # Handling security advisories Use this playbook when asked to triage, verify, fix, or manage GitHub security advisories. All advisory
nicolargoCLAUDE.mdnicolargo/glances/CLAUDE.md
strict confinement blocks host file access at the open stage, not the read stage. ### Security Glances runs unauthenticated by default — this is intentional and documented. Most users deploy on private
No other project uses it yet
surrealdbCLAUDE.mdsurrealdb/surrealdb/CLAUDE.md
execution, storage keys, or import/export, consult `SECURITY_GUIDE.md` and confirm the relevant invariants still hold. - Security model and review invariants: `SECURITY_GUIDE.md` - General code review checklist: `REVIEW.md` - Architecture decision records: `doc/adr/` - SurrealQL
No other project uses it yet
surrealdbCLAUDE.mdsurrealdb/surrealdb/surrealism/CLAUDE.md
wasm32-wasip2`, optimizes with wasm-opt, pre-initialises it by snapshotting `init` (see Security Model), packs into a `.surli` archive. - **Run:** `surreal ext run [--fn ] [args...]` — loads the archive, invokes
No other project uses it yet
davila7Reads credentialsCLAUDE.mddavila7/claude-code-templates/CLAUDE.md
dashboard` still call `scripts/deploy.sh`, which is a stale **Vercel** deploy: do not use them. ## Security Guidelines ### ⛔ CRITICAL: NEVER Hardcode Secrets or IDs **NEVER write API keys, tokens, passwords, project
Steady15 mentions in 2 weeks
No other project uses it yet
davila7CLAUDE.mddavila7/claude-code-templates/docs/CLAUDE.md
type has specific structure: **Agents** (162 total) - AI specialists organized by category (Development, Data/AI, Security, Business, etc.) - Stored in `cli-tool/components/agents/{category}/{name}.md` - Installation: `--agent ` **Commands** (210 total
Steady15 mentions in 2 weeks
No other project uses it yet
topoteretesReads credentialsCLAUDE.mdtopoteretes/cognee/CLAUDE.md
# CLAUDE.md This file provides guidance to Claude Code (claude.ai/code) when working with code
Steady10 mentions in 2 weeks
No other project uses it yet
projectdiscoveryCLAUDE.mdprojectdiscovery/nuclei/CLAUDE.md
repo's known vulnerabilities and recurring weak spots. Check it before writing or reviewing security-sensitive code
No other project uses it yet
tirth8205CLAUDE.mdtirth8205/code-review-graph/CLAUDE.md
clients. - File reads: read the bytes once, hash them, then parse the same bytes. ## Security Invariants - No `eval()`, `exec()`, `pickle` or `yaml.unsafe_load()`. - No `shell=True` in subprocess calls. - `_validate
No other project uses it yet
Zackriya-SolutionsCLAUDE.mdZackriya-Solutions/meetily/CLAUDE.md
reintroduce the archived FastAPI backend as a supported requirement. 5. **Legacy FastAPI Security Context**: The archived FastAPI/CORS behavior is unsupported legacy code and must not be treated as a supported
1 project uses a version of this
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.
