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.
mogeniusCLAUDE.mdmogenius/renovate-operator/CLAUDE.md
platform base URLs via `internal/utils/platformEndpoints.go`. Labels: `renovate-operator.mogenius.com/ `. ## Invariants Non-obvious rules that silently break security or state if skipped: - A new `Policy`/`AccessDefaults` field that gates behavior must be spelled
Matt-DionisCLAUDE.mdMatt-Dionis/claude-code-configs/claude-config-composer/CLAUDE.md
Server Components when applicable) - **Accessibility-first** design with full keyboard and screen reader support ## Security Best Practices *Combined from: Next.js 15, shadcn/ui* 1. **Always validate Server Actions input** with
seed4jCLAUDE.mdseed4j/seed4j/CLAUDE.md
utilities (`error`, `slug`, `collection`, etc.). | | `statistic/` | Analytics/statistics tracking. | | `wire/` | Spring wiring for frontend, security, springdoc, git info. | ### Module System (how to add a new generator module) A module
dbt-labsCLAUDE.mddbt-labs/dbt-mcp/CLAUDE.md
Change` (major), `Enhancement or New Feature` (minor), `Under the Hood` (patch), `Bug Fix` (patch), `Security` (patch). See `CONTRIBUTING.md` for full contributing guidelines. ## Testing - `MockFastMCP` in `tests/conftest.py` captures registered tools
ithacaxyzCLAUDE.mdithacaxyz/porto/CLAUDE.md
About Porto Porto is a Next-Generation Account Stack for Ethereum that provides a secure, scalable, and user-friendly account system. It's built as a TypeScript monorepo with multiple
SukramJCLAUDE.mdSukramJ/homematicip_local/CLAUDE.md
member ordering 2. **ruff** - Linting and auto-formatting 3. **codespell** - Spell checking 4. **bandit** - Security linting 5. **yamllint** - YAML validation 6. **prettier** - Code formatting 7. **mypy** - Type checking (strict mode
dheijlCLAUDE.mddheijl/swyh-rs/CLAUDE.md
compiler warnings or clippy lints - [ ] Appropriate use of lifetimes and borrowing - [ ] Performance considerations addressed - [ ] Security best practices followed ## Performance Considerations ### Memory Management - **Zero-cost abstractions**: Leverage Rust's zero-cost
anombyte93CLAUDE.mdanombyte93/prd-taskmaster/CLAUDE.md
cmd.py`), with anti-sybil slots released in a crash-safe `finally`. - `collect.py` is the security core — **commit-reveal** (`commit_hash = sha256(diff base..HEAD)`) defeats the diff-copy attack. `antisybil.py
vulnerability-lookupCLAUDE.mdvulnerability-lookup/vulnerability-lookup/CLAUDE.md
from various sources, managing Coordinated Vulnerability Disclosure (CVD), and providing a collaborative space for security advisories. It operates with a modular feeder system that imports vulnerabilities from 30+ sources including
yuxiaopengCLAUDE.mdyuxiaopeng/Github-Ranking-AI/Top100/Claude.md
/affaan-m/ECC) | 299368 | 44230 | JavaScript | 94 | The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond
portainerCLAUDE.mdportainer/agent/CLAUDE.md
Portainer Agent Lightweight Docker/Kubernetes API proxy that enables Portainer to manage remote environments securely. ## Build Commands ```bash make agent # Build agent binary make credential-helper # Build credential helper make healthy
christopherkaraniCLAUDE.mdchristopherkarani/Swarm/CLAUDE.md
shared notes box + one helper fan-out │ │ ├── Voice/ # VoiceSession, speech-to-text/TTS adapters │ │ ├── Security/ # SecretStore, Keychain, redaction, SecureFileIO │ │ ├── Extensions/ # Small Foundation/stdlib helpers │ │ ├── Macros/ # Public macro declarations │ │ ├── Integration/ # Membrane
zhsamaCLAUDE.mdzhsama/claude-sub-agent/CLAUDE.md
specific thresholds: - Requirements completeness validation - Architecture feasibility assessment - Code quality metrics and test coverage - Security vulnerability scanning - Production deployment readiness ### Agent Communication Protocol Agents communicate through structured artifacts: - Each agent
postalsysCLAUDE.mdpostalsys/imapflow/CLAUDE.md
test/` as `*-test.ts`. The parser, command compiler, and search compiler are the most security-sensitive areas - add hostile/malformed-input cases there. - Seeded fuzzing: `test/parser-fuzz-test.ts` generates server responses together with the structure
quiet-nodePipes a download into a shellCLAUDE.mdquiet-node/thuki/CLAUDE.md
must be the default (active) tap, never `ListenOnly`. `ListenOnly` taps are disabled by macOS secure input mode. Secure input activates whenever a password field is focused, when iTerm's "Secure
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.
