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.
STRRLCLAUDE.mdSTRRL/cloudflare-tunnel-ingress-controller/CLAUDE.md
Ingress Controller that integrates with Cloudflare Tunnel to expose Kubernetes services to the internet securely without requiring port forwarding or firewall configuration. It watches Kubernetes Ingress resources and automatically configures
chernistryCLAUDE.mdchernistry/bernstein/CLAUDE.md
src/bernstein/core/lineage/AGENTS.md` | Lineage: artifact provenance | | `src/bernstein/core/orchestration/AGENTS.md` | Orchestration engine | | `src/bernstein/core/quality/AGENTS.md` | Quality gates and verification | | `src/bernstein/core/security/AGENTS.md` | Security: audit chain, identity, policy | | `tests/AGENTS.md` | Test suite | ## Build & test ``` uv sync # install + lock uv run python
1 project uses a version of this
wireappCLAUDE.mdwireapp/wire-webapp/CLAUDE.md
connections for real-time communication - Protocol message handling (send/receive Protobuf messages) - Cryptographic operations for secure messaging The webapp uses these modules for all backend communication. When making changes to core
wellwelwelCLAUDE.mdwellwelwel/poku/CLAUDE.md
demand: - `/architecture`: project structure, execution flow, config system, competitive context - `/engineering`: performance patterns, security, build pipeline, CI/CD - `/testing`: test structure, fixtures, utils, Docker testing, coverage strategy - `/documentation`: Docusaurus framework, feature
affaan-mCLAUDE.mdaffaan-m/agentshield/CLAUDE.md
AgentShield Security auditor for AI agent configurations (Claude Code, MCP servers, hooks, agents). ## Build & Test ```bash npm run build # tsc + tsup → dist/ npm test # vitest (912 tests
learningequalityCLAUDE.mdlearningequality/kolibri/CLAUDE.md
pattern, update all usages — not just the one you're working on. - **Security**: API endpoints must have appropriate authentication and permissions. Validate submitted data. Don't bypass security practices
WindscribeCLAUDE.mdWindscribe/Desktop-App/CLAUDE.md
Linux written in C++17 with Qt. ### What It Does This application provides secure, private internet access by routing your traffic through encrypted VPN tunnels. It protects your physical location
No other project uses it yet
projectdiscoveryCLAUDE.mdprojectdiscovery/tlsx/CLAUDE.md
data gathering and analysis toolkit focused on TLS connection testing, certificate analysis, and security assessment. It's part of the ProjectDiscovery ecosystem and supports multiple TLS connection modes, fingerprinting
Steady6 mentions in 2 weeks
No other project uses it yet
RchGravCLAUDE.mdRchGrav/claudebox/claude/CLAUDE.md
Final review** - Check `git diff --staged` to review what will be committed 8. **Security check** - Verify no sensitive information (keys, tokens, passwords) is included ### Test Requirements **All tests must pass
RchGravCLAUDE.mdRchGrav/claudebox/CLAUDE.md
string comparisons - Docker containerization specialist understanding multi-stage builds, layer optimization, and security - Familiar with ClaudeBox architecture: project isolation, profile system, security model ## Code Analysis Approach 1. **READ** the entire
vndeeCLAUDE.mdvndee/llm-sandbox/CLAUDE.md
Large Language Model (LLM) generated code in a safe and isolated mode. It provides secure execution environments for AI-generated code while offering flexibility in container backends and comprehensive language
wflixuCLAUDE.mdwflixu/RClick/CLAUDE.md
AppState + ConfigService + MenuService + ActionService + PermissionService + Messager. **It is NOT a separate process / Helper.** - **BookmarkManager**: security-scoped bookmarks — the only folder-authorization mechanism (mandatory for the sandboxed App Store build) - Data
Kc1tCLAUDE.mdKc1t/alethe-agents/CLAUDE.md
BUNDLED_SKILLS` and install globally or into a project (`.claude/skills`, `.agents/skills`). ## 6. Gotchas / security - `tauri.conf.json` ships a strict CSP (`script-src 'self'`, `worker-src 'none'`), asserted literally by `src/securityPolicy.test.ts
prompt-securityCLAUDE.mdprompt-security/clawsec/CLAUDE.md
Commands **Pre-push validation** (mirrors CI — run before pushing): ```bash ./scripts/prepare-to-push.sh # lint, typecheck, build, security scans ./scripts/prepare-to-push.sh --fix # auto-fix where possible ``` **Lint:** ```bash npx eslint
Lazarus-AICLAUDE.mdLazarus-AI/clearwing/CLAUDE.md
Clearwing Clearwing is an AI-driven security research and pentesting framework. It provides ~100 agent tools organized into categories below. ## Authorship & attribution **Humans are the authors. AI is a tool
hookdeckCLAUDE.mdhookdeck/outpost/CLAUDE.md
Provide feedback on: - Code quality and best practices - Potential bugs or issues - Performance considerations - Security concerns - Test coverage Be constructive and helpful in your feedback
komikku-appCLAUDE.mdkomikku-app/anikku/CLAUDE.md
cases, models, repository interfaces | | `data/` | SQLDelight database, repository implementations | | `core:common/` | Network (OkHttp), security, storage, shared utils | | `core:archive/` | Archive reading utilities | | `core-metadata/` | Comic-info metadata parsing | | `source
borgheiCLAUDE.mdborghei/Claude-Skills/c-level-advisor/CLAUDE.md
sales, GTM - **coo-advisor/** — operations, scaling, process - **chro-advisor/** — talent, culture, comp - **ciso-advisor/** — security strategy, risk, compliance - Plus: board-deck-builder, board-meeting, change-management, chief-of-staff, company
Steady5 mentions in 2 weeks
No other project uses it yet
borgheiCLAUDE.mdborghei/Claude-Skills/documents/CLAUDE.md
document audit (comments, tracked changes, headings, styles) | | PDF Toolkit | `pdf-toolkit/` | `pdf_auditor.py` | PDF metadata, security, encryption, embedded JS / files | | Pptx Toolkit | `pptx-toolkit/` | `pptx_auditor.py` | PowerPoint audit (slides, density, notes, animations
Steady5 mentions in 2 weeks
2 projects use a version of this
borgheiCLAUDE.mdborghei/Claude-Skills/markdown-html/CLAUDE.md
HTML-escaped at the boundary. Treat any change that emits unescaped input as a security regression. ## Common Patterns ``` markdown-html/ / ├── SKILL.md ├── references/ │ └── *.md (rulebooks, severity models, layout and density guidance
Steady5 mentions in 2 weeks
No other project uses it yet
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.
