CLAUDE.md examples from real projects

kstenerudPipes a download into a shellCLAUDE.md

KSCrash / Benchmarks

kstenerud/KSCrash/Benchmarks/CLAUDE.md

mise install` (installs Tuist version from config) - **Trust config**: `mise trust` (required once for security) - **Run Tuist**: `mise exec -- tuist ` or activate mise in your shell ## Benchmarks Workflow ### Quick Start

No other project uses it yet

kstenerudPipes a download into a shellCLAUDE.md

KSCrash / Samples

kstenerud/KSCrash/Samples/CLAUDE.md

mise install` (installs Tuist version from config) - **Trust config**: `mise trust` (required once for security) - **Run Tuist**: `mise exec -- tuist ` or activate mise in your shell ## Sample App Workflow

No other project uses it yet

archtechxReads credentialsCLAUDE.md

tenancy

archtechx/tenancy/CLAUDE.md

databases and users - **TenantDatabaseManagers** - Database-specific implementations (MySQL, PostgreSQL, SQLite, SQL Server) - **Row Level Security (RLS)** - PostgreSQL-based tenant isolation using policies **Advanced Features:** - **Resource Syncing** - Sync central models

nyldnReads credentialsCLAUDE.md

claude-octopus

nyldn/claude-octopus/CLAUDE.md

mode ✅ Deliver Phase: Reviewing authentication implementation Providers: 🔴 Codex CLI - Code quality analysis 🧭 Antigravity CLI - Security and edge cases 🔵 Claude - Synthesis and recommendations ``` **Debate:** ``` 🐙 **CLAUDE OCTOPUS ACTIVATED** - AI Debate Hub 🐙 Debate

No other project uses it yet

yuzutechCLAUDE.md

kroki

yuzutech/kroki/CLAUDE.md

dependency updates that are user-visible (diagram library versions, base Docker image versions) or security-relevant. - Run the linter (`npm run lint` in `mermaid/`, i.e. `biome check src`) whenever

No other project uses it yet

vijaythecoderCLAUDE.md

awesome-claude-agents

vijaythecoder/awesome-claude-agents/CLAUDE.md

clarification ### Tool Inheritance - Omitting `tools` field = inherit all tools (recommended) - Specify tools only for security restrictions - Includes WebFetch, MCP tools when available ## Development Guidelines 1. **Creating New Agents**: - Use templates/agent-template.md

tigerless-labsDeletes or force-pushesCLAUDE.md

agent-memory

tigerless-labs/agent-memory/CLAUDE.md

behavior primes it. Reserve explicit prohibitions for failure modes actually observed in traces. ## Security — agents run autonomously, so the system must fail safe - **Trust nothing by default.** Treat external input

eunomia-bpfCLAUDE.md

bpf-developer-tutorial

eunomia-bpf/bpf-developer-tutorial/CLAUDE.md

Advanced libbpf development - `src/19-21,29,41-42`: Networking (LSM, TC, XDP, sockops) - `src/22-28,34`: Security topics - `src/31,37`: Language integration (Go, Rust) - `src/44-45`: BPF schedulers - `src/47`: GPU tracing - Each tutorial

sandbox-quantumReads credentialsCLAUDE.md

switch

sandbox-quantum/switch/CLAUDE.md

Overview Switch is an AI agent orchestration and governance platform. It onboards, orchestrates, and secures third-party AI agents using a Postgres-backed message store as the internal message

No other project uses it yet

txn2CLAUDE.md

kubefwd

txn2/kubefwd/CLAUDE.md

injecting the OS call (see `runCommand` and `goos` in `pkg/fwdapi/network.go`), not left uncovered. - **Security**: `make security` runs gosec, govulncheck on both modules (gated by `scripts/govulncheck-gate.py` against `.govulncheck-allow.txt`), and osv-scanner

No other project uses it yet

langroidCLAUDE.md

langroid

langroid/langroid/CLAUDE.md

transforming and passing messages - **Collaboration**: Multiple agents can work together on complex tasks ### Key Security Features: - The `full_eval` flag in both `TableChatAgentConfig` and `VectorStoreConfig` controls code injection protection - Defaults

No other project uses it yet

patriksimekCLAUDE.md

vm2

patriksimek/vm2/CLAUDE.md

safely sandboxes untrusted JavaScript code running in Node.js. This is a security-critical project -- every change must be evaluated for sandbox escape potential. ## Public API Exported from `lib/main.js` via `index.js

sw33tLieCLAUDE.md

macshot

sw33tLie/macshot/CLAUDE.md

secret filter │ ├── LanguageManager.swift # Locale resolution + L("…") lookup │ ├── ScreenshotHistory.swift # Local history in ~/Library/Application Support/ │ └── SaveDirectoryAccess.swift # Security-scoped bookmark for save directory │ ├── Upload/ │ ├── UploadPayload.swift # Streamed upload bodies (chunking, incremental SHA256, multipart

dora-rsPipes a download into a shellCLAUDE.md

dora

dora-rs/dora/CLAUDE.md

/review Run the `/review` skill on your changes before committing. This catches structural issues, security problems, and logic errors that tests and clippy miss. ### Step 2: Run /simplify

No other project uses it yet

skyhook-ioReads credentialsCLAUDE.md

radar

skyhook-io/radar/CLAUDE.md

# CLAUDE.md ## Project Overview Radar is a modern Kubernetes visibility tool — local-first, no account

No other project uses it yet

AnthropicCLAUDE.md

anthropic-sdk-python

anthropics/anthropic-sdk-python/CLAUDE.md

doesn't allow `None`. Drop the workaround. Where a wrong value would be a security problem, validate explicitly instead and reject anything unknown. - **Failing open on unknown values.** A permission

corazawafCLAUDE.md

coraza

corazawaf/coraza/CLAUDE.md

AGENTS.md](AGENTS.md). Read it before making changes; the testing, ADR, pull request and security sections are mandatory. @AGENTS.md

gadievronCLAUDE.md

raptor

gadievron/raptor/CLAUDE.md

training. --- ## COMMANDS /project - Project management — `libexec/raptor-project-manager [args]` (see PROJECTS) /scan /fuzz /web /codeql /analyze - Security testing — `python3 raptor.py ` /agentic - Scan → dedup → prep → analysis pipeline (exploitation-validator methodology) — `libexec/raptor-agentic --repo `. Optional

openrewriteCLAUDE.md

rewrite

openrewrite/rewrite/CLAUDE.md

local Maven repository ./gradlew publishToMavenLocal # Apply license headers to files ./gradlew licenseFormat # Run security vulnerability check ./gradlew dependencyCheck ``` ### Running Single Tests ```bash # Test specific module ./gradlew :rewrite-java:test # Test

matt1398CLAUDE.md

claude-devtools / src

matt1398/claude-devtools/src/CLAUDE.md

Structure Three-process Electron architecture: ## Processes - `main/` - Node.js runtime (file system, IPC, lifecycle) - `preload/` - Secure bridge (contextBridge API) - `renderer/` - React/Chromium (UI, state, visualization) - `shared/` - Cross-process types and utilities ## Import