How real projects brief Claude Code: the commands, conventions and warnings they put in CLAUDE.md.
alinaqiCLAUDE.mdalinaqi/maggy/CLAUDE.md
varies | Code review, bulk generation | | 11 | Claude Sonnet/Opus | $3-5 / $15-25 | Quality-critical, security, architecture | ### Use qwen3 (local) for: - grep, find, awk, sed, jq questions - Shell one-liners
trailofbitsCLAUDE.mdtrailofbits/coop/CLAUDE.md
host→guest data flow, architectural invariants. - [`docs/trust-model.md`](docs/trust-model.md) — trust boundaries and taint sources (the security spec; read before touching secrets, subprocess, network, or the guest boundary). - [`docs/code-style.md`](docs/code-style.md) — Rust authoring
AWSCLAUDE.mdawslabs/automated-security-helper/ash-agent-plugins/agentic-coding/plugins/claude/CLAUDE.md
Security Scanner @../AGENTS.md
sandbox-quantumCLAUDE.mdsandbox-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
ruvnetCLAUDE.mdruvnet/metaharness/kimi-k3-harness/CLAUDE.md
wiring, memory backend, host adapter. - `review-diff` — Review the current working diff for correctness, security, and reuse. ## Architecture This harness uses [@metaharness/kernel](https://www.npmjs.com/package/@metaharness/kernel) — a Rust-compiled WASM module
mhattingpeteCLAUDE.mdmhattingpete/claude-skills-marketplace/CLAUDE.md
Explore agent for thorough codebase mapping 2. Use Grep for pattern detection (security issues, TODOs) 3. Use Read for detailed file analysis 4. Use Bash to run linters/analyzers if available
henrydaumCLAUDE.mdhenrydaum/second-brain/CLAUDE.md
# Second Brain — Architecture Notes Local-first AI kernel with SQLite persistence, a REPL frontend
foreveryhCLAUDE.mdforeveryh/claude-code-switch/CLAUDE.md
README 3. Add defaults to config template 4. Add any region handling if required ## Security Notes - Token masking in `ccm status` - Recommend `chmod 600 ~/.ccm_config` - Environment vars override config file
joaoh82CLAUDE.mdjoaoh82/rustunnel/CLAUDE.md
working with code in this repository. ## What is rustunnel rustunnel is a self-hosted secure tunnel server written in Rust (similar to ngrok). It exposes local services through a public
0xnynCLAUDE.md0xnyn/airship/.claude/CLAUDE.md
Prefer simple conditionals over nested ternary operators - Group related code together and separate concerns ### Security - Add `rel="noopener"` when using `target="_blank"` on links - Avoid `dangerouslySetInnerHTML` unless absolutely necessary
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
danielealbanoCLAUDE.mddanielealbano/android-remote-control-mcp/CLAUDE.md
When you review a plan: - You MUST ALWAYS double check it from a Performance, Security and QA point of view and discuss with the user any relevant finding - the user
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
majiayu000CLAUDE.mdmajiayu000/claude-skill-registry/CLAUDE.md
place. ## Repo Map - `claude-skill-registry-core`: source of truth for discovery, download, dedupe, security scanning, registry/search-index generation, Pages, and publish orchestration. - `claude-skill-registry-data`: archive repo. Canonical layout
s0ld13rrCLAUDE.mds0ld13rr/pentestcode/CLAUDE.md
positives, validates evidence. Read-only. | | **webapp** | subagent | Web application specialist. OWASP Top 10, API security, XSS, SQLi, SSRF. | | **reflector** | subagent | Post-engagement reflection. Analyzes outcomes, generates learned skills, records knowledge
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
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
GMGNAICLAUDE.mdGMGNAI/gmgn-skills/CLAUDE.md
MUST use `gmgn-cli` via the skills below.** This includes: trending tokens, token info, security checks, K-line / price history, wallet holdings, KOL trades, Smart Money trades, swaps
gglucassCLAUDE.mdgglucass/headroom-desktop/CLAUDE.md
Loudness - Stable releases batch weekly; out-of-band stable releases are for regressions and security only (user feedback 2026-09-03: daily update prompts read as churn). Daily
AbilityaiCLAUDE.mdAbilityai/trinity/CLAUDE.md
feature-flows/` as needed - **New capability**: `docs/memory/requirements/ .md` (index: `requirements.md`) + `feature-flows/` ### 5. Security First (PUBLIC REPO) - **This is a public repository** - assume all commits are visible worldwide - Never expose
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.
