Curated GitHub repositories, open-source tools, and 566 brand DESIGN.md specifications for AI agents.
Enforce Next.js best practices, proper file structure, component patterns, and TypeScript usage with automated code reviews and suggestions. Validates Next.js App Router conventions, Server Client component patterns, proper imports, and TypeScript usage. Provides real-time feedback on code quality and adherence to Next.js best practices.
Automatically run quick tests after code modifications to ensure nothing breaks. This hook executes 'npm run test:quick' silently after any Edit operation and provides feedback on test status. Helps catch breaking changes immediately during development. Only runs if package.json exists and the test:quick script is available.
Automatically loads AGENTS.md configuration file content at session start to ensure Claude Code follows project-specific agent behavior. Only loads if AGENTS.md exists, otherwise passes empty context. Supports the universal AGENTS.md standard for cross-platform AI assistant compatibility.
Automatically format Python files after any Edit operation using black formatter. This hook runs 'black' on any .py file that Claude modifies, ensuring consistent Python code formatting. Requires black to be installed ('pip install black'). The command includes error suppression (2 dev null true) so it won't fail if black is not installed.
Automatically detects hardcoded secrets before git commits. Scans for API keys from 30 providers (Anthropic: sk-ant-..., OpenAI: sk-..., AWS: AKIA..., Stripe: sk live ..., Google: AIza..., GitHub: ghp ..., Vercel, Supabase, Hugging Face: hf ..., Replicate: r8 ..., Groq: gsk ..., Databricks: dapi..., GitLab, DigitalOcean, npm, PyPI, and more), tokens, passwords, private keys, and database credentials. Blocks commits containing secrets and suggests using environment variables instead.
Create automatic backup of files before any Edit operation for safety. This hook creates a timestamped backup copy (filename.backup.timestamp) of any existing file before Claude modifies it. Provides a safety net to recover previous versions if needed. Only backs up existing files, includes error suppression to handle edge cases gracefully.
Advanced protection against dangerous shell commands with multi-level security. Blocks catastrophic operations (rm -rf , dd, mkfs), protects critical paths (.claude , .git , node modules ), and warns about suspicious patterns. Features: catastrophic command blocking, critical path protection, smart pattern detection, and detailed safety messages.
Real-time browser visualization of Claude Code's context window and subagent tool execution as a git-graph timeline. Opens http: localhost:7878 on SessionStart with a vertical timeline (most recent on top), one column per agent (main subagents branching from their Task tool call). Tool calls are color-coded by type (Read green, Edit Write orange, Bash red, Grep Glob cyan, Task purple, Web yellow, MCP gray). Right sidebar shows context-window usage (tokens 200K) with cache read cache creation input output breakdown plus per-subagent mini-context. Reads .claude projects .jsonl directly - no data replication, no network calls. Pure stdlib Python, zero pip dependencies. Persistent daemon HTTP server on port 7878 (auto-fallback 7879-7888 if busy; override with CONTEXT TIMELINE PORT env var). Watchdog auto-shutdown after 1h of inactivity. Disable browser auto-open with CONTEXT TIMELINE NO BROWSER 1. Manual shutdown: python3 .claude hooks context-timeline.py --shutdown
Send Telegram notifications when Claude Code finishes working. Requires TELEGRAM BOT TOKEN and TELEGRAM CHAT ID environment variables. Get bot token from @BotFather, get chat ID by messaging the bot and visiting https: api.telegram.org bot getUpdates