Official open-source packages for Rulecatch — AI coding analytics, monitoring, and rule enforcement for Claude Code.
Track every AI coding session in real-time: tool calls, file edits, token usage, costs, and rule violations. Privacy-first with zero-knowledge encryption.
| Package | Description | npm |
|---|---|---|
@rulecatch/ai-pooler |
CLI + hooks for tracking AI coding activity |  |
@rulecatch/mcp-server |
MCP server — query violations and rules from Claude Code |  |
npx @rulecatch/ai-pooler monitor --no-api-keySee what your AI coding assistant is doing in real-time — tool calls, file edits, tokens, costs. Zero setup.
# 1. Install and configure
npx @rulecatch/ai-pooler init
# 2. Start the live monitor
npx @rulecatch/ai-pooler monitor
# 3. (Optional) Add MCP server for in-IDE rule violations
# Add to ~/.claude/mcp.json:
# { "mcpServers": { "rulecatch": { "command": "npx", "args": ["-y", "@rulecatch/mcp-server"] } } }- Tool calls — every Read, Write, Edit, Bash, Grep, Glob with success/failure and I/O size
- Token usage — input/output tokens per model, running totals
- Cost — real-time cost estimation by model (Opus, Sonnet, Haiku)
- Code changes — lines added/removed via git diff
- Session timeline — start, end, duration, active time
- Rule violations — custom rules enforced across your team
All personal data (file paths, emails, project names) is encrypted on your machine before it leaves. We use AES-256-GCM with PBKDF2 key derivation (100k iterations). Your encryption key never leaves your device.
Read more about our privacy architecture
Claude Code hooks → local buffer → flush to API → dashboard
↓
rule engine → violation alerts
- Hooks capture events from Claude Code (zero token overhead — hooks run in bash)
- Buffer stores events locally as JSON files
- Flush sends batched events to the Rulecatch API (encrypted)
- Dashboard shows analytics, trends, and team insights
- Rules are checked in real-time and violations surface in the MCP server
MIT