dqmjr

Cursor AI Agent Tooling Projects — AI skill for Claude Code

AI community

Local-first TypeScript tooling for AI coding agents: MCP governance, multi-agent control room, and verification-as-a-tool.

How to install Cursor AI Agent Tooling Projects

This entry records only its repository, not the path inside it, so there is no exact command to give. Open dqmjr/cursor-ai-agent-tooling-projects and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Cursor AI Agent Tooling Projects does

Local-first TypeScript tooling for AI coding agents: MCP governance, multi-agent control room, and verification-as-a-tool.

Alternatives in AI

Token Monitor — Local-first desktop widget for tracking token usage, costs, and limits across 32+ AI coding tools—including Cl 1.8k ★
TokenTracker — Local-first AI token usage & cost tracker for 31 coding tools incl 1.4k ★
Loushang — AI-native agent harness for coding workflows by python: multi-model LLM orchestration, stateful sessions, tool 1.3k ★

README

# Cursor AI Agent Tooling

[![CI](https://github.com/dqmjr/cursor-ai-agent-tooling-projects/actions/workflows/ci.yml/badge.svg)](https://github.com/dqmjr/cursor-ai-agent-tooling-projects/actions/workflows/ci.yml) [![License](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](./LICENSE) [![Node](https://img.shields.io/badge/node-%3E%3D18-brightgreen.svg)](./package.json) [![TypeScript](https://img.shields.io/badge/TypeScript-5.x-3178C6.svg)](https://www.typescriptlang.org/)

Local-first **TypeScript** tools for the AI coding-agent stack: MCP governance, a multi-agent control plane, and verification-as-a-tool.

No cloud lock-in. No telemetry by default. CLI-first, dashboards optional.

Projects

Package	Role	Install	Status
`mcp-sentinel`	Transparent MCP proxy · YAML policy · hash-chained audit · local dashboard	`npx -y mcp-audit-gateway`	`0.1.0`
`agent-control-room`	Parallel-agent kanban · approvals · diff preview · git rollback	clone this repo	`0.1.0`
`verify-mcp`	MCP `verify` tool · markdown / JSON Schema / secrets packs	`npx -y verify-artifact-mcp`	`0.1.0`

┌─────────────────┐     ┌──────────────────────┐     ┌─────────────┐
│  MCP Hosts      │     │  Coding Agents       │     │  Artifacts  │
│  Cursor/Claude  │     │  Claude/Cursor/…     │     │  docs/json  │
└────────┬────────┘     └──────────┬───────────┘     └──────┬──────┘
         │                         │                        │
         ▼                         ▼                        ▼
   mcp-sentinel            agent-control-room          verify-mcp
   policy + audit          timeline + approve          pass / fail

More detail: [docs/ARCHITECTURE.md](./docs/ARCHITECTURE.md)