sunchayn

Agenteq — AI skill for Claude Code

AI community

A single-source CLI tool to compile and publish repository rules, skills, commands, and MCP configurations to the developer's local AI agents.

How to install Agenteq

This entry records only its repository, not the path inside it, so there is no exact command to give. Open sunchayn/agenteq and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Agenteq does

A single-source CLI tool to compile and publish repository rules, skills, commands, and MCP configurations to the developer's local AI agents.

Alternatives in AI

AIHawk — Open-source AI browser agent: describe any task in plain language and it autonomously browses, clicks, types a 30.3k ★
Peekaboo — Peekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, o 3.2k ★
Open Science — Open Science Desktop — local-first, model-agnostic AI research workbench for macOS, Windows & Linux 1.5k ★

README

agenteq

![agenteq-gh-cover.png](art/agenteq-gh-cover.png)

[![npm](https://img.shields.io/npm/v/agenteq?style=flat-square)](https://www.npmjs.com/package/agenteq) [![CI](https://img.shields.io/github/actions/workflow/status/sunchayn/agenteq/ci.yml?style=flat-square)](https://github.com/sunchayn/agenteq/actions) [![Node.js](https://img.shields.io/badge/Node.js->=20-3c873a?style=flat-square)](https://nodejs.org) [![License](https://img.shields.io/badge/License-MIT-blue?style=flat-square)](LICENSE) [![Coverage](https://img.shields.io/codecov/c/github/sunchayn/agenteq?style=flat-square)](https://codecov.io/gh/sunchayn/agenteq)

[Getting started](#getting-started) • [Migrating an existing repo](#migrating-an-existing-repo) • [Usage](#usage) • [Supported agents](#supported-agents)

**A single source of truth for AI coding agents configuration.**
Agenteq reads guidelines, MCP servers, skills, and commands from one centralized folder, detects installed agents, and generate each relevant artifact in the path/format the agent expects. It lets you configure everything once, regardless of which agents your collaborators use, and keeps the generated files out of the repo.

![agenteq.png](art/agenteq.png)

Getting started

Add this layout to your repository:

.ai/GUIDELINES.md           # one agent-agnostic guidelines/rules document
.ai/mcp//config.json  # one file per MCP server (see MCP config below)
.ai/commands/**             # slash commands, synced verbatim per agent
.ai/skills/**               # skills, synced verbatim per agent

[!NOTE] The `.ai/GUIDELINES.md` holds the rules you want every agent to follow. `agenteq` writes a copy for each agent, in that agent's own format and location, for example `AGENTS.md` or `CLAUDE.md`.

Once the files are in place, run this.