Agent Plugins Marketplace
← All plugins

ratchet

v1.1.0

Ratchet — Goal-driven multi-agent persistent optimization system. Combines Goal-Driven master/subagent separation with AutoResearch signal design methodology. Implements an 'independent evaluation + kill-and-restart + ratchet progress' autonomous loop: master only judges, subagent only executes; if a subagent stalls or claims success without meeting acceptance criteria, it is killed and replaced. Suitable for long-running autonomous coding tasks that require verifiable deliverables and explicit termination conditions.

Claude Code1 Skill

By XRenSiuLicense: MIT2 GitHub starsUpdated 3 days ago

Directory evidence

Runtimes
Claude Code
Parsed components
1 skill or MCP entry
Source updated
Sep 21, 2026
Manifest status
Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install ratchet for Claude Code

Installs for the current user
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install ratchet@agent-plugin-marketplace

Paste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually
git clone https://github.com/XRenSiu/claude-code-forge

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is plugins/ratchet/.

Plugin files

plugins/ratchet/
├── .claude-plugin/plugin.json
└── skills/ratchet/SKILL.md

Included Skills1

ratchetskills/ratchet/SKILL.md

目标驱动的多智能体持久化优化系统。融合 Goal-Driven 的 master/subagent 分离架构 与 AutoResearch 的信号设计方法论,实现"独立评估 + 杀死重启 + 棘轮式进步"的 自主迭代循环。 当用户描述一个想要优化/改进/实现的目标时触发此 skill。 触发词包括但不限于：ratchet、棘轮优化、目标驱动、goal-driven、 "帮我持续优化 X 直到达标"、"我想让 X 达到 Y 标准"、 "帮我实现一个 X 并且要通过 Y 验证"、"自动跑到达标为止"。 也适用于：长时间自主编程任务、需要可验证产出的复杂工程任务、 任何需要 agent 持续迭代直到满足明确验收标准的场景。 即使用户只是模糊地说"我想把这个做好"或"帮我优化这个",也应触发此 skill。 与 autoresearch 的区别：ratchet 有独立评估者、自动杀死重启、明确的终止条件, 适合更大规模、更长时间的自主任务。autoresearch 更适合单文件的轻量迭代。

Plugin manifests1

plugins/ratchet/.claude-plugin/plugin.json
{
  "name": "ratchet",
  "description": "Ratchet — Goal-driven multi-agent persistent optimization system. Combines Goal-Driven master/subagent separation with AutoResearch signal design methodology. Implements an 'independent evaluation + kill-and-restart + ratchet progress' autonomous loop: master only judges, subagent only executes; if a subagent stalls or claims success without meeting acceptance criteria, it is killed and replaced. Suitable for long-running autonomous coding tasks that require verifiable deliverables and explicit termination conditions.",
  "version": "1.1.0",
  "author": {
    "name": "XRenSiu",
    "email": "[email protected]"
  },
  "homepage": "https://github.com/XRenSiu/claude-code-forge/tree/main/plugins/ratchet",
  "repository": "https://github.com/XRenSiu/claude-code-forge",
  "license": "MIT",
  "keywords": [
    "ratchet",
    "goal-driven",
    "autonomous-agent",
    "master-subagent",
    "independent-evaluation",
    "kill-and-restart",
    "acceptance-criteria",
    "autoresearch",
    "long-running-task",
    "verifiable-output"
  ]
}

For maintainers

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[ratchet on Agent Plugins Marketplace](https://pluginsmp.com/plugins/ratchet)