A workflow add-on that turns unclear work into defined targets, checks the result critically, applies fixes, and saves progress for later.

It helps lock requirements, validate outputs, patch problems, serialize state, and run a limited improvement loop.

It provides a repeatable way to move from an ambiguous request to a reviewed deliverable without losing the work state.

ratchet — Plugin for Claude Code by Megaprompting/torque-loop

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo

git clone --depth 1 https://github.com/Megaprompting/torque-loop

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/megaprompting/torque-loop/torque-loop/github.svg)](https://agentmods.dev/plugins/megaprompting/torque-loop/torque-loop)

Your own site

<a href="https://agentmods.dev/plugins/megaprompting/torque-loop/torque-loop"><img src="https://agentmods.dev/badge/plugins/megaprompting/torque-loop/torque-loop/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/plugins/megaprompting/torque-loop/torque-loop"><img src="https://agentmods.dev/badge/plugins/megaprompting/torque-loop/torque-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured The manifest loads nothing itself; its 23 skills, 3 agents, 3 hooks cost 1,956 tokens a session between them.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

ratchet scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude-plugin/plugin.json · 31 lines

What it actually says

{
  "name": "ratchet",
  "displayName": "Torque Loop",
  "version": "1.0.0",
  "description": "Torque Loop turns ambiguous work into shipped artifacts through target locking, adversarial validation, patching, and state serialization — plus a bounded /ratchet:evolve loop. A stateful advancement engine, not a prompt library. Not affiliated with Anthropic.",
  "author": {
    "name": "Danny Gillespie"
  },
  "homepage": "https://github.com/Megaprompting/torque-loop",
  "license": "MIT",
  "keywords": [
    "workflow",
    "quality",
    "validation",
    "prompts",
    "state",
    "qa",
    "decision"
  ],
  "mcpServers": {
    "torque": {
      "command": "node",
      "args": [
        "${CLAUDE_PLUGIN_ROOT}/bin/ratchet-mcp",
        "--root",
        "${CLAUDE_PROJECT_DIR}"
      ]
    }
  }
}

Contents

What it installs

The manifest is a name and a version. 23 skills, 3 agents, 3 hooks travel with it, and installing the plugin installs all of them — 1,956 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Files

What ships with it

1 file beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

marketplace.json 637 B

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

1mo ago First seen · 31 lines scan A 4db599f95d82

Subscribe to this mod's changes

ratchet is a plugin published in the GitHub repository Megaprompting/torque-loop (9 stars, last pushed 2mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Planning ai-agents ai-tools harness-engineering

ctx

Token-budgeted code intelligence, architecture rules, duplication detection, and deterministic quality gates for AI-assisted development.

agentis-tools/ctx · not measured

clipboard-mcp-server

Read, write, and inspect the system clipboard across macOS, Linux (X11/Wayland), and Windows via MCP. STDIO or Streamable HTTP.

cyanheads/clipboard-mcp-server · not measured

macos-permissions

Audit and control what software on a Mac can see, drive and outlive a reboot. TCC privacy grants across all 40 services and all three permission stores (system, user, and the Sequoia screen-capture plist tccutil cannot reach), including grants stranded by uninstalled apps that macOS never garbage-collects. Plus full p.

terrylica/cc-skills · not measured

rad-a11y

WCAG 2.2 AA accessibility toolkit for Claude Code. Six skills covering semantic HTML, ARIA patterns, keyboard/focus, forms, automated testing setup, and a static-analysis review pass; one autonomous reviewer agent. Four pure-stdlib Python validators (scan-jsx-patterns, check-tailwind-contrast with real WCAG sRGB ma.

RadOrigin-LLC/RAD-Claude-Skills · not measured

pict-test-designer

Design comprehensive test cases using PICT (Pairwise Independent Combinatorial Testing) for any piece of requirements or code. Analyzes inputs, generates PICT models with parameters, values, and constraints for valid scenarios using pairwise testing. Outputs the PICT model, markdown table of test cases, and expected…

eric861129/SKILLS_All-in-one · not measured

mosaic-bridge

Mosaic Bridge — Unity MCP assistant agents for scene building, shader creation, and session continuity.

MosaicXR-AI/mosaic-bridge · not measured