loop-eng

v0.20.0

Loop Engineering for Claude Code: /autoloop drives bounded tasks to completion via a builder/checker cycle with six stop rules; /polish iteratively raises code quality via multi-lens review, adversarial verification, and dry-round convergence. A Stop hook mechanically prevents quitting while a loop contract is unsatisfied, and a PreToolUse evidence gate ensures completion claims are machine-written, never typed.

Claude Code1 Skill

By sdsLicense: MIT2 GitHub starsUpdated 2 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 loop-eng 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 loop-eng@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/sdsrss/loop_eng

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

Plugin files

loop-eng/

├── .claude-plugin/plugin.json
└── skills/loop-eng/SKILL.md

Included Skills1

loop-engskills/loop-eng/SKILL.md

Closed-loop task execution and quality polishing for Claude Code. Use when the user wants a bounded task driven to completion hands-off — "keep iterating until tests pass", "don't stop until done", 自动循环/挂机/无人值守/跑到全绿 — via /autoloop (builder/checker rounds); wants code quality raised iteratively with every finding adversarially verified before fixing — 打磨/清理代码 — via /polish (review-verify-fix rounds); or asks how the loop-eng workflow works. Unlike prompt-only goal trackers, the Stop hook executes the contract's real verify commands and completion evidence is machine-written.

Plugin manifests1

.claude-plugin/plugin.json

{
  "name": "loop-eng",
  "version": "0.20.0",
  "description": "Loop Engineering for Claude Code: /autoloop drives bounded tasks to completion via a builder/checker cycle with six stop rules; /polish iteratively raises code quality via multi-lens review, adversarial verification, and dry-round convergence. A Stop hook mechanically prevents quitting while a loop contract is unsatisfied, and a PreToolUse evidence gate ensures completion claims are machine-written, never typed.",
  "author": {
    "name": "sds"
  },
  "license": "MIT",
  "homepage": "https://github.com/sdsrss/loop_eng",
  "repository": "https://github.com/sdsrss/loop_eng",
  "keywords": [
    "claude-code",
    "loop-engineering",
    "automation",
    "code-quality"
  ]
}