Plugin · Claude Code · AI Agents

Tmdgusya Roach Loop

tmdgusya-roach-loop is a Claude Code plugin for the Build phase that provides iteration-controlled continuous agent loops with planning, verification, and git-workflow automation.

by tmdgusya · github.com/tmdgusya/roach-loop

Run controlled continuous agent loops—with iteration limits, implementation plans, verification, and git workflow—so Claude Code does not stall or over-run autonomous tasks.

0
GitHub stars
0
Installs
0
Community votes
One vote per signed-in builder - it helps surface the tools the community actually relies on.
Install

Add it to Claude Code

Install the plugin in Claude Code. One command, paste-ready.

Install the plugin
/plugin install tmdgusya-roach-loop@tmdgusya/roach-loop
Add to ClaudeUse the Agent APISkillselion is itself an MCP server - your agent can fetch this config directly.
Agent API

Built to be called by your agent

Skillselion is itself an MCP server. Your agent can pull this entry and a paste-ready install config straight from the API - no copy-paste.

Retrieve this entry with skillselion.get_details("plugin:tmdgusya/roach-loop") and the paste-ready config with skillselion.get_install_config("plugin:tmdgusya/roach-loop").

About

What it does

tmdgusya-roach-loop is a one-plugin Claude Code bundle from tmdgusya/roach-loop aimed at solo builders who delegate multi-step implementation to an agent but need guardrails. Catalog keywords describe continuous execution, iteration control, planning, verification, git workflow, and Ralph-adjacent task-runner behavior—typical of loop plugins that read a plan file, execute, check results, and repeat until limits or success criteria are met. Use it when autonomous coding sessions otherwise wander, skip verification, or never terminate. It complements normal planning skills by focusing on how runs are chained and bounded, not on choosing product features. You still own repository safety, CI, and human review before production deploys.

Highlights

  • Continuous agent loop with explicit iteration limits and control
  • Implementation-plan and verification-oriented workflow (implementationplanmd)
  • Git-workflow aware autonomous execution patterns
  • Ralph-style task-runner keywords for long-running agent sessions
  • Single-plugin bundle: tmdgusya/roach-loop

Why builders use it

Unbounded agent loops waste tokens, skip verification, and make solo builders nervous about autonomous git changes.

After install, Claude Code can follow roach-loop style execution with explicit limits, implementation plans, and verification between iterations.

At a glance

  • Type - Plugin in AI Agents.
  • Adoption - 0 installs, 0 stars, 0 votes.

FAQ

Who is tmdgusya-roach-loop for?

It is for Claude Code users who run multi-iteration agent workflows and need continuous execution with limits, verification, and git-aware control.

When should I use tmdgusya-roach-loop?

Use it when you have an implementation plan or task list and want the agent to loop through build and verify steps until completion or iteration caps.

How do I add tmdgusya-roach-loop to my agent?

Install the tmdgusya/roach-loop plugin in Claude Code, prepare your plan or implementationplanmd-style artifact, then start a session configured for the roach-loop workflow.

Discussion

Comments

Share how you use tmdgusya-roach-loop, gotchas, or tips for other indie builders.

No comments yet - be the first to share how you use it.

This week for builders

Five minutes, every Monday — the tools, releases and tactics for shipping solo.

unsubscribe anytime.