wtf.loop

Community

Autonomously run Epics/Features with human review

Authorxiduzo
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Orchestrates end-to-end execution of a fully specified Epic or Feature by chaining implement → verify → PR, enforcing dependency order and human-in-the-loop gates to prevent drift and ambiguities.

Core Features & Use Cases

  • Builds a unified dependency graph across Epics, Features, and Tasks, including external blockers, and plans execution in phases with conflict-aware sub-phases for parallel work.
  • Spawns and coordinates sub-agents to implement tasks, verify outcomes, and create PRs while surfacing unresolved questions for human input.
  • Enforces pre-conditions (e.g., designed labels, complete Gherkin contracts, non-empty acceptance criteria) before execution and ensures PRs are merged in sequence as gates progress.

Quick Start

Approve a target Epic or Feature and the proposed execution plan, then allow the loop to execute tasks in phases with human-in-the-loop gates.

Dependency Matrix

Required Modules

None required

Components

references

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: wtf.loop
Download link: https://github.com/xiduzo/wtf/archive/main.zip#wtf-loop

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.