garbage-collection

Official

Fight entropy and keep your codebase healthy

AuthorHabitat-Thinking
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Garbage collection rules detect and mitigate repository entropy — stale documentation, dead code, convention drift, dependency rot, and harness degradation — so issues do not accumulate between active development gates and CI checks.

Core Features & Use Cases

  • Rule anatomy and catalogue: Each GC rule specifies what it checks, frequency, enforcement mode, execution tool, and whether auto-fix is safe, supported by a comprehensive reference catalogue.
  • Deterministic and agent enforcement: Schedule deterministic tools or agents to run daily or weekly to apply safe auto-fixes or create GitHub issues for human review.
  • Learning-driven checks: Leverage reflections and assessment artifacts to detect recurring failure patterns and propose new constraints or fitness functions to evolve the harness.
  • Use case: Run a weekly harness-gc agent that formats code, flags orphaned files, detects stale references, reports vulnerable dependencies, and suggests or applies safe fixes per the auto-fix rubric.

Quick Start

Run the garbage-collection agent to scan the repository for stale documentation, dead code, convention drift, and dependency issues, applying safe auto-fixes where deterministic and creating issues when human judgment is required.

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: garbage-collection
Download link: https://github.com/Habitat-Thinking/ai-literacy-superpowers/archive/main.zip#garbage-collection

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.