brutal-agent
CommunityAutomate end-to-end subsystem hardening.
System Documentation
What problem does it solve?
Orchestrate automated subsystem hardening by combining brutal-project-review and task-worker in a strict loop: review one subsystem, create CRITICAL/MAJOR tasks, run all tasks to completion, then move to the next subsystem. Continue full review/task passes until a complete pass finds no new CRITICAL/MAJOR issues. Use when the user wants both deep subsystem review and autonomous task execution with no instruction loss.
Core Features & Use Cases
- End-to-end orchestration: review a subsystem, generate CRITICAL/MAJOR tasks, run all tasks to completion, and move to the next subsystem.
- Deterministic pass-based execution: perform complete passes until no new critical issues emerge, with explicit state updates and cleanup.
- Use Case: large-scale software projects requiring automated hardening and reproducible workflows across multiple subsystems.
Quick Start
Load the two source SKILL.md files and start the first subsystem review, letting the task-worker loop drive execution.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 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: brutal-agent Download link: https://github.com/sssemil/SKILLS/archive/main.zip#brutal-agent Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.