Signature Brutus — Development agent for Claude Code
Adversarial reviewer.
How to install Signature Brutus
Installs to ~/.claude/agents/choppaaahh-cognitive-signature-ide-signature-brutus.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/Choppaaahh/cognitive-signature-ide/HEAD/agents/signature-brutus.md -o ~/.claude/agents/choppaaahh-cognitive-signature-ide-signature-brutus.md Restart Claude Code, or start a new session, for it to be picked up.
What Signature Brutus does
name: brutus description: Adversarial reviewer. Assumes the builder is wrong until proven right. Ships with CogSig for signature governance + available as a general-purpose specialist for any code, decision, or claim you want stress-tested before you act on it. model: opus color: red
Brutus — Adversarial Reviewer
You are Brutus. Your default stance: **assume whatever you're reviewing is wrong** until the evidence proves otherwise. Your value comes from catching what the author missed
Alternatives in Development
- Refactorer Agent — You are a refactoring expert who improves code structure without changing external behavior 1.3k ★
- TDD Refactoring Agent — Improves code structure while keeping all tests green during the TDD REFACTOR phase using proven refactoring p 652 ★
- Lex Legal — Use this agent when dealing with legal and compliance activities 523 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Signature Historian
Drift / change / evolution tracker. Ships with CogSig for signature-drift detection across sessions + availabl
Skeptical Reviewer
Performs adversarial review of PR changes, actively looking for bugs, edge cases, race conditions, and failure
Reviewer2
Adversarial scientific reviewer (Reviewer 2). Spawned as subagent to DESTROY weak claims. Assumes every claim
Partition Adversary
Adversarial auditor for a proposed partition — of ideas, backlog phases, plan boundaries or any other set some
Eve
Doubt-lens reviewer (Fable). Skeptical final pass plus de-slop; assumes the work is subtly wrong.
Boualam
Handles routine code quality tasks (linting, formatting, type checking) and trivial busywork. Runs iteratively
Related Skills
List All Tools
List all available tools detailed in your system prompt. Display them in bullet points. Display them in typesc
Bearing
An intel layer for AI coding agents that assumes its own rules might be wrong — and keeps the evidence. Author
Simulation Commands
Commands for initiating, configuring, and reviewing board simulation sessions -- adversarial role-play rehears