Guide for making code reviews. Use this when asked to make code reviews, or ask to use it before committing changes.

AI coding agent that plans, implements, and verifies code changes with human approval gates. Built on FlatAgents.

Explains code with visual diagrams and analogies. Use when explaining how code works, teaching about a codebase, or when the user asks "how does this work?"

Code review expert for security, quality, and performance analysis. Use when reviewing code, PRs, conducting security audits, or identifying performance issues.

Expert in the human side of code review. Covers giving feedback that lands, receiving criticism gracefully, navigating disagreements, and building a healthy review culture. Understands that code...

Conducts comprehensive backend code reviews including API design (REST/GraphQL/gRPC), database patterns, authentication/authorization, caching strategies, message queues, microservices...

Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.

Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.

Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.

Use when receiving code review feedback, before implementing suggestions,

Async REPL Protocol

Git Commit Rules

Explicit Identity Across Boundaries

Quality control, citation validation, fact-checking before human review

Store a learning, pattern, or decision in the memory system for future recall

Check reference SDK implementations using btca ask

Get a token-efficient overview of any project using the TLDR stack

Analyze brownfield codebase and create initial continuity ledger

LLM Tuning Patterns

Parallel Agent Type Contracts