AI-powered development workflows with TDD enforcement, planning, and quality tracking
npx claudepluginhub magic-ingredients/tiny-brain-releases --plugin tiny-brainAdversarial code reviewer that challenges TDD red/green work from an isolated context. Returns structured refactoring suggestions.
Runs CLI analyzers (ESLint, TypeScript, npm audit, etc.) and normalizes output. Use when orchestrating automated quality analysis.
System design and architecture specialist. Use for designing system architecture, making technical decisions, creating ADRs, and evaluating trade-offs.
Code review and quality feedback specialist. Use for reviewing code changes, identifying issues, and suggesting improvements.
General development agent for phased TDD workflows. Use for implementing features, fixing bugs, and writing code with test-first approach.
Performance optimization and efficiency specialist. Use for performance analysis, bottleneck identification, optimization strategies, and efficiency improvements.
Performance optimization and efficiency specialist. Use for performance analysis, bottleneck identification, optimization strategies, and efficiency improvements.
PRD and feature planning specialist. Use for creating Product Requirements Documents, breaking down initiatives into features, and defining implementation tasks.
Orchestrates comprehensive code quality analysis using specialist agents. Aggregates findings, calculates weighted scores, and persists results. Use for full repository quality assessments.
Code review and quality feedback specialist. Use for reviewing code changes, identifying issues, and suggesting improvements. Read-only - does not modify code.
Security analysis and vulnerability detection specialist. Use for security reviews, vulnerability assessment, and secure coding guidance.
Security analysis and vulnerability detection specialist. Use for security reviews, vulnerability assessment, and secure coding guidance. Read-only analysis.
TDD compliance validator and enforcement agent. Use for validating test-driven development practices, checking commit patterns, and ensuring TDD workflow compliance.
TDD compliance validator and flaky test detector. Use for validating test-driven development practices, checking commit patterns, detecting flaky test patterns, and ensuring TDD workflow compliance.
Create an Architecture Decision Record. Use when making significant architectural or technical decisions that should be documented.
Add a feature to an existing PRD. Use when user wants to add functionality to an existing product plan.
Create a fix document for bug tracking. Use when user reports a bug or wants to track a fix with full test plan.
Create a new PRD (Product Requirements Document). Use when user wants to plan a new feature, product, or initiative.
Run comprehensive code quality analysis on the repository. Performs weighted scoring across 8 categories using automated analyzers and 4 specialist investigation agents.
Stop vibe coding. Start shipping.
Your AI writes code fast. tiny-brain makes sure it actually works — tested, tracked, and ready to deploy.
tiny-brain is a Claude Code plugin that makes your codebase AI-ready. It analyses your code, sets up guardrails, and gives AI agents the context they need to write code you'd actually approve in a PR.
AI coding is fast. Until it isn't. You ship a feature in 20 minutes, then spend 2 hours fixing what it broke. No tests, no specs, no audit trail — just you cleaning up after AI.
One command analyses your codebase — languages, frameworks, test setup, project structure — and makes it all navigable for AI. Agents stop guessing and start working with your code.
npx tiny-brain analyse
Every task flows through a full pipeline, visible in real time on your local dashboard.
Per commit: 🔴 Red → 🟢 Green → 😈 Adversarial review
Per push: 🧟 Mutation testing → 📦 Dependency analysis
Every task records its test SHA, implementation SHA, review verdict, and refactor SHA. You can trace any line of code back to the task that created it.
AI that already knows your stack. No more re-explaining your conventions and preferences — personas load full context so you go straight to building.
Score your codebase across 8 categories. Know exactly where you stand before adding AI — because adding AI to a poor quality codebase just makes things worse.
# In Claude Code
/plugin marketplace add https://github.com/magic-ingredients/tiny-brain-releases
/plugin install tiny-brain@tiny-brain-marketplace
# In your terminal
npx tiny-brain analyse
# Back in Claude Code
as developer
/plan "add user authentication"
Dashboard available at localhost:8765
/plan, /feature, /fix, /adr, /quality)Built by magic ingredients. Free and open source.
Persona-driven AI development team: orchestrator, team agents, review agents, skills, slash commands, and advisory hooks for Claude Code
Admin access level
Server config contains admin-level keywords
Executes bash commands
Hook triggers when Bash tool is used
Share bugs, ideas, or general feedback.
SDLC enforcement for AI agents — TDD, planning, self-review, CI shepherd
AI-powered development workflow automation - Phase-based planning, implementation orchestration, preflight code quality checks with security scanning, ship-it workflow, and development principles generator for CLAUDE.md
Plugin for effective agentic development
AI-powered development workflow with planning, implementation, and review commands
23 agent skills for systematic software development. Covers design, planning, TDD, code review, debugging, quality gates, and adversarial testing. Every skill is eval-tested with measured A/B deltas using Anthropic's skill evaluation framework.
Modifies files
Hook triggers on file write and edit operations
Modifies files
Hook triggers on file write and edit operations
Uses power tools
Uses Bash, Write, or Edit tools
Uses power tools
Uses Bash, Write, or Edit tools
Share bugs, ideas, or general feedback.