AI-powered development workflows with TDD enforcement, planning, and quality tracking
Adversarial 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.
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.
Admin access level
Server config contains admin-level keywords
Executes bash commands
Hook triggers when Bash tool is used
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
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
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.
npx claudepluginhub magic-ingredients/tiny-brain-releases --plugin tiny-brainPersona-driven AI development team: orchestrator, team agents, review agents, skills, slash commands, and advisory hooks for Claude Code
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
Helder's personal SDLC toolbelt for AI coding agents — from PRD to ship. Bundles the tracer-bullet workflow alongside TDD, code review, audits, and shipping skills.
Plugin for effective agentic development
Code transformation: Dev SDLC orchestrator (code-shipping pipeline), plan, assert, audit, review, test, refactor, debug, for-sure. Hosts engineering agents.
PLAN/ACT/EVAL workflow with auto-detection, specialist agents, and reusable skills for systematic TDD development