Agentic development framework with mandatory gates and autonomous review loops
npx claudepluginhub mbstools/mbscodeUse after completing a milestone or group of related tasks, before proceeding to next phase
Use before any creative work - features, components, systems. Triggered by intent to build, NOT keyword matching. Trivial edits (under 3 steps, single file, no design decisions) are exempt.
Use when you have a written implementation plan to execute inline in the current session - for tightly coupled tasks that need shared context
Use when all implementation tasks are complete and verification passes
Use after every milestone, structural change, or new file creation
Use when executing implementation plans with multiple tasks - dispatches per task with dependency-aware parallel scheduling
Use when encountering any bug, test failure, or unexpected behavior - before proposing fixes
Use when writing tests for bug fixes, parsers, state machines, business logic, or high-risk code. Not universal - skip for trivial edits, config changes, and UI-only work.
Bootstrap skill — skill routing, gate enforcement, mandatory workflows
Use before claiming any work is complete, fixed, or passing - before committing, creating PRs, or moving to the next task
Use when you have an approved spec or requirements for a multi-step task, before touching any code
Use when creating or modifying skills - custom project skills or built-in mbscode skill overrides When to use -- trigger conditions that tell the agent to invoke this skill
Use after completing a milestone or group of related tasks, before proceeding to next phase
Use before any creative work - features, components, systems. Triggered by intent to build, NOT keyword matching. Trivial edits (under 3 steps, single file, no design decisions) are exempt.
Use when you have a written implementation plan to execute inline in the current session - for tightly coupled tasks that need shared context
Use when all implementation tasks are complete and verification passes
Use after every milestone, structural change, or new file creation
Use when executing implementation plans with multiple tasks - dispatches per task with dependency-aware parallel scheduling
Use when encountering any bug, test failure, or unexpected behavior - before proposing fixes
Use when writing tests for bug fixes, parsers, state machines, business logic, or high-risk code. Not universal - skip for trivial edits, config changes, and UI-only work.
Bootstrap skill — skill routing, gate enforcement, mandatory workflows
Use before claiming any work is complete, fixed, or passing - before committing, creating PRs, or moving to the next task
Use when you have an approved spec or requirements for a multi-step task, before touching any code
Use when creating or modifying skills - custom project skills or built-in mbscode skill overrides
AI-supervised issue tracker for coding workflows. Manage tasks, discover work, and maintain context with simple CLI commands.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Comprehensive toolkit for developing Claude Code plugins. Includes 7 expert skills covering hooks, MCP integration, commands, agents, and best practices. AI-assisted plugin creation and validation.
Orchestrate multi-agent teams for parallel code review, hypothesis-driven debugging, and coordinated feature development using Claude Code's Agent Teams
Context-Driven Development plugin that transforms Claude Code into a project management tool with structured workflow: Context → Spec & Plan → Implement
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.