By jonnycbb
Complete feature development workflow: /interview for requirements gathering, /research-problem for codebase research, /map-feature-to-plans and /break-down-initiative for feature splitting, /create-plan-tdd and /implement-plan-tdd for test-driven planning and execution, /code-review for multi-agent review, /verify-implementation for evidence generation, /commit and /pr-description for git workflows.
Non-interactive code tidy-up with autonomous decision-making and formatting
This pattern ensures that when a command declares it will spawn certain agents based on domain detection, those agents are actually spawned, and any deviations are communicated to the user.
This registry maps programming languages to their corresponding reviewer agents. Commands use this to dynamically select language-appropriate agents for code review and simplification.
Advisory guidance for choosing sub-agent models. This guide respects the user's default
Comprehensive code tidy-up with tests, simplification, and formatting
Specialist bug detection agent for code review. Focuses exclusively on finding real bugs — logic errors, runtime failures, resource leaks, race conditions. Zero false-positive philosophy. Use as part of the /code-review pipeline.
Explore codebases and find implementation details. Use for (1) finding WHERE code lives (file paths, directory structure), (2) finding HOW code works (data flow, architecture, entry points), or (3) finding WHAT patterns exist (code examples and implementations to model after). Works on local files (fastest) or external repos via gh repo clone fallback. Adapts depth based on what is asked — specify "where", "how", or "show me examples" in your prompt.
Holistic code review agent focusing on objective alignment, design, error handling, API compatibility, dependencies, and documentation. Bugs and security are handled by specialist agents (bug-catcher, security-reviewer). Use as part of the /code-review pipeline or standalone for general review.
Use this agent when you need to analyze and review Python code for simplification opportunities and best practices. Examples: <example>Context: User has written a complex Python function with nested loops and wants recommendations for simplification. user: 'I just wrote this function but it's getting complex with all these nested loops. Can you review it and suggest improvements?' assistant: 'I'll use the python-code-simplification-reviewer agent to analyze this code and provide detailed recommendations for better readability and Pythonic style.' <commentary>The user wants code review and recommendations, so use the python-code-simplification-reviewer agent to analyze and suggest improvements.</commentary></example> <example>Context: User has completed a feature implementation and wants a code quality review before committing. user: 'I've finished implementing the data processing module. Can you review the code and tell me what could be improved?' assistant: 'Let me use the python-code-simplification-reviewer agent to review your code and provide specific recommendations according to Python best practices and conventions.' <commentary>The user wants a code quality review, so use the python-code-simplification-reviewer agent to analyze and provide improvement suggestions.</commentary></example>
Use this agent when you need to analyze Python code and review test coverage to identify missing tests and redundant tests. Examples: <example>Context: User has written a new Python module and wants to know what tests are needed. user: 'I just wrote a data processing module with functions for parsing and transforming data. What tests should I write for it?' assistant: 'I'll use the python-test-reviewer agent to analyze your module and provide detailed test recommendations.' <commentary>Since the user needs test coverage analysis, use the python-test-reviewer agent to analyze the code and recommend appropriate tests following pytest best practices.</commentary></example> <example>Context: User has modified existing Python code and wants to ensure test coverage is adequate. user: 'I updated the API client to handle retry scenarios better. Can you review what tests are missing or redundant?' assistant: 'Let me use the python-test-reviewer agent to analyze your changes and provide test coverage recommendations.' <commentary>The user needs test coverage analysis, so use the python-test-reviewer agent to review and recommend test changes.</commentary></example>
Decompose a PRD, RFC, epic, or high-level initiative into independently-executable feature outlines using vertical slices. Each feature gets its own research pipeline run. Use when the input is too large or too high-level for a single research/plan cycle. Trigger phrases (1) "break down initiative" (2) "break down epic" (3) "split into features" (4) "break down PRD" (5) "PRD to features" (6) "break this down". Outputs to ~/.claude/thoughts/shared/decomposition/.
Comprehensive code review with internalized bug detection (bug-catcher), OWASP security analysis (security-reviewer), code simplification (language reviewers), test quality (test reviewers), holistic review (general-code-reviewer), domain expertise (domain agents), and a post-review pipeline (review-calibrator, review-deduplicator). Replaces /pr-review.
Common code simplification patterns shared across languages (Java, Scala, Python). Covers naming conventions, structural patterns (DRY, SOLID), and comment quality. Use alongside language-specific simplification skills.
Create structured git commits with co-authorship attribution. Use when the user asks to commit changes or says "/commit".
Create TDD-aware implementation plans with wave-based parallelism and multi-persona review. Follows Red-Green-Refactor methodology per task, groups tasks into dependency-based waves for parallel execution, and validates plans through 4 specialized reviewer personas before finalization. Trigger phrases (1) "create a TDD plan" (2) "plan with tests first" (3) "create-plan-tdd" (4) "TDD implementation plan" (5) "test-driven plan". Use when the user wants a plan that enforces test-first development, needs wave-based parallelization of implementation tasks, or wants built-in plan review by specialized personas.
Uses power tools
Uses Bash, Write, or Edit tools
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.
A directory with my Claude Code setup - agents, commands, skills.
Follow the README for instructions on how to use these for your own use cases and hopefully be inspired by what's possible.
Important Note: The agents and commands are constantly evolving. I'll try to keep this README up-to-date but hopefully the content can be useful in inspiring others to leverage some more advanced features of Claude Code.
This repo also serves as a Claude Code plugin marketplace. You can install plugins directly from this repo.
| If you want to... | Install |
|---|---|
| Build features with AI-guided TDD workflow | jbb-feature-dev |
| Investigate incidents or document architecture | eng-utils |
| Create interactive explainers or presentations | jiffy-toolkit |
| All of the above | Install all three -- they work independently |
| Plugin | When to use it | Description | Examples |
|---|---|---|---|
| jbb-feature-dev | You're building a feature from scratch | End-to-end development workflow: from requirements gathering and codebase research through TDD planning, parallel implementation, code review, and delivery. | /interview -> /create-plan-tdd -> /implement-plan-tdd -> /code-review |
| eng-utils | Something is broken in production or you need to understand a system | Incident triage and root cause investigation, architecture documentation with C4 diagrams, and service diagnostics (pods, logs, alerts, callgraphs, edge config). | /incident-investigation, /system-architecture-doc |
| jiffy-toolkit | You need to explain or present something | Turn concepts into polished interactive pages, slide decks, and standards-compliant documentation. | /teach-me, /frontend-slides |
| Plugin | Skills | Agents | Commands | Size |
|---|---|---|---|---|
| jbb-feature-dev | 17 | 13 | 2 | Comprehensive |
| eng-utils | 3 | 1 | 0 | Focused |
| jiffy-toolkit | 5 | 5 | 0 | Lightweight |
From within Claude Code:
/plugin marketplace add https://github.com/JonnyCBB/claude-code-config.git
Or from the terminal:
claude plugin marketplace add https://github.com/JonnyCBB/claude-code-config.git
/plugin install jbb-feature-dev@jbb-claude-code-plugins
/plugin install eng-utils@jbb-claude-code-plugins
/plugin install jiffy-toolkit@jbb-claude-code-plugins
Add to any project's .claude/settings.json to prompt users to install automatically:
{
"extraKnownMarketplaces": {
"jbb-claude-code-plugins": {
"source": {
"source": "git",
"url": "https://github.com/JonnyCBB/claude-code-config.git"
}
}
}
}
Required for all plugins:
gh CLI tool for GitHub workflowsnpx claudepluginhub jonnycbb/claude-code-config --plugin jbb-feature-devEngineering utilities: /assess-incident for severity classification, /incident-investigation for root cause analysis across backend/data/indexing domains, /refactor-architecture for codebase friction analysis and proposals, /system-architecture-doc for C4 architecture documentation, plus service diagnostics and operational skills.
Creative and standards tools: /teach-me for interactive scrollytelling explanations, /frontend-slides for HTML presentations, plus editorial, diagram, and skills-authoring standards with companion review agents.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
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.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
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.
Complete developer toolkit for Claude Code