Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
npx claudepluginhub aaronbassett/agent-foundry --plugin devsUse this agent when you need to explore, search, or understand a codebase. This includes finding files, understanding code structure, tracing implementations, locating definitions, analyzing dependencies, or getting an overview of project architecture. Examples: <example> Context: User wants to understand how a feature is implemented user: "How does the batch auction clearing price calculation work?" assistant: "I'll use the codebase-navigator agent to trace through the implementation and find all relevant code." <commentary> Since the user wants to understand an implementation, use the codebase-navigator agent to search for relevant files, trace function calls, and build a comprehensive picture of how the feature works. </commentary> </example> <example> Context: User needs to find where something is defined user: "Where is the ExecutionWorker struct defined and what does it do?" assistant: "Let me use the codebase-navigator agent to locate the definition and analyze its purpose." <commentary> The user is looking for a specific definition. Use the codebase-navigator agent to quickly locate the struct and understand its role in the codebase. </commentary> </example> <example> Context: User wants to understand project structure user: "Give me an overview of the node/src directory structure" assistant: "I'll use the codebase-navigator agent to explore the directory and summarize its organization." <commentary> For understanding project structure and organization, the codebase-navigator agent can efficiently traverse directories and provide a clear overview. </commentary> </example> <example> Context: User needs to find all usages of a function or type user: "Find all places where EOAccountInfo is used" assistant: "I'll launch the codebase-navigator agent to search for all references to EOAccountInfo across the codebase." <commentary> Searching for usages across a codebase is a core use case for the codebase-navigator agent, which can use multiple search strategies in parallel. </commentary> </example> <example> Context: User wants to understand data flow user: "Trace the transaction lifecycle from RPC submission to execution" assistant: "I'll use the codebase-navigator agent to trace through the code and map out the complete transaction flow." <commentary> Tracing data flow through a system requires reading multiple files and following function calls. The codebase-navigator agent excels at this kind of deep exploration. </commentary> </example>
Use this agent when you need a thorough code review after writing or modifying code. Examples:\n\n<example>\nContext: The user has just implemented a new feature with multiple files changed.\nuser: "I've finished implementing the user authentication feature. Here are the changes:"\n<code changes shown>\nassistant: "Let me use the Task tool to launch the senior-code-reviewer agent to provide a comprehensive review of these changes."\n<commentary>\nSince significant code was written, use the senior-code-reviewer agent to perform a thorough code review.\n</commentary>\n</example>\n\n<example>\nContext: The user has refactored a complex module.\nuser: "I've refactored the payment processing module to improve performance."\nassistant: "I'll use the Task tool to launch the senior-code-reviewer agent to review the refactoring for correctness, performance improvements, and potential issues."\n<commentary>\nRefactoring requires careful review to ensure functionality is preserved and improvements are realized.\n</commentary>\n</example>\n\n<example>\nContext: The user has fixed a bug.\nuser: "Fixed the race condition in the event handler"\nassistant: "Let me use the Task tool to launch the senior-code-reviewer agent to verify the fix addresses the root cause and doesn't introduce new issues."\n<commentary>\nBug fixes should be reviewed to ensure they properly address the issue without side effects.\n</commentary>\n</example>
Use this agent when you need to manage project dependencies across TypeScript, Rust, or Python ecosystems. This includes auditing installed packages, checking for outdated dependencies, scanning for security vulnerabilities, finding release notes, preparing upgrade reports with breaking change analysis, inspecting transient dependencies in lock files, installing or uninstalling packages, clearing package caches, and managing monorepo workspace dependencies. Examples: - User: 'Check if any of my dependencies have security vulnerabilities' Assistant: 'Let me use the deps-maintenance agent to run a security audit across your project dependencies.' - User: 'I need to upgrade React to v19, what will break?' Assistant: 'I\'ll use the deps-maintenance agent to prepare an upgrade report for React 19 including breaking changes and migration steps.' - User: 'What outdated packages do I have?' Assistant: 'Let me use the deps-maintenance agent to check all your dependencies for available updates.' - User: 'Why is this package in my node_modules?' Assistant: 'I\'ll use the deps-maintenance agent to trace the dependency chain and find out what requires it.'
Use this agent when you need expert assistance with Python programming tasks, including writing new Python code, refactoring existing code, debugging Python applications, implementing Python-specific design patterns, optimizing Python performance, or answering questions about Python best practices and language features.\n\nExamples:\n\n<example>\nContext: The user needs to write a function to process data from a CSV file.\nuser: "I need to write a function that reads a CSV file and returns the average of values in the 'price' column"\nassistant: "I'm going to use the Task tool to launch the python-expert agent to create this data processing function."\n<commentary>\nSince this requires Python-specific expertise including proper CSV handling, error handling, and Pythonic code patterns, use the python-expert agent.\n</commentary>\n</example>\n\n<example>\nContext: The user has written a Python class and wants it reviewed for best practices.\nuser: "Here's my User class implementation. Can you review it?"\nassistant: "I'm going to use the Task tool to launch the python-expert agent to review this code for Python best practices and potential improvements."\n<commentary>\nSince this involves evaluating Python code against Python-specific conventions, design patterns, and best practices, use the python-expert agent.\n</commentary>\n</example>\n\n<example>\nContext: The user is experiencing a performance issue with their Python script.\nuser: "My script is running very slowly when processing large lists"\nassistant: "I'm going to use the Task tool to launch the python-expert agent to analyze the performance issue and suggest optimizations."\n<commentary>\nSince this requires Python-specific performance analysis and knowledge of Python's optimization techniques, use the python-expert agent.\n</commentary>\n</example>
Use this agent when you need to build, refactor, or debug React components and applications. This includes creating new components, implementing state management, optimizing performance, handling hooks, working with React Router, integrating with APIs, or solving React-specific architectural challenges.\n\nExamples:\n- <example>\nuser: "I need to create a reusable dropdown component with keyboard navigation support"\nassistant: "I'm going to use the Task tool to launch the react-dev agent to create this component with proper accessibility features."\n</example>\n\n- <example>\nuser: "My React app is re-rendering too often and causing performance issues"\nassistant: "Let me use the Task tool to launch the react-dev agent to analyze and optimize the rendering performance."\n</example>\n\n- <example>\nuser: "Can you help me implement a custom hook for managing form state?"\nassistant: "I'll use the Task tool to launch the react-dev agent to create a well-structured custom hook following React best practices."\n</example>\n\n- <example>\nuser: "I'm getting an error about 'Cannot read property of undefined' in my component"\nassistant: "I'm going to use the Task tool to launch the react-dev agent to debug this issue and implement proper error handling."\n</example>
Comprehensive code review guidance for quality, performance, and architecture across all programming languages. Use when (1) User explicitly requests code review, (2) After writing significant code changes, (3) Before commits/PRs, (4) Reviewing existing codebases, (5) Analyzing code quality, (6) Detecting performance issues, (7) Identifying architectural problems, (8) Finding code smells. Provides automated analysis scripts and manual review checklists for thorough code evaluation.
Comprehensive dependency management expertise covering TypeScript (npm, yarn, pnpm, bun), Rust (cargo), and Python (pip, poetry, uv). Use when working on projects requiring: (1) Dependency auditing and listing, (2) Checking for outdated packages, (3) Security vulnerability scanning, (4) Finding release notes and changelogs, (5) Preparing upgrade reports with breaking change analysis, (6) Inspecting transient dependencies in lock files, (7) Installing or uninstalling packages, (8) Clearing package caches, (9) Monorepo workspace dependency management, or (10) Cross-ecosystem dependency health checks.
Comprehensive Python development expertise covering modern best practices, type hints, FastAPI web development, async/await, testing, and performance optimization. Use when working on Python projects requiring guidance on: (1) Modern Python features and best practices, (2) Type hints and static typing with mypy, (3) FastAPI web development, (4) Async/await and asyncio patterns, (5) Testing with pytest, (6) Data validation with Pydantic, (7) Database integration (SQLAlchemy), (8) Project structure and dependencies, (9) Performance optimization, (10) Logging and observability, or (11) Code reviews and common errors.
Create and review React components following strict TypeScript patterns, container/presenter architecture, and composition-first design. Use when asked to: (1) Create a React component, (2) Review a React component, (3) Build UI features, (4) Implement forms, (5) Add data fetching with TanStack Query. Enforces KISS/YAGNI principles, headless component patterns, Tailwind v4 styling, and Web3 security best practices.
Comprehensive React application development guidance covering project architecture, state management, performance optimization, security, and modern best practices including React 19 features. Use when (1) Working in React codebases (.jsx/.tsx files), (2) Architecting React applications (project structure, state management strategies), (3) Optimizing React performance (code splitting, memoization, virtualization), (4) Implementing security best practices (auth, XSS prevention, CSRF protection), (5) Applying React 19 features (Server Components, Actions, new hooks), (6) Setting up build configurations and tooling. Automatically triggered when working with React projects or addressing React-specific architecture, performance, or security concerns.
Uses power tools
Uses Bash, Write, or Edit tools
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Essential Claude Code extensions: core agents, hooks, commands, and universal tools
Custom commands, skills, agents, rules, hooks, and output styles for Claude Code - session continuity and modern CLI tooling for real-world development workflows
Expert agents for specific programming languages (Python, Go, Rust, etc.)
Complete developer toolkit for Claude Code
React/TypeScript frontend + Go backend enforcement harness. 92 wired hooks across 101 scripts enforce patterns on every edit. Green != done: `test-warning-check` surfaces warnings on passing test/lint/type runs (DeprecationWarning, React `act()`, unhandled rejection, `@ts-ignore`); `ci-warning-audit` Stop-hook scans `gh run view --log` on green CI for deprecations / console warnings / skipped tests. 66 skills from TDD through CI-green PR, including /steelman anti-sycophancy guard + /snyk-ux-security per-path vuln sweep (JS + Go ecosystems; exploitability-triage first gate via `bun why`/`go mod why`/`govulncheck`; top-level direct dep bump first, parent dep bump second, resolutions/overrides/replace as last resort only with follow-up TODO to remove; React 18 pin + changelog-walked major bumps + no-deferral escalation; Go `snyk test --file=go.mod` + `go get -u` + `go mod tidy` + `govulncheck` verify). Session exit blocked while PR review threads remain unresolved. TypeScript escape hatches blocked at Edit. tsconfig strictness weakening blocked. Worktree isolation + branch safety hook-enforced. bun.lock + yarn.lock parity enforced (Snyk IO doesn't parse bun.lock). 21 LLM failure modes enforced: 7 Karpathy single-agent + 14 MAST multi-agent (Cemri et al. NeurIPS 2025). OWASP + STRIDE subset + snyk/bun audit. Core Web Vitals perf gate. MCP ban with CLI redirect (~20x token savings). Agent-browser wrap (~91% token reduction for AI browsing). 3-hat plan review (product/engineering/design). 9 agents (adds plan hats + karpathy reference), 5 routines. Opus 4.7 tuned, POSIX-friendly.
Universal Claude Code workflow with specialized agents, skills, hooks, and output styles for any software project. Includes orchestrator, code-reviewer, debugger, docs-writer, security-auditor, refactorer, and test-architect agents.
Explore, develop, and refine ideas through creative collaboration — from open-ended riffing to structured ideation to ruthless refinement — before any design or implementation work begins.
AI-powered image generation using Google Gemini models via the nanobanana MCP server. Generate, edit, and manage images with intelligent model selection, aspect ratio control, and multi-model support.
Create isolated Docker-based development environments for running Claude Code safely
Guide users through creating complete, unambiguous feature specifications using a discovery-driven process.
Configuration toolkit for streamlining Claude Code project setup with powerline status line and attribution settings
Build. Ship. Repeat. A collection of Claude Code plugins for devs.
| Plugin | Description |
|---|---|
| constitution | Create, validate, and enforce project constitutions with living governance |
| dev-specialisms | Niche developer skills (deployment, frontend vibes, Hashbrown) |
| devs | Specialist coding agents and skills for Python, Rust, TypeScript, React, and security |
| flutter-core | Flutter and Dart development toolkit covering UI/UX, state management, testing, and ServerPod |
| git-lovely | Lovely Git workflows with conventional commits and GitHub CLI integration |
| ideas | Turn vague ideas into sharp vision documents through structured creative collaboration |
| image-gen | AI-powered image generation using Google Gemini models via nanobanana MCP server |
| pr-tools | Parallel PR review agents for code quality, SDD task verification, and TODO tracking |
| readme-and-co | Generate README, LICENSE, CONTRIBUTING, SECURITY, and GitHub templates |
| sandbox | Isolated Docker-based development environments for Claude Code |
| sdd | Specification-Driven Development: specs, plans, tasks, codebase mapping, and quality gates |
| settings-presets | Powerline status line and attribution configuration presets |
| spec-writer | Guided discovery process for writing complete feature specifications |
| utils | Plugin management utilities: dependency checking, scanning, and root resolution |
| worktrees | Git worktree workflows for parallel AI development |
Add the marketplace, then install individual plugins:
claude mcp add-marketplace aaronbassett/agent-foundry
claude plugin install sdd@agent-foundry
Or install a plugin directly from the repo:
claude install-plugin https://github.com/aaronbassett/agent-foundry/tree/main/plugins/sdd
This repository uses lefthook for git hooks.
lefthook --versionlefthook installAutomatic validation:
Manual validation:
scripts/validate-marketplace.shscripts/validate-plugin.sh <plugin-name>scripts/ci/validate.shBypassing hooks:
Use git commit --no-verify or git push --no-verify when:
Note: GitHub Actions will still validate all changes.