Build and review AI agent applications using PydanticAI, LangGraph, DeepAgents, and Vercel AI SDK. Guides architectural decisions, implements agents, reviews code for bugs and anti-patterns, and builds streaming chat interfaces.
Guides architectural decisions for Deep Agents applications. Use when deciding between Deep Agents vs alternatives, choosing backend strategies, designing subagent systems, or selecting middleware approaches.
Reviews Deep Agents code for bugs, anti-patterns, and improvements. Use when reviewing code that uses create_deep_agent, backends, subagents, middleware, or human-in-the-loop patterns. Catches common configuration and usage mistakes.
Implements agents using Deep Agents. Use when building agents with create_deep_agent, configuring backends, defining subagents, adding middleware, or setting up human-in-the-loop workflows.
Guides architectural decisions for LangGraph applications. Use when deciding between LangGraph vs alternatives, choosing state management strategies, designing multi-agent systems, or selecting persistence and streaming approaches.
Reviews LangGraph code for bugs, anti-patterns, and improvements. Use when reviewing code that uses StateGraph, nodes, edges, checkpointing, or other LangGraph features. Catches common mistakes in state management, graph structure, and async patterns.
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.

Image: NASA, Public Domain. Source
Beagle is a Claude Code plugin marketplace with 145 skills across code review, documentation, testing, architectural analysis, and git workflows. Use it to review before you push, detect AI-generated artifacts, draft and improve docs, generate test plans, and analyze codebases — across Python, Go, Rust, Elixir, React, Remix v2, iOS/Swift, and AI frameworks.
Used with Amelia for agent-based workflows and Daydream for automated review-fix-test loops.
Prerequisites:
run-test-plan skill (optional)# Add the marketplace
claude plugin marketplace add https://github.com/existential-birds/beagle
# Install the plugins you need
claude plugin install beagle-core@existential-birds
claude plugin install beagle-python@existential-birds
claude plugin install beagle-react@existential-birds
Verify installation by opening a new Claude Code session and running /beagle-core:commit-push — if the skill loads, the plugin is active.
To update:
claude plugin marketplace update existential-birds && claude plugin update <plugin-name>
Troubleshooting:
~/.claude/plugins/known_marketplaces.json and restart Claude Code.claude plugin marketplace update existential-birds to refresh the marketplace.Use the skills CLI to install beagle skills for other AI agents:
npx skills add existential-birds/beagle
This downloads the skills and configures them for your agent.
Codex users: Link each plugin into ~/.agents/skills/ — see .codex/INSTALL.md for setup instructions.
| Plugin | Skills | Category |
|---|---|---|
| beagle-core | 20 | Shared workflows, verification, git |
| beagle-python | 7 | Python, FastAPI, SQLAlchemy, pytest |
| beagle-go | 13 | Go, BubbleTea, Wish SSH, Prometheus |
| beagle-elixir | 11 | Elixir, Phoenix, LiveView, ExUnit, ExDoc |
| beagle-ios | 16 | Swift, SwiftUI, SwiftData, iOS frameworks |
| beagle-react | 16 | React, React Flow, shadcn/ui, Tailwind |
| beagle-remix-v2 | 12 | Remix v2 route modules, loaders/actions, forms, sessions |
| beagle-rust | 12 | Rust, tokio, axum, sqlx, serde |
| beagle-ai | 13 | Pydantic AI, LangGraph, DeepAgents |
| beagle-docs | 10 | Documentation quality, AI writing detection (Diataxis) |
| beagle-analysis | 13 | Brainstorming, ADRs, strategy, LLM-as-judge, spec gap resolution, TDD plan writing |
| beagle-testing | 2 | Test plan generation and execution |
| Total | 145 | — |
These are the canonical skill entry points for Beagle.
| Skill | Description |
|---|---|
review-plan <path> | Review implementation plans |
review-llm-artifacts | Detect LLM coding artifacts |
verify-llm-artifacts | Confirm or reject review findings before deletes |
fix-llm-artifacts | Fix detected artifacts |
commit-push | Commit and push changes |
create-pr | Create PR with template |
gen-release-notes <tag> | Generate release notes |
receive-feedback <path> | Process review feedback |
fetch-pr-feedback | Fetch bot comments from PR |
respond-pr-feedback | Reply to bot comments |
subagent-prompt | Hand off the current session as an orchestrator-plus-subagents prompt for a fresh session |
skill-builder | Create new skills |
prompt-improver | Optimize prompts |
| Skill | Plugin | Description |
|---|---|---|
review-python | beagle-python | Python/FastAPI code review |
review-frontend | beagle-react | React/TypeScript code review |
review-go | beagle-go | Go code review |
review-tui | beagle-go | BubbleTea TUI code review |
review-ios | beagle-ios | iOS/SwiftUI code review |
review-elixir | beagle-elixir | Elixir/Phoenix code review |
review-rust | beagle-rust | Rust/tokio/axum code review |
review-remix-v2 | beagle-remix-v2 | Remix v2 code review (loaders, actions, forms, sessions) |
npx claudepluginhub jmagar/.agents --plugin beagle-aiRust code review and development skills covering ownership, lifetimes, error handling, async/tokio, serde, sqlx, axum, macros, FFI, unsafe, concurrency, and testing patterns.
React, React Flow, React Router, shadcn/ui, Tailwind v4, Vitest, and Zustand code review. Pairs with beagle-core for full workflow.
Architecture analysis, brainstorming, ADR generation, LLM-as-judge comparison, and spec gap resolution.
Python, FastAPI, SQLAlchemy, PostgreSQL, and pytest code review. Pairs with beagle-core for full workflow.
Swift, SwiftUI, SwiftData, iOS animation design/implementation/review, and framework code review (HealthKit, CloudKit, WidgetKit, watchOS, App Intents). Pairs with beagle-core for full workflow.
Shared code review workflows, verification protocol, git commands, and feedback handling. Recommended as a base for all beagle plugins.
Personal Claude Code + Codex dev stack: security hooks, AI-first code conventions, /security-review, /repo-map, /stack-check, portable statusline. Designed to complement other skills-based plugins, not replace them.
Verification-first engineering toolkit for Claude Code. 15 skills across a 5-phase spine (Investigate → Design → Implement → Verify → Ship), 8 specialist agents, an interactive setup wizard. Every skill has rationalizations + evidence requirements. Built for senior ICs and tech leads.
Production-grade engineering skills for AI coding agents — covering the full software development lifecycle from spec to ship.
OpenAgentsControl — multi-agent orchestration for Claude Code. Context-aware development with skills, subagents, parallel execution, and automated code review.
Use this agent when implementing AI/ML features, integrating language models, building recommendation systems, or adding intelligent automation to applications. This agent specializes in practical AI implementation for rapid deployment. Examples:\n\n<example>\nContext: Adding AI features to an app\nuser: "We need AI-powered content recommendations"\nassistant: "I'll implement a smart recommendation engine. Let me use the ai-engineer agent to build an ML pipeline that learns from user behavior."\n<commentary>\nRecommendation systems require careful ML implementation and continuous learning capabilities.\n</commentary>\n</example>\n\n<example>\nContext: Integrating language models\nuser: "Add an AI chatbot to help users navigate our app"\nassistant: "I'll integrate a conversational AI assistant. Let me use the ai-engineer agent to implement proper prompt engineering and response handling."\n<commentary>\nLLM integration requires expertise in prompt design, token management, and response streaming.\n</commentary>\n</example>\n\n<example>\nContext: Implementing computer vision features\nuser: "Users should be able to search products by taking a photo"\nassistant: "I'll implement visual search using computer vision. Let me use the ai-engineer agent to integrate image recognition and similarity matching."\n<commentary>\nComputer vision features require efficient processing and accurate model selection.\n</commentary>\n</example>