An agent is a specialist Claude hands a whole job to, with its own tools and its own context.
161 agents across 675 plugins.
Expert code review specialist with severity-rated feedback, logic defect detection, SOLID principle checks, style, performance, and quality strategy
Accessibility standards and assistive features — remapping, text scaling, colorblind modes, screen reader support.
Implements game AI — behavior trees, state machines, pathfinding, perception, decision-making, NPC and enemy behavior, AI debugging.
Telemetry and analytics — event tracking, player behavior, A/B test frameworks, dashboard specification, data pipelines.
1. **Using tools that don't exist** — Always verify tools via `list_agent_tools()` before designing. Common hallucinations: `csv_read`, `csv_write`,…
Agents are defined as a single `agent.yaml` file. No Python code needed. The runner loads this file directly -- no `agent.py`, `config.py`, or…
Defines agent personalities (Orchestrator, Explorer, Librarian, etc.) and manages their configuration lifecycle. This directory implements the **Agent Factory…
**BMAD (Business-Minded Agile Development)** - AI-driven agile development automation with role-based agents
Direct slash commands for daily coding tasks without workflow overhead
Lightweight alternative to BMAD for rapid prototyping and simple feature development
Clean up, simplify, or refine recently written or modified code without changing behavior. Improves readability, removes duplication, clarifies naming,…
Analyzes codebase implementation details. Call the codebase-analyzer agent when you need to find detailed information about specific components.
Locates files, directories, and components relevant to a feature or task. Basically a "super search/find/ls tool.
Audits logic, duplication, and dead-code risks; enforces rule compliance.
Finds the smallest correct change set; prevents patching around root causes.
Implements scoped changes with tests and minimal diffs.
Read this prompt top-to-bottom before judging. You verify a **finished paper** as one self-contained document: does the complete manuscript, read on its own,…
Read `AGENTS.md` (the standing contract, including the PRIME DIRECTIVE) and this prompt top-to-bottom before planning.
Read `AGENTS.md` (the standing contract, including the PRIME DIRECTIVE) and this prompt top-to-bottom before revising. This is the single, self-contained…
Station AI agent operator. Use proactively for ANY Station-related tasks including creating agents, running tasks, managing environments, configuring MCP…
Adversarial code review - verify demos work, then spec compliance, then code quality
Use this agent when you need to debug Electron application issues, particularly UI-related problems, component rendering issues, or when you need to bypass…
Use this agent when you need to run, debug, or troubleshoot end-to-end Electron tests. This includes handling test execution, interpreting test results, and…
Image-generation subagent. Use PROACTIVELY whenever a task needs image files — generating or editing icons, logos, banners, illustrations, mockups, photos, or…
Root-cause a failing test, crash, stack trace, or misbehaving feature by delegating the investigation to OpenAI Codex (GPT-5) via the local Codex CLI, then…
Hand a well-specified, high-volume coding task to OpenAI Codex (GPT-5) to actually write the code, so it runs on the user's ChatGPT quota instead of this…
ELITE ARCHITECT: The unified execution heart of the Maestro system. Expert in Architecture, Frontend, and Backend.
Cross-artifact consistency and coverage analysis specialist with Anthropic think protocol. Validates alignment between specifications, plans, tasks, and…
Production deployment specialist with Anthropic safety patterns managing CI/CD pipelines, infrastructure provisioning, and safe rollout strategies. Defaults to…
Root cause analysis and debugging specialist with Anthropic think protocol and 3-retry limit. Focuses on systematic problem diagnosis, error tracing, and fix…
Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recently modified code unless…
Work plan and code review expert — thorough, structured, multi-perspective (Opus)
Root-cause analysis, regression isolation, stack trace analysis, build/compilation error resolution
Owns visual identity — style guides, art bible, asset standards, color palettes, UI visual direction.
Owns sonic identity — music direction, sound palette, audio implementation strategy, mix balance.
Player-facing communication — patch notes, social posts, community updates, feedback collection, player bug triage, crisis communication.
Agents are declarative JSON configs in `exports/`: ``` exports/my_agent/ agent.json # The entire agent definition mcp_servers.json # MCP tool server config…
Use browser nodes (with `tools: {policy: "all"}`) when: - The task requires interacting with web pages (clicking, typing, navigating) - No API is available for…
Interactive System Architect agent for technical design with quality scoring and user confirmation
Automated Developer agent for implementing features based on PRD, architecture, and sprint plan
© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic