AI Agents & MCP Subagents
320 ai agents & mcp subagents for Claude Code and AI agents, ranked by real installs from npm, PyPI and skills.sh.
#Type
- 1technical-directorThe Technical Director owns all high-level technical decisions including engine architecture, technology choices, performance strategy, and technical risk management.May 2026
- 2mcp-backend-engineerUse this agent when you need to work with Model Context Protocol (MCP) implementation, especially when modifying the MCP layer of the application.Jul 2026
- 3verifierPractical patterns, starters & CLI tools for loop engineering with AI coding agents. Design systems that prompt and orchestrate agents (inspired by Addy Osmani and Boris Cherny). Includes loop-audit,…Jul 2026
- 4aegisSecurity vulnerability analysis and testingJan 2026
- 5agentica-agentBuild Python agents using Agentica SDK - spawn agents, implement agentic functions, multi-agent orchestrationJan 2026
- 6context-query-agentQuery the artifact index for precedent and guidanceJan 2026
- 7krakenImplementation and refactoring agent using TDD workflowJan 2026
- 8orchestratorMulti-phase development agent. Research > Plan > Implement with validation gates. Use PROACTIVELY when building features that touch >5 files or require architecture decisions.Jul 2026
- 9openenv-architectDesign new environments or features by analyzing existing patterns. Use when planning significant new work.Jul 2026
- 10mcpc-testerProbe the local Apify MCP server with mcpc during development. Use proactively after implementing features or fixing bugs to test that the implementation follows the spec, confirm requirements are…Jul 2026
- 11AGENTS<skills>Jun 2026
- 12swarm-orchestratorDelegates to this agent when the user wants to coordinate multiple pentest agents as a team, run a full automated red team engagement, orchestrate parallel reconnaissance and exploitation workflows,…Jun 2026
- 13advisorNatively — Free open-source AI meeting assistant, interview copilot, and note taker. The best alternative to Cluely, Otter, Granola, Final Round AI, Fireflies, and Interview Coder. Real-time…Jul 2026
- 14ipc-integration-engineerUse when wiring Context OS into ipcHandlers, IntelligenceEngine, LLMHelper, WhatToAnswerLLM, phone mirror, recap, follow-up, or meeting summary surfaces.Jul 2026
- 15memory-safety-engineerUse when modifying SessionTracker, prior assistant responses, Hindsight, long-term memory, assistant claim storage, memory write gates, or memory provenance.Jul 2026
- 16retrieval-evidence-engineerUse when modifying RAG, ModeHybridRetriever, OKF retrieval, meeting RAG, EvidencePack, RetrievalEvidencePack, source IDs, provenance, chunk metadata, or property-aware retrieval.Jul 2026
- 17source-authority-architectUse when designing or reviewing Natively Context OS, SourceAuthorityKernel, source contracts, source precedence, and capability-scoped retrieval. Trigger for source ownership, context contamination,…Jul 2026
- 18mcp-protocol-expertPROACTIVELY use for MCP protocol questions, transport implementations, JSON-RPC debugging, and spec compliance verification. Expert in the current stable MCP specification.Jul 2026
- 19mcp-reviewerReview MCP server changes for tool safety, schema quality, and host integration correctness.Jul 2026
- 20READMEClaude Code Skill Factory — A powerful open-source toolkit for building and deploying production-ready Claude Skills, Code Agents, custom Slash Commands, and LLM Prompts at scale.Nov 2025
- 21archonAutonomous vision agent. Decomposes vague or specific direction into campaign phases. Delegates to Marshals and specialists. Reviews output against quality standards. Maintains campaign state across…Jul 2026
- 22fleetParallel campaign orchestrator. Runs multiple campaigns in coordinated waves within a single session. Spawns 2-3 agents per wave, collects discoveries, shares context between waves, rebalances…Jul 2026
- 23mcp-server-architectDesigns and implements MCP servers with transport layers, tool/resource/prompt definitions, completion support, session management, and protocol compliance. Specializes in FastMCP 2.x async servers…Jul 2026
- 24verifierReviews a diff against the goal spec assuming the code is broken. Invoke after every code change.Jul 2026
- 25controller-agentCreates thin, RESTful Rails controllers with strong parameters, proper error handling, and request specs. Use when creating controllers, adding actions, implementing CRUD, or when user mentions…Jun 2026
- 26database-reviewerPostgreSQL database specialist for query optimization, schema design, security, and performance. Use PROACTIVELY when writing SQL, creating migrations, designing schemas, or troubleshooting database…Jun 2026
- 27form-agentCreates form objects for complex multi-model forms with validations, type coercion, and nested attributes. Use when building search forms, wizard forms, registration forms, or when user mentions form…Jun 2026
- 28implementation-agentOrchestrates TDD GREEN phase by implementing minimal code that passes failing tests, coordinating specialist subagents. Use when making tests pass, implementing features from failing specs, or when…Jun 2026
- 29job-agentCreates idempotent, well-tested background jobs using Solid Queue with proper error handling and retry logic. Use when creating async tasks, scheduled jobs, or when user mentions background jobs,…Jun 2026
- 30lint-agentAutomatically corrects Ruby and Rails code style using RuboCop, ERB lint, and formatting tools. Use proactively after code changes to ensure style compliance. Use when fixing lint errors,…Jun 2026
- 31mailer-agentCreates Action Mailer emails with previews, templates, and delivery tests following Rails conventions. Use when building transactional emails, notifications, password resets, or when user mentions…Jun 2026
- 32migration-agentCreates safe, reversible database migrations with proper indexes, constraints, and zero-downtime strategies. Use when creating tables, adding columns, modifying schema, or when user mentions…Jun 2026
- 33model-agentCreates well-structured ActiveRecord models with validations, associations, scopes, and callbacks. Use when creating models, adding validations, defining associations, or when user mentions…Jun 2026
- 34policy-agentCreates secure Pundit authorization policies with comprehensive RSpec tests and scope restrictions. Use when adding authorization, restricting access, defining permissions, or when user mentions…Jun 2026
- 35analyzerCode analysis agent in Claude formatMay 2026
- 36council-advisorUse this agent when the user is facing architectural decisions, design choices, or has been stuck debugging a problem after multiple failed attempts. This agent proactively suggests consulting the…Jul 2026
- 37claude-code-hook-agentPlays agent-specific sounds for the 6 hooks that actually fire in agent sessionsJun 2026
- 38run-executorSingle-step executor — session next(inline-brief)/run brief(backtrack) + inline skill execution, unnamed nesting for multi-agent orchestrationJul 2026
- 39team-workerUnified worker agent for team pipelines. Executes role-specific logic loaded from a role_spec file within a built-in task lifecycle (discover, execute, report).Jul 2026
- 40prompt_engineerPrompt engineering specialist for LLM prompt design, few-shot and chain-of-thought structuring, eval harnesses, and RAG retrieval quality. Use when the task requires writing or reviewing prompts,…Jul 2026
- 41mcp-crate-engineerUse this agent when editing any files within the crates/mcp directory. This includes modifications to the MCP router implementation, tool discovery, search functionality, or execution routing.Mar 2026
- 42ai-agent-devLLM 集成、Prompt 工程和 AI Agent 开发。例如：实现 RAG 管道、设计 system prompt、集成工具调用、添加 guardrails。**主动调用 when** 任务涉及 LLM API、prompt 设计、guardrail 或多 LLM 切换。（关键词：DeepSeek、Doubao、Qwen、MiniMax、RAG、prompt 注入、tool…Jul 2026
- 43CLAUDE368 AI skills, 76 expert agents, and 859 stdlib Python tools for every team: engineering, PM, marketing, C-level, compliance, business ops, and research. Installs on Claude Code, Cursor, Codex,…Jul 2026
- 44chaos-engineOrchestrator charter of the main thread (Fable@high effort; fallback Sonnet@max). Plans, delegates, reviews, verifies — never implements. Spawn only to sub-orchestrate a bounded multi-agent effort.Jul 2026
- 45copilot-studio-advisor[THIS IS A SUB-AGENT] Advisory agent for Copilot Studio. Recommends design patterns before authoring, reviews existing agent YAML against patterns and known pitfalls, and troubleshoots validation…Jul 2026
- 46copilot-studio-author[THIS IS A SUB-AGENT] Copilot Studio YAML authoring specialist. This sub-agent creates and edits topics, actions, knowledge sources, child agents, and global variables. Use when building or modifying…Jul 2026
- 47copilot-studio-manage[THIS IS A SUB-AGENT] ALM operations for Copilot Studio agents. Clones, pushes and pulls agent content between local YAML files and the cloud, publishes agents to make drafts live, lists environments…Jul 2026
- 48copilot-studio-test[THIS IS A SUB-AGENT] Testing agent for Copilot Studio agents. Runs PPAPI evaluations against draft agents (no publish needed), batch test suites via the Kit, point-tests via DirectLine or SDK, and…Jul 2026
- 49developer-hubYour intelligent developer command center -- start here for any Python, wxPython, desktop app, NVDA addon, accessibility tool building, desktop accessibility, or general software engineering task.Jul 2026
- 50github-hubYour intelligent GitHub command center -- start here. GitHub Hub discovers your repos and organizations, understands what you want to accomplish in plain English, and guides you to the right outcome…Jul 2026
- 51parallel-dispatcherDispatches multiple worker agents in parallel based on DAG dependencies.Apr 2026
- 52task-workerEphemeral worker for executing a single task. Coordinates via message bus.Apr 2026
- 53architect-agent**Type**: `architect-agent` **Role**: Implementation planning and architecture design **Spawned By**: Issue Orchestrator **Tools**: Codebase read, architecture-rubric, BEADS CLIJun 2026
- 54coder-agent**Type**: `coder-agent` **Role**: TDD implementation of features and fixes **Spawned By**: Issue Orchestrator **Tools**: Full codebase read/write, test runner, BEADS CLIJun 2026
- 55issue-orchestrator**Type**: `issue-orchestrator` **Role**: Main coordinator for a single GitHub Issue lifecycle **Spawned By**: Swarm Coordinator or GitHub webhook **Tools**: BEADS CLI, GitHub API, Task tool (spawns…Jun 2026
- 56engineering-mcp-builderMCP Server开发专家，负责设计和实现Model Context Protocol工具服务器，精通FastMCP/Python SDK、工具命名最佳实践、Zod验证和JSON/Markdown双输出格式Jul 2026
- 57code-review-modeMain thread configuration for evidence-based code review sessions. Focuses on systematic review with evidence gathering and structured findings. Use via: claude --agent code-review-mode Or set in…Jul 2026
- 58context-managerManages context across multiple agents and long-running tasks. Use PROACTIVELY when coordinating complex multi-agent workflows or when context needs to be preserved across multiple sessions. MUST BE…Jul 2026
- 59brainstormerUse this agent when you need to brainstorm software solutions, evaluate architectural approaches, or debate technical decisions before implementation.Mar 2026
- 60mackAutomation Specialist. Use proactively for API integrations, MCP server setup, webhook receivers, OAuth flows, automations, and the connection layer of external imports (fetch the bytes from a live…Jul 2026
- 61super-devActivate the Super Dev pipeline for research-first, commercial-grade project delivery. Use when user says /super-dev or super-dev: followed by a requirement.Jun 2026
- 62fullstack-engineerSenior full-stack engineer operating the P7 methodology: read reality → design solution → impact analysis → implement → three-question self-review → [P7-COMPLETION] delivery. Ships features across…Apr 2026
- 63tool-expertTool expert who picks the right tools, chains complex workflows, and troubleshoots tool failures. Knows when to use built-in tools vs MCP servers vs shell commands. Use for complex tool chaining, MCP…Apr 2026
- 64verifierA local-first, open-source coding agent for your desktop. Bring your own LLM key; your code stays on your machine and only ever leaves to the model provider. The AI Agent builds its own Harnes.Jul 2026
- 65itsvffSonnet 기반 Fable 5 구조 이식 서브에이전트 — 위임 전용(현재 세션에 직접 적용하는 모드는 itsvff 스킬 사용). 구현·분석·리서치·작문 등 독립 작업을 별도 컨텍스트에서 Sonnet 단가로 처리할 때 위임한다. 내부 추론은 난이도에 맞춰 high까지 스케일링, 출력은 읽기 쉽게 군더더기 없이.Jun 2026
- 66AGENTSCommunity collection of Apify agent skills for AI coding assistantsJun 2026
- 67ai-architectSpecializes in architecting AI-powered applications on Vercel — choosing between AI SDK patterns, configuring providers, building agents, setting up durable workflows, and integrating MCP servers.Jul 2026
- 68antigravity-delegateUse this subagent PROACTIVELY — don't wait for the user to ask for delegation — whenever a task contains a well-scoped, ABOVE-break-even unit of work for the Antigravity CLI (agy / Gemini): bulk…Jul 2026
- 69mcp-server-expertUse this agent when the user needs guidance, advice, or best practices related to Model Context Protocol (MCP) server development, architecture, implementation, or usage.Jul 2026
- 70entire-searchSearch Entire checkpoint history and transcripts with `entire search --json`, or code content across repositories with `entire search --code --json`. Use proactively when the user asks about previous…Jul 2026
- 71code-freeWOZCODE free-plan fallback agent — active when the monthly free-plan cap is exhausted. Claude Code's built-in Read, Edit, Write, Grep, Glob, and NotebookEdit are available; WOZCODE MCP tools are…Jul 2026
- 72chain-executorExecutes delegated chain steps with context isolation. Automatically used when chains use the ==> delegation operator. The step instructions, system prompt, and previous step context are provided in…Jul 2026
- 73mastra-ai-agent-builderUse this agent when you need to build, configure, or understand Mastra AI agents using the latest best practices and approaches. Examples: <example>Context: User wants to create a new Mastra AI agent…Jul 2026
- 74builderUse this agent to implement code changes for a task that has already been planned by lead and analyzed by explorer. The builder writes, edits, and creates files based on the plan and the explorer's…Jul 2026
- 75consultantTechnical advisor agent for @cardor/agent-harness-kit. Runs after the explorer and before the builder. Provides structured advisory — patterns, best practices, warnings, and risks — written directly…Jul 2026
- 76explorerUse this agent to read and map the codebase for a specific task. The explorer researches relevant files, understands existing patterns, and produces a structured analysis for the builder to use.…Jul 2026
- 77actOODA Act phase - Implements the decided solution with precision, tests thoroughly, and validates resultsJul 2025
- 78decideOODA Decide phase - Evaluates options, considers trade-offs, and recommends the best course of actionJul 2025
- 79observeOODA Observe phase - Gathers comprehensive information about the current situation, codebase state, and problem contextJul 2025
- 80orientOODA Orient phase - Analyzes observations to understand context, identify patterns, and synthesize insightsJul 2025
- 81pneuma-amenderPneuma Skills amendment specialist (DEFAULT / opus engine). Use proactively to apply code-review findings to existing work inside the git worktree the parent prepared — judge each finding (fix valid…Jul 2026
- 82pneuma-amender-fablePneuma Skills amendment specialist — HEAVYWEIGHT Fable-5 engine. Identical discipline to pneuma-amender (judge each finding, surgical fixes, escalate wrong / out-of-authority ones, per-finding…Jul 2026
- 83pneuma-architectPneuma Skills architecture & design authority (design-authoring, Fable-5 engine). Use proactively for design-level work on any Pneuma layer / contract / mode / backend, present or future — TWO modes:…Jul 2026
- 84pneuma-explorePneuma Skills codebase reconnaissance specialist. Use proactively for any research, investigation, or architecture-understanding task scoped to the pneuma-skills repository. Internalizes the project…Jul 2026
- 85pneuma-implPneuma Skills implementation specialist (DEFAULT / opus engine). Use proactively to implement a SINGLE well-defined task that has a spec / acceptance criteria, inside a git worktree the parent…Jul 2026
- 86pneuma-impl-fablePneuma Skills implementation specialist — HEAVYWEIGHT Fable-5 engine. Identical discipline to pneuma-impl (TDD + contract-first discipline, full quality gates, strict spec obedience, mandatory visual…Jul 2026
- 87mlb-fantasy-coachOrchestrates a multi-agent team for Yahoo Fantasy Baseball management. Spawns specialists (lineup, waiver, streaming, trade, category, playoff) each in advocate + critic variants, runs…Jul 2026
- 88cc-orchestration-writerCreates Claude Code agent orchestration scripts - bash scripts that chain multiple Claude CLI calls with structured output, rate limiting, status tracking, and error handling.Feb 2026
- 89core-principlesExpert agent for developing PRPM (Prompt Package Manager) - applies core architecture principles, quality standards, and development best practices for building the universal package manager for AI…Jun 2026
- 90format-conversionExpert agent for converting between AI prompt formats (Cursor, Claude, Continue, Windsurf) - ensures lossless conversions, quality scoring, and round-trip validationJun 2026
- 91skill-creatorGenerate spec-compliant skills for the cc-polymath library. Takes a topic/domain and produces a well-structured SKILL.md with proper frontmatter, progressive loading, and atomic design.Feb 2026
- 92frankyImplementation worker for one Superloopy criterion or one non-overlapping slice. Use when a bounded build/edit slice can be owned end-to-end with artifact-backed proof.Jul 2026
- 93jinbeFinal Superloopy gate reviewer that integrates implementation, QA, review, and audit evidence into an APPROVE/REJECT. Use as the last check before the parent finishes the loop.Jul 2026
- 94namiRead-only codebase navigator for Superloopy subagent-driven work. Finds files and code in the working tree and returns absolute paths with a direct answer. Never edits, never writes evidence.Jul 2026
- 95robinRead-only, skeptical evidence auditor for a Superloopy criterion. Use to judge whether Superloopy's deterministic re-run actually satisfies the scenario and write a verdict.Jul 2026
- 96usoppQA worker that exercises Superloopy criteria and writes artifact-backed QA evidence. Use to run the app/regression surface and prove behavior, not review code.Jul 2026
- 97zoroIndependent code reviewer for a bounded Superloopy change. Use to review a diff for correctness, tests, security, and scope drift before the gate.Jul 2026
- 98plugin-manifest-expertValidates plugin.json schema compliance, semantic versioning rules, and plugin architecture integrity. Use when features modify plugin manifests, add/remove agents, change plugin metadata, or require…Jul 2026
- 99al-agent-builder.agentAgent Toolkit Builder — specialist in designing and coding Business Central agents using the AI Development Toolkit and Agent SDK. Follows the official Agent Template project structure. Handles both…Jul 2026
- 100al-conductorOrchestrates Planning, Implementation, Review, and Commit cycle for AL Development. Enforces TDD and quality gates for Business Central extensions. Use when you need structured TDD orchestration with…Jul 2026
