bulk-reader
Read large files or many files on the caller's behalf and return short line-referenced summaries with coverage. Use when a file exceeds the read budget or the…
An agent is a specialist Claude hands a whole job to, with its own tools and its own context.
8,939 agents across 675 plugins.
Read large files or many files on the caller's behalf and return short line-referenced summaries with coverage. Use when a file exceeds the read budget or the…
Agent for running E2E tests on web applications. Navigates pages, fills forms, clicks buttons, and verifies results.
Agent for browsing and extracting structured content from web pages. Navigates pages, handles pagination, and returns structured data.
Read-only spec-integrity auditor that runs after every issue has merged. Walks the approved PRD requirement by requirement, maps each to the evidence it can…
Read-only senior code reviewer that reviews one completed Foreman issue's diff against its plan/requirements and the repo's conventions — from a fresh context…
Read-only grader that reviews a completed Foreman issue against its acceptance criteria, the referenced PRD sections, and the saved evidence — from a fresh…
Use this agent for Output.ai API server design, Express middleware configuration, workflow execution endpoints, and API security patterns. Specializes in…
Use this agent for Output.ai containerization including Docker Compose configuration, Node.js container optimization, Temporal service orchestration, and…
Use this agent for AI SDK integration, LLM provider configuration, prompt template management, error handling for AI APIs, and optimizing LLM workflow patterns…
Architecture research and judgment executor on Opus at xhigh effort. Use for architecture proposals, complex multi-step reasoning, and high-risk analysis —…
Heavy execution worker on Opus at high effort. Use for hard, well-scoped execution — cross-module refactors, tricky concurrency or state fixes, changes that…
Read-only codebase explorer on Sonnet at high effort. Use to locate files, symbols, call paths, tests, uncertainties, and candidate affected surfaces before…
Station AI agent operator. Use proactively for ANY Station-related tasks including creating agents, running tasks, managing environments, configuring MCP…
<!-- Loaded by nextjs-ecommerce-engineer when task involves admin UI, order management, product CRUD, inventory tracking, analytics, or role-based access -->
Verify implementations match Architecture Decision Records: decision mapping, contradiction detection, scope creep analysis.
**Scope**: Task-to-agent routing table; capabilities and boundaries per agent.
文章视觉策划与配图子代理。由工作流导演在 Humanizer 之后、最终事实核查之前的 Stage 11 显式调用。
[Subagent] 写作复盘学习器。 对比 AI 初稿(draft_v1.md) 与用户确认的最终定稿,提炼结构化的写作经验教训。 由工作流导演在流程收尾阶段始终调用;没有可学习差异时也落盘记录原因。
[Long-running, run synchronously] Use when user says: 'research X', 'learn about X', 'study X', 'build a knowledge tree for X', 'help me understand X deeply',…
Lint agent configurations using agnix CLI. Invoke agnix skill and return validation results.
Uses Zapier MCP to discover, enable, audit, and execute app actions safely and efficiently while following Zapier's read/write confirmation lifecycle.
Backend Developer - API implementation using patterns, RLS enforcement
Business Systems Analyst - Pattern discovery, spec creation, acceptance criteria definition
Monitors ABM program performance, intent signals, and funnel conversion to prioritize next actions.
Designs multi-threaded account-based programs with aligned offers, plays,
Synthesizes usage, support, and sentiment signals into actionable account health insights.
Validates and structures lesson candidates before persisting to lessons.json
Designs feature architectures by analyzing existing codebase patterns and conventions, then providing comprehensive implementation blueprints with specific…
Deeply analyzes existing codebase features by tracing execution paths, mapping architecture layers, understanding patterns and abstractions, and documenting…
Fold event analyses into an OKF knowledge bundle in deterministic sequence. This is the only agent that writes `.okf/`, executing the reduce phase of backfill…
Analyze a single repository history event (git commit or session turn) to extract domain concepts and semantic content. Use in parallel during the map phase of…
Reviews code for quality, security, and project conventions. Use after completing features or before commits.
Debugs errors, test failures, and unexpected behavior. Knows PromptScript architecture.
PromptScript language expert. Helps with syntax, compilation issues, and migrations.
Use this agent when you need to refactor existing code, rewrite a module for better maintainability, decompose a large file into focused sub-modules, eliminate…
Use this agent when you want a comprehensive review of code quality, readability, structure, and maintainability. This agent focuses on how well-written and…
Use this agent when the user needs information from project documentation files, SDK docs, protocol specs, or any `@docs` prefixed directories. This includes…
AI/ML research agent — model architecture analysis, training optimization, mechanistic interpretability, safety alignment, inference optimization
Vulnerability research agent — identifies CVEs, finds exploit PoCs, maps attack chains, and develops custom exploitation strategies
Blind adversarial checker — given ONLY a finding artifact and its evidence (never the author's reasoning), tries to refute it and emits a structured rebuttal…
Full Board of Directors deliberation with 5 expert directors assessing, discussing, and voting.
Expert CEO advisor with 30 years entrepreneurship experience. Provides strategic guidance, business analysis, and leadership advice. Advisory only - does not…
© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic