code-reviewer
409Agent
Reviews code for quality and correctness.
not rated 453 today A 11 tokens
MIT
checker
410Agent
Judges finished work against its validator and the real need, leaving nothing unchecked. Use when code or a deliverable needs independent verification before it ships. Never edits the work, never implements the fix.
not rated 453 today A 42 tokens
MIT
executor
411Agent
Turns a dispatched task into working, validated code that fits the project. Use when an approved scope must become code. Never plans, never judges its own work.
not rated 453 today A 34 tokens
MIT
Agent Claude Code
Use this agent when you need to develop medium to long-term (18-month) trading strategies based on Stanley Druckenmiller's investment philosophy. This agent synthesizes technical analysis, market sentiment, news events, and macroeconomic trends to formulate 4-scenario strategic plans (Base/Bull/Bear/Tail Risk) with…
not rated 283 7mo ago A 80 tokens
MIT
Agent Claude Code
Use this agent when you need comprehensive market analysis combining recent news impact assessment and forward-looking event scenarios. Specifically use this agent when:\n\n \nContext: User wants to understand recent market movements and prepare for upcoming events.\nuser: "Can you analyze what's been driving the…
not rated 283 7mo ago A 0 tokens
MIT
Agent Claude Code
Use this agent when you need comprehensive technical analysis of market conditions that synthesizes multiple data sources including government bond yields, VIX volatility index, stock indices, commodity prices, sector performance, and individual stock analysis. Deploy this agent when:\n\n \nContext: User has just…
not rated 283 7mo ago A 0 tokens
MIT
agent builder
415Agent
You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command.
not rated 20 6mo ago A 6 tokens
MIT
module builder
416Agent
You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command.
not rated 20 6mo ago A 6 tokens
MIT
workflow builder
417Agent
Workflow Building Master.
not rated 20 6mo ago A 6 tokens
MIT
Agent
You are a read-only verification subagent spawned to check a design deliverable the main agent just built or edited. Your only job: load that deliverable, verify it, and report a single verdict — done or needswork — back to the main agent. You must not modify, create, or delete any file, edit the source, build, or…
not rated 10 1mo ago A 0 tokens
MIT
Agent
You are a read-only capability probe spawned before a design task tries to read or inspect screenshots. Your only job is to determine whether this Claude Code session's current model/provider can accept image input.
not rated 10 1mo ago A 0 tokens
MIT
analyzer
420Agent
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
not rated 7 4mo ago A 0 tokens
MIT
comparator
421Agent
Compare two outputs WITHOUT knowing which skill produced them.
not rated 7 4mo ago A 0 tokens
MIT
grader
422Agent
Evaluate expectations against an execution transcript and outputs.
not rated 7 4mo ago A 0 tokens
MIT
complete-agent
423Agent
A fully complete and valid agent.
not rated 402 yesterday A 9 tokens
Apache-2.0
Agent
An agent with all new fields configured correctly.
not rated 402 yesterday A 13 tokens
Apache-2.0
valid-agent
425Agent
A fully valid agent configuration.
not rated 402 yesterday A 8 tokens
Apache-2.0
Agent Gemini CLI
An agent to test Spanner MCP with auth.
not rated 402 yesterday A 14 tokens
Apache-2.0
customer-service
427agents-universe/agents-universe
Agent
智能客服智能体——严格依据项目知识库（FAQ、服务政策、话术）回答用户问题；知识库没有答案时明确告知并转人工；可经自定义 API 与 MCP 工具查询业务系统.
not rated 235 yesterday A 47 tokens
Apache-2.0
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: