Subagents with their own prompt and tools. Injected whole, so what you see in the token column is what every session pays.
Agent Claude Code
Designs 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 with real API integrations and plain text formatting for optimal LLM consumption.
Agent Claude Code
Server-Side Template Injection specialist. Covers Jinja2 (H1 #74), Twig, Velocity, FreeMarker, ERB, Handlebars, Thymeleaf. Use for any rule-engine, comment/message rendering, PR automation, admin template, or user-customizable template surface. Systematic blocklist mapper + CVE bypass runner + runtime-vs-parse…
Agent Claude Code
Use this agent when you need to port an evaluation benchmark from the LightEval framework to openbench. This includes converting LightEval task definitions, dataset loaders, metrics, and scoring functions to the Inspect AI framework used by openbench. The agent should be invoked when the user mentions porting…
Agent
Agent "vllora-data-agent" from vllora/vllora, covering role, workflow, standard analysis (default), light-touch by default and decide focus (based on user intent).
Agent Claude Code
Classifies one candidate pair of archived references as the same document, a newer copy, a revision, a translation, related or distinct. Use only from the reference archive workflow, one pair per invocation.
Agent Claude Code
A11y auditing, WCAG compliance, and inclusive design review. Ensures digital content is usable by everyone.
Agent ✓ vendor
You are Agent D (Host + Wrapper + Correctness) in the cutile-rs conversion pipeline. Agents A and B have already produced the reference analysis and the device-only Rust kernel. You own the host boundary.
Agent Claude Code
Use this agent when you need to create foundational templates, boilerplate code, or starter configurations for new projects, components, or features. This agent excels at generating clean, well-structured base templates that follow best practices and can be easily customized. Examples: Context: User needs to start a…
Agent Claude Code
Orchestrate F1 test drives to validate the Cyrus agent system end-to-end. Use this agent to run comprehensive test drives that verify issue-tracker, EdgeWorker, and renderer components.
microsoft/CopilotStudioSamples
Agent ✓ vendor
The solution zip contains both agents, their custom connectors, and connection references — all in one package.
Agent Claude Code
Create Tool UI component source files. Use after designer agent produces a spec to implement the actual component code.
Agent
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
alirezarezvani/claude-code-tresor
Agent
Code refactoring specialist focused on clean architecture, SOLID principles, and technical debt reduction. Use proactively for code quality improvements and architectural refactoring.
Agent Claude Code
../../src/agents/refactoring/refactoring-expert.md.
Agent
An agent that designs explanations using learning-science methods for beginners who need to understand and repeat the assigned topics in their own words.
Agent Cursor
Trellis quality check agent. Use this exact agent for Trellis task verification, check.jsonl context injection, and self-fixing code review. Do not use generic/default/generalPurpose agents for Trellis checks.
stretchcloud/claude-code-unified-agents
Agent Claude Code
Master orchestrator that coordinates multiple sub-agents for complex multi-domain tasks.
Agent
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
Auriti-Labs/geo-optimizer-skill
Agent Claude Code
Agent "TEAM_USAGE" from Auriti-Labs/geo-optimizer-skill, covering agent team usage guide, geoready / geo optimizer, 1. agent inventory, 2. read-only reviewers and 3. code-writing implementation agents.
Agent
You are an External Integration agent - a specialized assistant for executing actions across connected external services. Your purpose is to interact with any connected Composio toolkit (900+ platform-wide) and return structured results to the main agent.
RyanAlberts/best-of-Agent-Harnesses
Agent
Audits a codebase's AI agent stack against the live best-of-Agent-Harnesses dataset — finds which harnesses the repo uses, flags dead or graveyarded ones, and names live replacements. Use when the user asks "is my agent stack current", "audit my agent dependencies", or inherits an agent project of unknown vintage.
Agent Claude Code
Implementa EXATAMENTE UMA feature de plan/features.json do gov-loop (DeskcommCRM · Governança de Atendimento), com precisão e impacto mínimo. Usado pela sessão do loop (loop/LOOP.md) para todo trabalho. Recebe o briefing com id, acceptance verbatim e restrições; devolve resumo com evidência observada. Não marca…
Agent ✓ vendor
The agentServer manages explicit, named conversations with full CRUD semantics. Each conversation has its own isolated dispatcher instance, chat history, conversation memory, and persist directory. Multiple clients can connect to the same conversation simultaneously and share state; clients connected to different…
Agent
Agent "adversary" from joelhooks/swarm-tools, covering adversary agent - sarcasmotron, agent type, model, purpose and when to use.
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: