harness · market
Harness
Put raw intelligence to work.
Skills, MCP servers, prompts, assistants and connectors. Every listing shows its author, version and the permissions it needs.
On the shelves21,000
- MCP servers18,849
- Skills1,282
- Assistants651
- Prompts218
0 items
AgentsSpecialist assistants, also called subagents. Installed in Claude Code, Codex and the like, they take on the work their main session hands them.
- Identity Graph Operatormsitarzewski 158kOperates a shared identity graph that multiple AI agents resolve against. Ensures every agent in a multi-agent system gets the same canonical answer for "who is this entity?" - deterministically, even under concurrent writes.Agents
- Agentic Identity & Trust Architectmsitarzewski 158kDesigns identity, authentication, and trust verification systems for autonomous AI agents operating in multi-agent environments. Ensures agents can prove who they are, what they're authorized to do, and what they actually did.ArchitectureAgents
- Multi-Agent Systems Architectmsitarzewski 158kSystems architect specializing in the design, coordination, and governance of multi-agent AI pipelines — covering topology selection, context management, inter-agent trust, failure recovery, human-in-the-loop gating, and observability for production-grade agent systems.MonitoringArchitectureAgents
- Roast Judge Agentalirezarezvani· roast 28kConvenes a 5-angle adversarial panel (Critic, Champion, Analyst, Investigator, Customer) on a business idea, then acts as the Judge to deliver one GO / RESHAPE / KILL verdict with the cheapest 48-hour test to de-risk it. Fires all five reviewers in parallel as general-purpose subagents with the same brief, refuses to average the scores, names and resolves the real tension, and never softens the call. Use to pressure-test or stress-test an idea before building it.Opus1 skillAgents
- TDD orchestratorwshobson· backend-development 40kMaster TDD orchestrator specializing in red-green-refactor discipline, multi-agent workflow coordination, and comprehensive test-driven development practices. Enforces TDD best practices across teams with AI-assisted testing and modern frameworks.OpusTestingCodingAgents
- AI engineerwshobson· llm-application-dev 40kBuild production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and enterprise AI integrations.Same as sessionAgentsAI models
- Context managerwshobson· agent-orchestration 40kElite AI context engineering specialist mastering dynamic context management, vector databases, knowledge graphs, and intelligent memory systems. Orchestrates context across multi-agent workflows, enterprise AI systems, and long-running projects with 2024/2025 best practices.Same as sessionDatabasesMemoryAgents
- Team leadwshobson· agent-teams 40kTeam orchestrator that decomposes work into parallel tasks with file ownership boundaries, manages team lifecycle, and synthesizes results. Use when coordinating multi-agent teams, decomposing complex tasks, or managing parallel workstreams.FableAgents
- Fullstack engineeralirezarezvani 28kFullstack-engineering orchestrator. Walks the Matt Pocock 7-question forcing-question grill, runs the deterministic profile picker, then forks into the POWERFUL-tier specialists (api-design-reviewer, ci-cd-pipeline-builder, database-designer, performance-profiler, slo-architect — listed alphabetically; workflow order is dependency-driven) rather than reimplementing their scope. Forks own context so heavy ingestion does not pollute parent thread. Invoke via /cs:fullstack-review or Agent({subagent_type:"cs-fullstack-engineer",...}).1 skillDatabasesArchitectureAgents
- Firestore Security Rules Authorfirebase 462MANDATORY specialist subagent for Cloud Firestore Security Rules (firestore.rules). Whenever your task requires creating, authoring, or modifying Firestore Security Rules (firestore.rules), you MUST delegate rules authoring to this subagent rather than writing firestore.rules directly in the main agent.SecurityWritingAgents