1,506 tagged agent, measured the same way as everything else here.
Browse within: coding 208vibe 200vibecoding 200Multi-Agent 108agent-teams 107opencode-plugin 107agentic 91code 87claude-code-plugin 68Autonomous 65chatbot 65agent-framework 59AI Safety 53agents-md 53
Agent
Task decomposition and approach brainstorming agent. Use this agent when you need to break down a complex task into actionable steps, compare implementation approaches, or design a plan before coding. Dispatched by cf-plan for approach analysis. Trigger this agent when the task requires evaluating multiple strategies…
Agent
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
Agent
Compare two outputs WITHOUT knowing which skill produced them.
Agent
Evaluate expectations against an execution transcript and outputs.
Agent Claude Code
Agent "ecc-architect" from KornLabs/truss, covering prompt defense baseline, your role, architecture review process, 1. current state analysis and 2. requirements gathering.
Agent Claude Code
Agent "ecc-performance-optimizer" from KornLabs/truss, covering prompt defense baseline, performance optimizer, core responsibilities, analysis commands and bundle analysis.
Agent Claude Code
Agent "ecc-planner" from KornLabs/truss, covering prompt defense baseline, your role, planning process, 1. requirements analysis and 2. architecture review.
Agent Codex
Multi-Agent Orchestrator - Coordinate agents by projecttype + attributes and pipeline Specify->Plan->Tasks->Implement.
Agent
MutantX mutation testing agent — autonomously runs mutation testing on a project and produces a report.
Agent
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
Agent
Compare two outputs WITHOUT knowing which skill produced them.
Agent
Evaluate expectations against an execution transcript and outputs.
Agent
Read-only search worker for the specship pipeline. Use to delegate one wide fan-out sweep when a stage needs an answer that means reading many files — it returns verified conclusions only, so the caller's context stays clean. A stage invokes it, never a user directly; it never writes or changes code.
Agent
External-fact search worker for the specship research stage. Use to run one query angle of a larger question and return verified, cited conclusions. One invocation per angle — it gathers and checks its own sources, and it neither picks the angles nor writes the report.
Agent
Independent code reviewer for the specship review stage — one member of the opt-in review panel. Use to get fresh, context-free eyes on a working diff, optionally through a named lens (correctness, security, performance, contract-consistency). Reports findings only; it does not fix code, decide the verdict, or touch…
tonik173/generative-ai-explained
Agent
Behaviour is assembled fresh every turn, out of text.
tonik173/generative-ai-explained
Agent
Agent "agent-loop" from tonik173/generative-ai-explained, covering the agent loop, the loop, the wrapper runs the loop, not the model, one turn, traced and where it goes wrong.
tonik173/generative-ai-explained
Agent
Agent "agent-memory" from tonik173/generative-ai-explained, covering memory, the model is stateless, memory is files, read back in and the recipe.
Agent
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
Agent
Compare two outputs WITHOUT knowing which skill produced them.
Agent
Evaluate expectations against an execution transcript and outputs.
Agent
Execute a recursive, hypothesis-driven deep dive research workflow — orchestrating corpus scanning, web scouting, source fetching, sprint synthesis, bibliography enrichment, and academic paper generation. Instantiates the workflow defined in docs/guides/deep-research.md.
Agent
Coordinate multi-workflow sessions spanning research, docs, scripting, and fleet changes — sequence executive agents and maintain session coherence.
Agent
Maintain the health of the repository as an open-source resource — issues, labels, milestones, changelog, contributing docs, and community standards.
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: