Eight multi-agent arena modes with a persistent best-agent library that forges Specialist Council members.
Plugin agent-arena-mode from marketplace moaa in ahmadhammoud56/MOAA. Commands read from the repo's manifest — 5 days ago.
cascadeExplore many agent proposals and progressively invest in the strongest survivors. Use when the user requests agent-arena cascade mode or invokes /agent-arena-mode:cascade.
effort-trialMeasure whether council roles find more at a higher effort than at a lower one, per unit of cost, and suggest each role's effort preset. Use when the user asks to tune council effort or model costs, or invokes /agent-arena-mode:effort-trial.
evolutionEvolve agent populations through inheritance, selection, mutation, and final synthesis. Use when the user requests agent-arena evolution mode or invokes /agent-arena-mode:evolution.
fold-trialMeasure whether a council of subagents beats one agent loop on your own tasks, per unit of cost - the same frozen tasks run solo and as a council, judged blind, with the tasks whose outcome flips. Use when the user asks whether subagents or the council are worth it, or invokes /agent-arena-mode:fold
harness-leagueCompare agent harnesses (Claude Code, Codex, Gemini CLI, OpenCode through allies) on the same frozen tasks, judged blind, with score, pass rate, cost and the tasks where they differ - real data for routing work to allies. Use when the user asks which agent or harness is best for a kind of task, or i
judgeSelect the best of independent agent answers with one strong judge. Use when the user requests agent-arena judge mode or invokes /agent-arena-mode:judge.
karpathy-loopImprove something against a fixed number - edit, measure with a script the agent may not change, keep the change if the number improved, otherwise revert, repeat until the budget runs out (after Karpathy's autoresearch). Use for tuning code speed, model loss, test pass rate, file size or any measura
leagueCompare frozen agent answers across repeated Elo-rated matches. Use when the user requests agent-arena league mode or invokes /agent-arena-mode:league.
libraryFind, inspect, load, and reuse the best saved agent-arena profiles and results from the persistent database. Use when the user asks for saved arena agents, the agent library, or /agent-arena-mode:library.
redteamUse adversarial agents to test, repair, and validate competing solutions. Use when the user requests agent-arena redteam mode or invokes /agent-arena-mode:redteam.
swarmRun collaborative agent competition with shared findings and iterative elimination. Use when the user requests agent-arena swarm mode or invokes /agent-arena-mode:swarm.
synthesisCombine compatible contributions from independent agents and specialists. Use when the user requests agent-arena synthesis mode or invokes /agent-arena-mode:synthesis.
tournamentRun a head-to-head agent knockout tournament with attacks, revisions, and judging. Use when the user requests agent-arena tournament mode or invokes /agent-arena-mode:tournament.
agent-arena-judgeEvaluate agent-arena submissions against a supplied frozen task, rubric, hard gates, and evidence. Use for arena judging and final validation.
Harness-native ECC operator layer - 68 agents, 286 skills, 94 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
200 skills · 94 commands · 68 agents · 1 MCP server · hooks
Expose the plugin-safe Claude Code subset of Agentic Awesome Skills through a single marketplace entry.
200 skills
Specialist Council: 60 role agents with per-role model/effort and arena-forged members; assembles teams and delivers one verified result.
2 skills · 60 agents · hooks
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
37 skills
Token usage tracking, model cost attribution per agent, budget alerts, and optimization recommendations
24 skills · 1 command · 1 agent · hooks
Talk like caveman. Cut 65% output tokens vs unprompted baseline (measured). Keep all technical accuracy.
20 skills · 1 command · 3 agents · hooks
Tenant-isolated AI teams that plan work, coordinate tasks, recall approved context, and return evidence-backed results
6 skills · 6 commands · 4 agents · 1 MCP server
Write accurate Pydantic AI code from the start. Up-to-date patterns, decision trees, and common gotchas for agents, tools, structured output, streaming, and multi-agent apps.
Orchestrate multi-agent teams for parallel code review, hypothesis-driven debugging, and coordinated feature development using Claude Code's Agent Teams
6 skills · 7 commands · 4 agents
Claude Code native multi-agent orchestration with intelligent model routing across agents and skills. Zero learning curve. Maximum power.
85 skills · 20 commands · 19 agents · 1 MCP server · hooks
Multi-agent collaboration — spawn N parallel subagents that compete on code optimization, content drafts, research approaches, or any task that benefits from diverse solutions. 7 slash commands (/hub-init, /agenthub:spawn, /hub-status, /agenthub:eval, /agenthub:merge, /agenthub:board, /hub-run), agent templates, DAG-based orchestration, LLM judge mode, message board coordination.
8 skills · 1 agent · hooks
Agent coordination and meta-programming - multi-agent orchestration, workflow automation, and safe refactor governance. Works best with other voltagent plugins installed.
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.