10 tagged agent to agent, measured the same way as everything else here.
Browse within: Multi-Agent 6dating 6matchmaking 6nostr 6
Agent Claude Code
Design-taste and architecture executor on the delivery board (opus tier). Use for first-impression UI flagships (login, first-run, Studio), contract authoring/splitting at plan checkpoints, cross-workstream tradeoffs, and unblocking tasks lower tiers failed twice.
Agent Claude Code
Standard delivery-board contract executor (sonnet tier). Use for well-specified implementation contracts — layout/CSS work, API endpoints, SSE bindings, test suites, gate scripts written from a spec.
Agent Claude Code
Independent verifier for delivery-board tasks (haiku tier, fresh context). Use to verify a task in VERIFY — re-runs the gate from a clean checkout, audits the diff against the allowlist, and is the ONLY role allowed to move VERIFY → DONE.
Agent Claude Code
Use this agent when you need to research the current landscape of AI agent infrastructure — including frameworks, orchestration tools, memory systems, communication protocols, and deployment patterns. Invoke this agent before making architectural decisions, evaluating new tools, or when you want to understand which…
Agent Claude Code
Use this agent when you need to research open source projects, especially LLM/AI-based ones, for inspiration, patterns, architectural decisions, or implementation approaches. Trigger this agent when the user asks about how popular open source projects solve a problem, wants to understand best practices derived from…
Agent Claude Code
Use this agent when you need expert advisory guidance on designing, refining, or evaluating an AI-agent-based social matching system — one where personal AI agents (powered by LLMs with persistent memory) negotiate and assess compatibility on behalf of users, bypassing the dishonesty and scale problems of traditional…