Agent Claude Code
Requirements analyst that turns gaps, assumptions, constraints, and follow-up work into Beads-tracked items.
15 2mo ago A 28 tokens
original MIT
luna-critic
26Agent Claude Code
An adversarial review agent that examines software work for correctness, security, regressions, and missing tests. It reports specific issues with their severity and the files involved.
11 1mo ago A 21 tokens
original MIT
luna-scout
27Agent Claude Code
A read-only codebase scout that searches source code, dependencies, and documentation, then returns structured paths and conclusions. It is described in Chinese and does not modify files.
11 1mo ago A 25 tokens
original MIT
luna-worker
28Agent Claude Code
A focused execution agent for clearly bounded coding tasks, searches, and test additions. Its description is provided in Chinese and emphasizes high-throughput work with clear boundaries.
11 1mo ago A 32 tokens
original MIT
debater
29Agent Claude Code
Formal debate participant. Constructs Toulmin-structured arguments for assigned position.
6 8mo ago A 17 tokens
original MIT
judge
30Agent Claude Code
Objective debate evaluator. Scores arguments on quality and tactical effectiveness.
6 8mo ago A 14 tokens
original MIT
Agent
Use for server-side Python work in FastAPI, Django, Flask, and other established services: HTTP APIs, business logic, authentication, data access, PostgreSQL, migrations, workers, realtime communication, caching, object storage, external integrations, generated documents, observability, and backend tests. Not for data…
2 11d ago A 88 tokens
original MIT
Agent
Use for client-facing React web applications and client React layers inside full-stack frameworks: pages, components, forms, interactions, accessibility, browser data, API integration, PWA and offline behavior, realtime UI, rich content, visualizations, frontend tests, and incremental refactoring. Not for React…
2 11d ago A 85 tokens
original MIT
Agent
Use for server-side TypeScript work in Node.js applications: NestJS, Express, Fastify, Next.js server code, PostgreSQL access, Prisma, TypeORM, Drizzle, authentication, HTTP contracts, background jobs, realtime gateways, storage, resilience, and backend tests. Not for Python services, substantial client-only React UI…
2 11d ago A 83 tokens
original MIT
council-seat
34Agent Claude Code
A single anonymized seat on the Elenchus council — a thin sandbox the chairman dispatches in parallel, one per model tier (Fable/Opus/Sonnet/Haiku). Its persona, round, and exact output schema arrive INSIDE the chairman's dispatch prompt (composed from the engine's seat-base + tier adapter + the front end's round…
2 16d ago A 90 tokens
Agent
A single browser-verification seat for the finishing-implementation-elenchus skill — a thin, report-only sandbox the chairman dispatches (one at a time, pinned to a model tier) to drive the running app via Playwright MCP and report which acceptance-checklist items PASS / FAIL / need a human / are MISSING. It NEVER…
2 16d ago A 106 tokens
tui-verifier
36Agent
A single terminal-render verification seat for the elenchus-tui skill — a thin, report-only sandbox the chairman dispatches (one per breakpoint, in parallel, pinned to a model tier) to drive a pure-ASCII TUI mockup inside its OWN isolated tmux session and report whether its assigned breakpoint renders cleanly: PASSED…
2 16d ago A 135 tokens
Agent Cursor
MODE and SPECDIR are passed by the orchestrator.
2 27d ago A 0 tokens
original MIT
Agent Cursor
Turn DB schema JSON + stack into persistence-layer skeleton only (entities, DbContext, schema.prisma append, etc.). No HTTP layer, no src/features/ product code, no task files.
2 27d ago A 0 tokens
original MIT
qa-agent
39Agent Cursor
The orchestrator (/ship) passes a MODE flag and the corresponding feature root.
2 27d ago A 0 tokens
original MIT
Agent
Use when selecting, benchmarking, or tuning Ollama models on constrained edge hardware; analysing LLM inference performance and context window behaviour; designing or evaluating prompt injection detection approaches; or producing model research documentation. Produces research notes, configuration recommendations, and…
2 15d ago A 68 tokens
Agent
Use when building or modifying server-side services, REST or GraphQL APIs, background workers, CouchDB data models, or Go microservices. Covers Node.js/TypeScript and Go implementations.
2 15d ago A 42 tokens
Agent
Use when building or modifying UI components, pages, client-side state, web performance, accessibility, or browser-facing TypeScript. Covers React/Next.js with TypeScript.
2 15d ago A 38 tokens