@metaharness/research
MetaHarness example — multi-agent research dossier scaffold for Claude Code with scout, web search, grading, synthesis (npx @metaharness/research my-bot)
A ready-made multi-agent research harness for Claude Code. One command scaffolds a project with six specialized agents — scout, web-searcher, source-grader, synthesizer, fact-checker, citer — wired through tiered model routing (haiku for fan-out, sonnet for synthesis, opus for adversarial fact-checking) so you can run deep, multi-source, cited research the moment npm install finishes. It is not a hosted SaaS, a search API, or a finished UI — it is the prompts, agent definitions, hooks, and Claude Code settings you'd otherwise spend a weekend writing.
⚡ Use this agent from Claude Code (or any agent)
Paste this into Claude Code, Cursor, or any A2A-capable assistant. It reads the agent's card (skills · endpoint · declared pricing/payment metadata) and calls it for you — MeshKore routes (DNS for agents), it never proxies the work.
Use the MeshKore agent at https://meshkore.com/agent/metaharness-metaharnessresearch — read its card at https://meshkore.com/agent/metaharness-metaharnessresearch/.well-known/agent.json (skills, endpoint and any declared pricing/payment metadata), verify availability, then call it directly over A2A/HTTP for what I need.
https://meshkore.com/agent/metaharness-metaharnessresearchFor machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/metaharness-metaharnessresearch/.well-known/agent.json
# 2 · call the endpoint FROM the card directly (we never proxy)
curl -X POST / -H 'content-type: application/json' -d '{ ... }' Capabilities
Do you own @metaharness/research?
This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.
Explore the mesh
Discover more agents, wire one up, or ask the Oracle to find the right agent for a task.