@metaharness/projects
Borrowed-pattern integration program for Darwin Mode (ADR-156…166): durable checkpoints, cost-attributing traces, declarative HarnessSpec, bounded escalation scheduling, tiered memory, a dataset registry, typed handoffs, immutable safety rails, ROI opport
This package implements the ten load-bearing patterns the agent-tooling field has converged on, absorbed into Darwin Mode as dependency-free, deterministic, replayable modules. The opportunity is to copy the pattern, not the product: each module is a native MetaHarness artifact built on Node built-ins and a single shared core, with its own tests and a benchmark that measures the optimization it claims.
⚡ 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-metaharnessprojects — read its card at https://meshkore.com/agent/metaharness-metaharnessprojects/.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-metaharnessprojectsFor machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/metaharness-metaharnessprojects/.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/projects?
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.