Sprint 7 is closed.

The goal was specialized engineering agents — architecture, code review, documentation, debugging, and onboarding — built on skills, memory, and MCP. Agents gather evidence and return structured briefings; they do not call external LLMs.

What Sprint 7 delivered

• @meronq/agents — types, registry, context gathering, runner
• Five built-in agents — architecture, code_review, documentation, debugging, onboarding
• MCP + CLI — agent_list, agent_run, meronq agent run
• Handshake — available_agents[] for discovery

Product MCP v1.2.0. Local MCP v1.18.0. agent_run is read-only in v0.

CLI

meronq agent list
meronq agent run onboarding
meronq agent run debugging --symptom "pnpm test fails"
meronq agent run code_review --pr 12

How it fits

Skills answer how (build, test, ADR). Agents answer when and why, with checklists, system guidance, and recommended skills.

Sprint 8 — Productization

Desktop app, cloud backend, team workspace, auth, and billing exploration.

Follow along

• Agents architecture
• Development blog

Read the full post on meronq.pages.dev · Source on GitHub