{
"$type": "site.standard.document",
"bskyPostRef": {
"cid": "bafyreigtyfc3ov6obkevgxzprayy4s76c7qkesigovtshzexbnli6rv7z4",
"uri": "at://did:plc:25rdn5elo5izoxrmtis34zuk/app.bsky.feed.post/3mpmpxbm2f5c2"
},
"coverImage": {
"$type": "blob",
"ref": {
"$link": "bafkreiadbsufsopibqzuof4zzpdafe37xf3rzr6g26c4b7sh2nbrqnwj4m"
},
"mimeType": "image/webp",
"size": 50820
},
"path": "/meronq/sprint-7-closed-engineering-agents-1d35",
"publishedAt": "2026-07-01T23:14:37.000Z",
"site": "https://dev.to",
"tags": [
"devtools",
"ai",
"opensource",
"engineering",
"Agents architecture",
"Development blog",
"meronq.pages.dev",
"Source on GitHub",
"@meronq"
],
"textContent": "Sprint 7 is **closed**.\n\nThe 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.\n\n## What Sprint 7 delivered\n\n * **`@meronq/agents`** — types, registry, context gathering, runner\n * **Five built-in agents** — `architecture`, `code_review`, `documentation`, `debugging`, `onboarding`\n * **MCP + CLI** — `agent_list`, `agent_run`, `meronq agent run`\n * **Handshake** — `available_agents[]` for discovery\n\n\n\nProduct MCP **v1.2.0**. Local MCP **v1.18.0**. `agent_run` is read-only in v0.\n\n## CLI\n\n\n meronq agent list\n meronq agent run onboarding\n meronq agent run debugging --symptom \"pnpm test fails\"\n meronq agent run code_review --pr 12\n\n\n## How it fits\n\nSkills answer _how_ (build, test, ADR). Agents answer _when_ and _why_ , with checklists, system guidance, and recommended skills.\n\n## Sprint 8 — Productization\n\nDesktop app, cloud backend, team workspace, auth, and billing exploration.\n\n## Follow along\n\n * Agents architecture\n * Development blog\n\n\n\n**Read the full post on meronq.pages.dev** · Source on GitHub",
"title": "Sprint 7 closed: Engineering Agents"
}