{"id":77627,"plugin_id":"plugins_6ae8cbe5a6708191b99fec2318f2e009","kind":"skill","collection_source":"plugin_package","comparison_source":null,"observed_at":"2026-11-03T00:15:25.111Z","digest":"093cf78f64f62f1a0c5b42aefe7ec58c33cf088e015cfb29c8b54f784de4e09a","against":null,"payload":{"description":"Coordinate genuine specialized coding, UX, security and verification subagents for a substantial MCP build when the host supports multi-agent delegation; fall back to one-agent execution otherwise.","included_files":[],"name":"orchestrate-agents","skill_md_contents":"---\nname: orchestrate-agents\ndescription: Coordinate genuine specialized coding, UX, security and verification subagents for a substantial MCP build when the host supports multi-agent delegation; fall back to one-agent execution otherwise.\n---\n# Specialist execution for MCP projects\n\n1. Inspect agent tools. If actual subagents are unavailable, do NOT fabricate delegation or claim multiple models executed. Use a serial workflow and a single integrator.\n2. Appoint a lead integrator that owns accepted requirements, task graph and final test evidence. Choose specialists only when they can independently contribute: architecture/tool contracts, UI/UX, implementation, security review, protocol QA.\n3. Delegate discrete tasks with inputs, objective, allowed files/tools, expected artifacts, test requirements and budget. Give review agents read-only scope. Separate concurrent code edits by files or worktrees.\n4. Freeze public tool contracts before parallel implementation. The lead integrates outputs and resolves conflicts. No agent can self-certify its own security or quality.\n5. Request a structured handoff: artifacts, edits, commands executed, observed results, risks, blockers. Validate that reports match actual filesystem and test evidence.\n6. Use a bounded review → repair → re-test loop. Prioritize broken behavior, unauthorized writes, broken keyboard/UI flows, then aesthetics.\n7. External publishing, secrets, network modifications and significant charges require appropriate user approval. Honor the actual host permission system.\n\nRead `../../references/orchestration.md` and `../../references/execution-model.md`. Do not invent agent APIs; use tools available in the host and current SDK docs.\n"},"changes":[],"summary":"First saved snapshot. No earlier version is available for comparison.","summary_kind":"deterministic","summary_metadata":{}}