architect
01Agent Claude Code
Architect solution, transform intent into reliable tech specs, etc. Full subagent.
An instruction layer for AI coding agent
This repository also configures its own agents. See what rosetta tells them →
Agent Claude Code
Architect solution, transform intent into reliable tech specs, etc. Full subagent.
Agent Claude Code
Discover project context, patterns, affected areas, dependencies, etc. Lightweight subagent.
Agent Claude Code
Implement and test to high quality under the orchestrator-assigned identity. Full subagent.
Agent Claude Code
Run simple commands, collect and summarize results to protect parent context. Lightweight subagent.
Agent Claude Code
Plan execution: turn approved intent/specs into a sequenced plan scaled to size. Full subagent.
Agent Claude Code
Author and adapt prompts — discover, draft, deliver — under HITL approvals. Full subagent.
Agent Claude Code
Author, refine, and finalize requirements and specifications with traceability. Full subagent.
Agent Claude Code
Run deep research with grounded references, systematic exploration, self-validation, etc. Full subagent.
Agent Claude Code
Review artifacts against intent and contracts, recommend, etc. Full subagent.
Agent Claude Code
Validate that implementation matches intent via execution and evidence. Full subagent.
Agent Claude Code
Architect solution, transform intent into reliable tech specs, etc. Full subagent.
Agent Claude Code
Discover project context, patterns, affected areas, dependencies, etc. Lightweight subagent.
Agent Claude Code
Implement and test to high quality under the orchestrator-assigned identity. Full subagent.
Agent Claude Code
Run simple commands, collect and summarize results to protect parent context. Lightweight subagent.
Agent Claude Code
Plan execution: turn approved intent/specs into a sequenced plan scaled to size. Full subagent.
Agent Claude Code
Author and adapt prompts — discover, draft, deliver — under HITL approvals. Full subagent.
Agent Claude Code
Author, refine, and finalize requirements and specifications with traceability. Full subagent.
Agent Claude Code
Run deep research with grounded references, systematic exploration, self-validation, etc. Full subagent.
Agent Claude Code
Review artifacts against intent and contracts, recommend, etc. Full subagent.
Agent Claude Code
Validate that implementation matches intent via execution and evidence. Full subagent.
Agent Claude Code
Compares old vs new instruction outputs against original codebase, scores 8 quality categories, emits pass/fail JSON verdict for CI/CD validation pipeline.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: