core

Workflow for the rest of tasks: lightweight documentation, build, track, synchronize, etc.

Phase 3 Code Analysis of aqa-flow

Phase 1 Data Collection of aqa-flow

Phase 2 Requirements Clarification of aqa-flow

Phase 4 Selector Identification of aqa-flow

Author and adapt prompts — discover, draft, deliver — under HITL approvals. Full subagent.

Architect solution, transform intent into reliable tech specs, etc. Full subagent.

Discover project context, patterns, affected areas, dependencies, etc. Lightweight subagent.

Implement and test to high quality under the orchestrator-assigned identity. Full subagent.

Run simple commands, collect and summarize results to protect parent context. Lightweight subagent.

To orchestrate parallel coding-agent farms (Claude, Codex, Copilot, Gemini, etc.) on isolated git worktrees.

To author, register, and test Rosetta hooks, add a SemanticKind, or debug a hook that won't fire.

To author, adapt, review, and validate prompts (skills, agents, workflows, rules, etc.) with brief, contracts, and a validation pack.

To implement features, fix bugs, and refactor with KISS/SOLID/DRY and systematic validation.

Rosetta CRITICAL MUST skill. MUST activate when action or its consequence is potentially dangerous, potentially irreversible, potentially destructive, or HIGH RISK. MUST activate when consequence MAYBE dangerous even if action itself seems safe. This is enterprise environment — the cost of dangerous activities is EXTREMELY HIGH, recovery may be impossible, and blast radius may affect production, shared environments, or other teams. If there is even a remote chance - load the skill.

1 hook across 1 event