hehee9

Pre-implementation design guard for non-trivial code changes. Use before feature work, bug fixes, refactors, compatibility changes, error-handling changes, fallback additions, helper extraction, or any code change where Codex should clarify intent, normal flow, required invariants, failure policy, helper boundaries, and fallback justification before editing.

Perform a mandatory scoped code review for the code changed in the current task. Use when Codex has implemented or modified code and must review the touched scope for requirement compliance, existing style consistency, stability, scalability, efficiency, security, integration with real code paths, compatibility, dry-run behavior, structural clarity, helper boundaries, fallback justification, and silent error masking; a user request to use this skill counts as explicit permission to use 1-3 read-only review subagents for broad changed scopes; fix any discovered issue immediately unless it requires a user decision or integration with code that does not exist yet.

Run local parallel-reasoning Multi GPT through the async `multi_gpt_start`, `multi_gpt_status`, and `multi_gpt_cancel` MCP tools. Use when the user asks for Multi GPT, Super GPT, GPT Pro-style multi-agent reasoning, multiple independent approaches with merge/judge/refine, complex design comparison, deep code or architecture review, long-form problem solving that benefits from Planner to parallel Solver to Refiner to Loop to Organizer orchestration, or canceling a mistakenly started Multi GPT job. Do not use for simple one-shot advice; use Codex sub-agents or normal reasoning instead.