Run a structured scan/plan/implement/verify/review workflow inside the current parent Codex session without launching external workers or helper scripts. Use when the user wants a single-session workflow, wants to avoid subagents, or wants lower token overhead with disk-backed checkpoints and compact handoff files.
Hard plan-first contract for every coding request. Use when Codex must convert any coding request into a clarified, user-approved natural-language plan before implementation, including new features, bug fixes, refactors, direct edit requests, and follow-up changes across parent and /sub workflows.
Orchestrate one or more internal chat-session subagents for delegated implementation, review, analysis, or generation work. Use when Codex should act as a supervisor that decomposes a request, decides whether delegation is justified, chooses team size and worker roles, adapts model and reasoning per worker, runs workers serially or in parallel, preserves evidence on disk, and validates outputs before reporting back. Trigger when the user explicitly starts a request with /sub, or asks for subagents, worker teams, parallel help, delegated execution, supervisory workflows, or multi-agent delivery inside a local workspace.
Default local anti-overengineering overlay for coding work. Use to prefer the smallest complete design, surface assumptions, keep edits surgical, and define concrete verification goals without weakening local plan-first, score-tracking, or writable-scope rules.
Guides stable API and interface design. Use when designing APIs, module boundaries, or any public interface. Use when creating REST or GraphQL endpoints, defining type contracts between modules, or establishing boundaries between frontend and backend.
Tests in real browsers. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data via Chrome DevTools MCP.
Automates CI/CD pipeline setup. Use when setting up or modifying build and deployment pipelines. Use when you need to automate quality gates, configure test runners in CI, or establish deployment strategies.
Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch.