agent-infra

Use after receiving WebGPT or other LLM feedback on an agent-infra roadmap/todo and before sending the todo back for another review. Produce a concise handoff response that says what we adopted, what we reject or question, and what WebGPT should specifically re-evaluate in the todo.

Use when preparing a Formax code handoff: selecting files, generating repomix bundles, and writing a high-quality prompt for WebGPT or another coding agent with clear constraints and validation scope.

Use when implementing or reviewing changes in this repository and you need a strict, repeatable local development loop: align with repo docs, execute one mainline task at a time, run pnpm-based targeted verification, run codex review for code changes, and prepare clean commits/PR context.

Use after task analysis when a non-trivial repository task needs a structured docs/todolist.md with [x]/[ ] items, data/type/interface-first ordering, explicit non-goals, tests, and loop-ready execution slices.

Use when a repository task is non-trivial and you should analyze goals, non-goals, boundaries, data/type/interface impact, test strategy, and whether an xhigh subagent is actually needed before writing a todo or code.