This skill should be used after a change is complete — at the wrap-up of /maigo:quick, /maigo:go, /maigo:team, or /maigo:address-comments — when the current branch may already have an open GitHub PR, to check whether the PR's title/description still accurately reflects the actual diff and draft an update if it has drifted. It never runs `gh pr edit` on the user's behalf.
Repository-grounded threat modeling that enumerates trust boundaries, assets, attacker capabilities, abuse paths, and mitigations, and writes a concise Markdown threat model. Trigger only when the user explicitly asks to threat model a codebase or path, enumerate threats/abuse paths, or perform AppSec threat modeling. Do not trigger for general architecture summaries, code review, or non-security design work.