Sg Mission Lock

Lock the literal user mission and authorization level before work to prevent scope drift, inferred permission, adjacent-work expansion, plan churn, and false completion. Use unconditionally when the active model is gpt-5.6 or gpt-5.6-sol at any reasoning effort, when the user names GPT-5.6 Sol or Sol Ultra as the agent, after terse continuations such as continue/do all, after compaction or correction, and whenever review/plan/code/publish/live boundaries could be crossed.

bacoco Updated 7 repo stars
ShipGuard — Agentic AI Audit & Visual Regression

File contents

bacoco/shipguard commit 71993c67df

Frequently asked questions

npx get-skill add bacoco/sg-mission-lock