ShipGuard

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.

Use when UI changes need visual verification — after an audit or process check flags routes, after frontend edits, or on demand to run or re-run the project's visual test manifests.

Use when a change is ready to ship — before a PR or release — and the user wants the full ShipGuard verification (audit, behavior, visual, review) run on it.

Use when a project needs visual test manifests created or refreshed — before the first visual run, after UI routes change, or when sg-visual-run reports uncovered routes.

Use after visual runs, code audits, or process checks when results need human review — builds and serves the interactive ShipGuard dashboard.

Use when the ShipGuard review dashboard server should be shut down after a review session — stops the sg-visual-review HTTP server via its PID file, with a port-based fallback.

Use after visual runs, screenshot capture, frontend PRs, or before stakeholder review — creates the durable ShipGuard before/after report for UI-visible changes.

Use after an audit, visual run, or debugging session when learnings should be captured — records local hints and mistakes, and proposes sanitized improvement issues.

Use when looking for techniques to improve ShipGuard itself — researches GitHub and similar tools and files scored proposals from the ShipGuard checkout.

Use when a human has annotated screenshots in the ShipGuard review dashboard and exported a fix manifest — applies the requested UI fixes and captures before/after evidence.

Use when a user flow should be captured by demonstration — records browser interactions with Playwright into a replayable ShipGuard visual test manifest.

Use when code has changed and needs a bug audit before shipping — after a feature, before a PR, or on demand for any scoped path. Emits structured findings consumed by the ShipGuard pipeline.

Use after editing backend or pipeline code, before shipping, or when asked whether a diff changes observable behavior — verifies before/after process behavior without requiring the stack to run.