---
description: Thinking sessions get the same freeze + build-verification honesty gates as roadmap loops (Check OK)
alwaysApply: true
---

# Check OK — Thinking session honesty gates

When a session is **Thinking** (Model label Thinking / thinking-high / Thinking → Auto),
the same twin gates used on ROADMAP phases apply — even if the work is **not** a roadmap
row (side research, spike, consumer experiment).

## Beginning gate (spec)

Before Auto build depends on the Thinking output, or before treating a side-check doc as
ground truth:

1. Ensure a freeze artifact exists (`frozen: true`) — roadmap PHASE doc **or**
   `docs/reviews/<date>-<slug>.md` via **`/check-ok`** / `ok check-ok --scaffold-only`
2. Run **`/freeze-review`** or **`/freeze-review-loop`** (thinking-high)
3. Mechanical gate: `ok check-ok --path <artifact>` (same engine as `ok review --freeze`)
4. Do **not** start Auto until verdict is **`pass`** (or human clears `blocked`)

## End gate (implementation)

After code/tests claim the work is done:

1. Run **`/build-verification-review`** (thinking-high; independent posture)
2. Do **not** mark DONE / “shipped” / “OK” until verdict is **`pass`**

## Operator shortcut

Anyone may type **Check OK** or **`/check-ok`** in Cursor or Claude Code. Copilot and
other assistants: paste `docs/CHECK-OK.md` or run `ok check-ok` in the terminal.
No new `docs.lanes` entry for one-offs.

## Same code everywhere

Consumers get Cursor + Claude Code skill copies via **`ok sync`**
(`.cursor/skills/**` and `.claude/skills/**`). The review engine is kit CLI
(`tools/freeze_reviewer/`) — not a per-repo fork.