knowtation / rules
Cursor rule1 starsChanged 2 months agoMITView on GitHub
Thinking sessions get the same freeze + build-verification honesty gates as roadmap loops (Check OK)
Where files are headingNew Cursor rule files have more rules about planning and tracking tasks, and fewer about code style.
Of the Cursor rule files we read, the 4,144 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository26 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .cursor/rules/build-verification-required.mdcCursor rule
- .cursor/rules/governance-sync.mdcCursor rule
- .cursor/rules/l1-checkpoints-consumer-owned.mdcCursor rule
- .cursor/rules/no-docs-only-pr-to-main.mdcCursor rule
- .cursor/rules/orchestrator.mdcCursor rule
- .cursor/rules/print-next-closeout.mdcCursor rule
- .cursor/rules/tier-authority.mdcCursor rule
- .cursor/rules/workspace-authority.mdcCursor rule
- build-verification-reviewSkill
- check-okSkill
- deploy-verification-reviewSkill
- freeze-review-loopSkill
- freeze-reviewSkill
- governance-syncSkill
- print-nextSkill
- workspace-statusSkill
- build-verification-reviewSkill
- check-okSkill
- deploy-verification-reviewSkill
- freeze-review-loopSkill
- freeze-reviewSkill
- governance-syncSkill
- knowtationSkill
- print-nextSkill
- workspace-statusSkill
The file
We split this check-ok-thinking.mdc into the rules it gives an agent
9 rules. About 0 are common, 3 are distinctive, and 6 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
When a session is Thinking (Model label Thinking / thinking-high / Thinking → Auto), the same twin gates used on ROADMAP phases apply — …
- Distinctive: line 14
Before Auto build depends on the Thinking output, or before treating a side-check doc as ground truth:
- Very specific: line 17
Ensure a freeze artifact exists (frozen: true) — roadmap PHASE doc or docs/reviews/<date>-<slug>.md via /check-ok / ok check-ok …
- Very specific: line 19
Run /freeze-review or /freeze-review-loop (thinking-high)
- Very specific: line 21
Do not start Auto until verdict is pass (or human clears blocked)
- Distinctive: line 25
After code/tests claim the work is done:
- Very specific: line 27
Run /build-verification-review (thinking-high.
- Very specific: line 28
Do not mark DONE / “shipped” / “OK” until verdict is pass
- Very specific: line 34
No new docs.lanes entry for one-offs.
≈ “Common” is an estimate: at least 1 in 5 of the 6,668 Cursor rule files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
--- 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.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

