knowtation / rules
Cursor rule1 starsChanged 2 months agoMITView on GitHub
Mandatory build verification before marking Auto phases DONE (SD-3 honesty gate)
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/check-ok-thinking.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 build-verification-required.mdc into the rules it gives an agent
5 rules. About 0 are common, 0 are distinctive, and 5 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 8
After any Auto build phase ({step}b, or any roadmap row with Model: Auto), before setting the phase to DONE in {{docs.roadmap_path}}:
- Very specific: line 11
Run /build-verification-review (skill: .cursor/skills/build-verification-review/SKILL.md)
- Very specific: line 12
Use thinking-high model — independent verifier posture.
- Very specific: line 19
Before any Auto phase starts, the frozen spec must have pass freeze review (/freeze-review-loop when needed).
- Very specific: line 24
Sibling (shipped / live-health claims only): when the session claims a live deploy, production health, or "shipped" outside the local repo, …
≈ “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: Mandatory build verification before marking Auto phases DONE (SD-3 honesty gate)
alwaysApply: true
---
# Build verification — mandatory before DONE
After any **Auto** build phase (`{step}b`, or any roadmap row with **Model: Auto**), **before** setting
the phase to **DONE** in `{{docs.roadmap_path}}`:
1. Run **`/build-verification-review`** (skill: `.cursor/skills/build-verification-review/SKILL.md`)
2. Use **`thinking-high`** model — independent verifier posture; not the build session model
3. Compare the **frozen spec** (`frozen: true`) to the **actual diff**, tests, and claims in
`{{docs.handover_path}}`
4. **Do not mark DONE** until verdict is **`pass`**
5. On **`findings`**: fix only cited path:line items; re-run verification (max 5 rounds per skill)
6. On **`blocked`** or escalation (`security`, `irreversible`, `real_money`, `gates_tier3`): stop for human
Before any **Auto** phase **starts**, the frozen spec must have **`pass`** freeze review
(`/freeze-review-loop` when needed).
Tests green alone is **not** sufficient for DONE.
**Sibling (shipped / live-health claims only):** when the session claims a live deploy, production
health, or "shipped" outside the local repo, also run **`/deploy-verification-review`**
(`.cursor/skills/deploy-verification-review/SKILL.md`). Do **not** run it for ordinary kit-only
Auto builds — that would false-close non-ship phases. Build verification is never waived.
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.

