knowtation / rules
Cursor rule1 starsChanged 2 months agoMITView on GitHub
Tier 1/2/3 decision authority — when to act vs ask (policy/tiers.yaml)
- Commits and pushes
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/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/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 tier-authority.mdc into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is 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.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 14
Run tests; update .gitignore / .museignore
≈ “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: Tier 1/2/3 decision authority — when to act vs ask (policy/tiers.yaml)
alwaysApply: true
---
# Decision authority tiers
Machine-readable source: `policy/tiers.yaml`. Standing Decisions: `{{docs.standing_decisions_path}}`.
## Tier 1 — just do it (no per-time ask)
- Feature-branch commits (docs **or** code) — SD-1
- `git push` to feature branch, open feature-branch PR — SD-17
- Run tests; update `.gitignore` / `.museignore`
- Governance sync doc updates in the closing commit — SD-17
- **Finish-mode land hygiene after BV `pass` (SD-21):** Muse merge/cherry-pick →
`{{vcs.git.main_branch}}` → `muse-bridge-deploy` → merge **green**
`{{vcs.git.mirror_branch}}` → GitHub `{{vcs.git.main_branch}}` when the diff has
**no** live posture/env flip, secrets, real money, or Delegation write env
**Never** Tier 1: staging push, live posture flips, secrets/money/data deletion,
feature→GitHub-`{{vcs.git.main_branch}}`, or `git push {{vcs.git.remote}} {{vcs.git.main_branch}}`.
**Land closeout (PMHF):** land is incomplete until land-b post-merge sync — never claim
"land complete" while `ok land-closeout` fails.
## Tier 2 — recommend, confirm once, record
- Persistence shape, adapter contracts, schema-version choices
- Record the decision in `{{docs.standing_decisions_path}}` (append-only ADR log)
## Tier 3 — stop for operator authorization
- Merge to `{{vcs.git.main_branch}}` **outside** SD-21 land hygiene
- `muse push {{vcs.muse.staging_remote}}` when applicable
- Live capability / posture gate flips
- Real payments, secrets, data deletion, cross-repo merges
## VCS regime: {{vcs.regime}}
| Regime | Extra hard stop |
| --- | --- |
| `muse+git-mirror` | Muse `{{vcs.git.main_branch}}` before GitHub; mirror via `{{vcs.git.mirror_branch}}` only (SD-14). SD-21 still uses that path. |
| `muse-only` | Never run `git` / `gh` in this repo |
| `git-only` | Never `git push {{vcs.git.remote}} {{vcs.git.main_branch}}` without Tier 3 (unless SD-21 criteria met for that regime’s land path) |
A **dirty tree at session end is a failure**, not a safe default.
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.

