octo-cluster / rules
Cursor rule3 starsChanged 23 days agoMITView on GitHub
Cost routing — tier first, no mid-task model switch, capped loops
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 4,329 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 repository12 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .cursor/rules/00-consumer-boundary.mdcCursor rule
- .cursor/rules/caveman-mode.mdcCursor rule
- .cursor/rules/execute-operator-intent.mdcCursor rule
- .cursor/rules/ponytail-lite.mdcCursor rule
- debugSkill
- ponytail-liteSkill
- promptSkill
- pr-reviewSkill
- shipSkill
- systematic-debuggingSkill
The file
We split this cost-routing.mdc into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Verify: focused test on changed behavior first.
≈ “Common” is an estimate: at least 1 in 5 of the 6,873 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: Cost routing — tier first, no mid-task model switch, capped loops alwaysApply: true --- # Cost routing (lite) Tier at start: L0 trivial · L1 local · L2 multi-file/tests · L3 architecture/hard bug · L4 critical. Session model: L0 haiku · L1-L2 sonnet · L3-L4 opus. Mismatch → say once at start; never switch model mid-task (full cache rebuild). Subagent only for broad fan-out search or verbose output; pass `model: haiku` for search. Else direct tools. Retry cap: 2 failed attempts, same approach → stop, show evidence, propose escalation. Verify: focused test on changed behavior first; widen only on failure. Same manual task twice → propose script or skill.
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.

