kata-code / rules
Cursor rule1 starsChanged 39 days agoMITView on GitHub
pstack per-role model choices (overrides skill defaults)
In this repository21 other files it gives its agents.
- .cursor/rules/global.mdcCursor rule
- .cursor/rules/kata-code-browser.mdcCursor rule
- .cursor/rules/lifecycle.mdcCursor rule
- .cursor/rules/ponytail.mdcCursor rule
- .cursor/rules/sub-agents.mdcCursor rule
- 1passwordSkill
- astra-orchestratorSkill
- eli5Skill
- readmeSkill
- rebase-kata-upstreamSkill
- release-testflightSkill
- resolve-reviewsSkill
- show-meSkill
- test-t3-appSkill
- test-t3-mobileSkill
- thermo-nuclear-code-quality-reviewSkill
- thermo-nuclear-reviewSkill
- thermo-runSkill
- thermosSkill
- unslopSkill
- verify-katacodeSkill
The file
Files
--- description: pstack per-role model choices (overrides skill defaults) alwaysApply: true --- # pstack model configuration Provider-qualified per-role choices. Read the installed pstack provider-dispatch reference before dispatching a configured role. Every documented role remains present. `inherit-parent` and `auto` use the parent model natively and still count as one panel lane. feature, refactoring: cursor:grok-4.7@xhigh bug-fix: cursor:grok-4.7@xhigh perf-issue: cursor:grok-4.7@xhigh hillclimb: cursor:grok-4.7@medium judgment and prose: cursor:grok-4.7@high hardest tasks: claude:opus@xhigh how explorer: cursor:grok-4.7@medium how explainer: cursor:grok-4.7@xhigh why investigators: inherit-parent why synthesizer: inherit-parent reflect tooling: inherit-parent reflect judgment, divergent, synthesizer: inherit-parent arena runners: cursor:grok-4.7@xhigh, claude:fable@xhigh, codex:gpt-6-sol@max, claude:opus@xhigh arena cross-judge pool: cursor:grok-4.7@xhigh, claude:fable@xhigh, codex:gpt-6-sol@max, claude:opus@xhigh swarm workers: cursor:grok-4.7@medium architect runners: cursor:grok-4.7@xhigh, claude:fable@xhigh, codex:gpt-6-sol@max, claude:opus@xhigh interrogate reviewers: cursor:grok-4.7@xhigh, claude:fable@xhigh, codex:gpt-6-sol@max, claude:opus@xhigh
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.