setup-jstack
Skill2 starsChanged 8 months agoMITView on GitHub
Use when the user wants to configure Jstack's per-role Claude models.
We split this skill 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 19
Write ~/.claude/jstack-models.md, a per-role model override sheet you include from your global CLAUDE.md.
- Very specific: line 45
Every real slug written must be in the detected set.
- Very specific: line 49
Write ~/.claude/jstack-models.md with the shape below.
- Very specific: line 77
If ~/.claude/CLAUDE.md does not already include ~/.claude/jstack-models.md, append the @~/.claude/jstack-models.md line so it loads on …
- Very specific: line 88
Default panel: claude-opus-5, claude-fable-5-1, claude-sonnet-5
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill 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
Setup Jstack
On Codex, Cursor, or another non-Claude runtime, read the runtime mapping, including its per-skill notes, before following this skill.
Write ~/.claude/jstack-models.md, a per-role model override sheet you include from your global CLAUDE.md. Each Jstack skill names a default model inline; the override sheet is the layer that adapts those defaults to the models you actually have access to.
Claude Code has no auto-applied "rules" mechanism like Cursor's .mdc. Inclusion is explicit: the user adds a line to ~/.claude/CLAUDE.md (or their project CLAUDE.md) such as:
@~/.claude/jstack-models.mdso the file is loaded as context for every session.
Steps
1. Detect available models
Enumerate the model slugs you can pass to an Agent subagent in this session — that is the dependable source. The currently available Claude models and the default panel are listed in Models below; the quad is chosen for cross-family, cross-tier diversity, and the single-role default stays out of the panels because it already covers the single-model roles. Ask the user to confirm or paste any additional slugs they want available. Never write a real slug you have not confirmed is available. The aliases inherit-parent and auto are always valid even though they are not detected slugs; both mean the role runs on the parent session's model, which the Agent call expresses by omitting model.
2. Load current state
The default role-to-model mapping is the rule shape shown in step 5 below. If ~/.claude/jstack-models.md already exists, read it and treat its values as the current choices. Otherwise start from those defaults.
3. Map and confirm
Show every role with its current model, marking any real slug not in the detected set as needing a choice. Ask whether to accept as-is or change specific roles, offering the detected models plus inherit-parent and auto as the options. Prefer AskUserQuestion over free text. For panel roles (arena runners, architect runners, interrogate reviewers) the value is a list, and one subagent runs per entry, alias entries included, so the list length sets the count. arena cross-judge pool is also a list, but Arena selects one value from it whose model family differs from the parent's when possible. swarm workers is the default model for every worker unless a race or comparison assigns another model per arm.
4. Validate
Every real slug written must be in the detected set; inherit-parent and auto always pass. If a chosen real slug is not available, stop and ask again.
5. Write the override sheet
Write ~/.claude/jstack-models.md with the shape below. Overwrite the whole file so re-runs stay idempotent.
# Jstack model configuration
Per-role model overrides for Jstack skills. Each Jstack SKILL.md names its defaults in a Models section; the values here override those defaults. Delete a line to fall back to the skill default. A value of `inherit-parent` or `auto` runs that role on the parent session's model (the `Agent` call omits `model`); an alias entry in a panel list still counts toward that panel's fan-out.
feature, refactoring: claude-opus-5
bug-fix: claude-fable-5-1
perf-issue: claude-fable-5-1
hillclimb: claude-fable-5-1
judgment and prose: claude-opus-5
strongest judgment: claude-fable-5-1
how explorer: claude-opus-5
how explainer: claude-opus-5
why investigators: claude-opus-5
why synthesizer: claude-opus-5
reflect tooling: claude-opus-5
reflect judgment, divergent, synthesizer: claude-opus-5
arena runners: claude-opus-5, claude-fable-5-1, claude-sonnet-5
arena cross-judge pool: claude-opus-5, claude-fable-5-1, claude-sonnet-5
swarm workers: claude-opus-5
architect runners: claude-opus-5, claude-fable-5-1, claude-sonnet-5
interrogate reviewers: claude-opus-5, claude-fable-5-1, claude-sonnet-56. Wire it in
If ~/.claude/CLAUDE.md does not already include ~/.claude/jstack-models.md, append the @~/.claude/jstack-models.md line so it loads on every session. If the user prefers project scope, add the include to the project's CLAUDE.md instead.
7. Confirm
Tell the user where the override was written and how it loads (via the @ include in CLAUDE.md). Re-running this skill updates the override sheet.
Models
Defaults originate from the upstream plugins/pstack/models.json. Refresh them through scripts/vendor_jstack.py after reviewing the upstream change.
- Available Claude models: Opus 5 (
claude-opus-5), Opus 4.8 (claude-opus-4-8), Opus 4.6 (claude-opus-4-6), Fable 5.1 (claude-fable-5-1), Sonnet 5 (claude-sonnet-5), Sonnet 4.6 (claude-sonnet-4-6), Haiku 4.5 (claude-haiku-4-5) - Default panel:
claude-opus-5,claude-fable-5-1,claude-sonnet-5 - Single-role default:
claude-opus-5
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- juancamiloqhz/skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository93 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .cursor/rules/code-simplifier.mdcCursor rule
- .cursor/rules/tdd-verification.mdcCursor rule
- ckm:banner-designSkill
- ckm:brandSkill
- ckm:designSkill
- ckm:design-systemSkill
- ckm:slidesSkill
- ckm:ui-stylingSkill
- ui-ux-pro-maxSkill
- mission-control-agent-integrationSkill
- agent-watchdogSkill
- architectSkill
- arenaSkill
- automate-meSkill
- babysitSkill
- before-and-afterSkill
- blast-radiusSkill
- broSkill
- code-structureSkill
- create-verification-skillSkill
- deslopSkill
- evidence-driven-testingSkill
- factory-babysit-prSkill
- factory-collectSkill
- factory-human-digestSkill
- factory-lookbackSkill
- factory-recoverSkill
- factory-review-prsSkill
- factory-shipSkill
- factorySkill
- factory-watchdogSkill
- figure-it-outSkill
- fix-ciSkill
- fix-merge-conflictsSkill
- get-pr-commentsSkill
- greploop-appsSkill
- greploopSkill
- howSkill
- interrogateSkill
- maintain-verification-skillSkill
- make-pr-easy-to-reviewSkill
- mission-control-budget-controlSkill
- mission-control-deliverySkill
- mission-control-heartbeatSkill
- mission-control-record-memorySkill
- mission-control-register-agentSkill
- mission-control-request-approvalSkill
- mission-control-run-loggingSkill
- mission-control-submit-deliverableSkill
- mission-control-task-lifecycleSkill
- new-featureSkill
- no-commentsSkill
- plan-arbiterSkill
- poteto-modeSkill
- principle-attack-the-premiseSkill
- principle-boundary-disciplineSkill
- principle-build-the-leverSkill
- principle-encode-lessons-in-structureSkill
- The first 60 shown.
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.

