setup
/setup
Choose which Claude model and effort each factory tier uses (judgment, code, mechanical, panel). Detects the models available, asks for a budget, and writes ~/.claude/rules/factory-models.md, which every session loads. Use for /factory:setup or to change factory models.
- Author
- ketiyohannes ↗
- Repository
- workflows ↗
- Licence
- MIT
- Last repository change
- 04.11.2026
Assessment and security
- Files in this package
- 1
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 04.11.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
Choose which Claude model and effort each factory tier uses (judgment, code, mechanical, panel). Detects the models available, asks for a budget, and writes ~/.claude/rules/factory-models.md, which every session loads. Use for /factory:setup or to change factory models.
Original author description
Choose which Claude model and effort each factory tier uses (judgment, code, mechanical, panel). Detects the models available, asks for a budget, and writes ~/.claude/rules/factory-models.md, which every session loads. Use for /factory:setup or to change factory models.
How it works
- Tiers
- Steps
SKILL.md preview
--- name: setup description: "Choose which Claude model and effort each factory tier uses (judgment, code, mechanical, panel). Detects the models available, asks for a budget, and writes ~/.claude/rules/factory-models.md, which every session loads. Use for /factory:setup or to change factory models." disable-model-invocation: true --- # Setup Write `~/.claude/rules/factory-models.md`. Claude Code loads every `.md` file in `~/.claude/rules/` into each session, and the factory skills pass these tiers to every workflow. ## Tiers | Tier | Runs | Default | | --- | --- | --- | | `judgment` | Consolidation, critique, refutation, judging, security and architecture review, hard units | `opus high` | | `code` | Analysis lenses, conformance checks, implementation, review, proving criteria | `opus high` | | `mechanical` | Running the merge and check scripts | `opus high` | | `panel` | Competing designers, planners, and architects, one per entry | `opus high, opus high` | The workflows apply these defaults themselves, so a tier the rule file leaves out still runs on `opus high`. `opus` resolves to the newest Opus model. ## Steps 1. **Detect.** Read the `model` and `effort` values the `Agent` tool accepts in this session. Never write a value you have not confirmed is available. If you cannot detect them, ask the user which models they can use. 2. **Load.** If the rule file exists, read its current values; otherwise start from the defaults. 3. **Budget.** Ask with `AskUserQuestion`: `medium (high)` (the defaults), `large (xhigh)`, `unlimited (max effort)`, or `small (medium)`. Apply it to every tier except `mechanical`, stepping down to the highest detected effort when the target is unavailable. 4. **Confirm.** Show every tier with its value and ask whether to accept or change specific tiers. Offer the detected models and efforts, plus `inherit`, which runs the tier on the session model. 5. **Write.** Overwrite the whole file, so re-runs are idempotent, with no frontmatter: ``` # factory model configuration. One line per tier. Delete a line to use the default, opus high. # Each value is `<model> <effort>`, a comma-separated list for panel, or `inherit`. # budget: medium (high) judgment: opus high code: opus high mechanical: opus high panel: opus high, opus high ``` Tell the user the change applies to new sessions.
Versions
| Repository | Score | Licence |
|---|---|---|
| This page · ketiyohannes/workflows | 100 | MIT |
| HwangSlater/harness-fit | 100 | MIT |
| nesquikm/dev-process-toolkit | 100 | MIT |
| userKael/rastro | 100 | MIT |
| als-apg/osprey | 100 | BSD-3-Clause |
| dedujeong/gemba | 100 | Apache-2.0 |
| eigenwise/eigenwise-toolshed | 100 | MIT |
| awrshift/agent-memory-kit | 100 | MIT |
| lifecycle-innovations-limited/claude-ops | 100 | MIT |
Database snapshot: 13.11.2026 · package version 233fb12278dd (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 100model-routing
Pick the cheapest Claude model and effort level that can do each task well, and set it up in Claude Code (/model, /effort, subagent model and effort, opusplan, CLAUDE.md routing rules). Use when splitting work across models or subagents, when usage limits or cost are a concern,… - 100build-with-agents
Run a written dark-factory task to a pull request with the factory's roles as subagents of this session, instead of build.mjs. Use when the user asks to build a factory task with agents or subagents, or to run the subagent side of the factory A/B. - 100use-agent-factory
How to drive the 14-workflow agent factory in this repo from a Claude session. Covers: when to use the factory vs. direct edits, how to start the chain, where the human gates are, how to pick an implementer, how to recover from stuck PRs, and all the failure modes learned to… - 100agent-models
Show, check, and change the model and effort every agent role runs on (interactive sessions, /vet reviewers, review panels, audits, Claude subagents and Workflow agents, prun workers) through the one registry at user/agent-models.json. Use when the user asks which model… - 100model-picker
Choose the right Claude model (Haiku 5.5, Sonnet 5.5, Opus 5.5, Fable 5.2) and effort level for a task, subagent, API integration, or an app that hosts an agent through the Agent SDK. Use when the user asks which model to use, wants to cut cost or latency, is configuring… - 100setup-pstack
Configure which T3 provider and model pstack uses per role and at what reasoning budget. Detects the models T3 can run and writes the model sheet that overrides the skill defaults. Use for /setup-pstack, "configure pstack models", "pstack budget", or changing pstack's model choices.