Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →archive228/model-routing
Split the Plan/Act/Verify loop across three model tiers — frontier planner, cheap executor, frontier judge — via env vars read by run.sh.
Passed 21 of 21 test cases with the skill, and 8 of 21 without it.
and 15 more in the full report
14 fixed8 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.
In spec-driven workflows that use the dedicated planner model variable, what specific artifact file is drafted prior to execution?
| Checked | Without skill | With skill |
|---|---|---|
| Identifies PROMPT.md as the drafted spec artifact. | Missed | Passed |
The instructions your model reads when the skill loads.
run.sh reads three optional env vars and threads them into each claude invocation as --model. All default to unset, in which case the CLI default model is used (behaviour unchanged from a bare run).
CLAUDE_PLANNER_MODEL — reserved for /spec workflows that draft PROMPT.md up front. Not read by the current run.sh loop, but claimed here so future planner passes bind to it.CLAUDE_EXECUTOR_MODEL — used on the "do the next step" call. This is the workhorse; it runs on every iteration. Pick something cheap and fast.CLAUDE_JUDGE_MODEL — used on the /verify call. Runs once per iteration to adversarially check the executor's diff. Pick a frontier model — a weak judge is worse than no judge.planner = frontier (Opus-class, runs once at /spec time)
executor = cheap-fast (Haiku-class, runs every turn)
judge = frontier (Opus-class, runs every turn but on a small diff)
export CLAUDE_PLANNER_MODEL="claude-opus-4-7"
export CLAUDE_EXECUTOR_MODEL="claude-haiku-4-7"
export CLAUDE_JUDGE_MODEL="claude-opus-4-7"
./run.sh
A cheap executor paired with a frontier judge outperforms a frontier executor with no judge on long loops. The judge catches the executor's premature-victory claims that a mono-model run rationalises away when it runs out of context. Cost stays low because the judge only sees the diff, not the working history.
test cases passed, vs 8 / 21 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.