Automated README summary
Automatically summarized from the README on 26 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A Claude Code mod for developers who want simple prompts to cost less and hard prompts to get more power. It asks TypeSafe's Jev how hard each prompt is, then sets the model and effort to match, starting in shadow mode.
How it uses Jev
On a session's first prompt, Jev judges whether a stronger tier is needed (0.5) or a weaker one will do (0.8), fixing the model for the session. Every prompt, Jev scores effort from low to max; the result is adjusted for continuation, failure, and risky actions, then clamped to min_effort/max_effort and the model's limits.
Primitives:choicescore
Technique worth stealing
Use a fast judgment model to route model tier once per session and effort every turn, with shadow mode to validate before enabling.
Try it
/plugin marketplace add KevinYu1580/jcGearbox, /plugin install jc-gearbox@jc-gearbox, then run /jcGearbox-setup.
Model judgments from README excerpts
Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.
Models & evaluation dates
- Inclusion gate
jev-1.14.0- Project signals
jev-1.14.0- Category
jev-1.14.0- Pattern tags
jev-1.14.0
Evidence
These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.
- Jev is core to the projectFound in material0.92
- Shows a System One patternunclear0.58
- Describes handling uncertaintynot found in the excerpt0.03
- Reports measured numbersnot found in the excerpt0.02
- Is a runnable toolFound in material0.87
- Top-10 learning shortlist signalnot found in the excerpt0.26
- Is a replica of the modelnot found in the excerpt0.02
- Solves a common problem (0–2)score on a 0–2 scale1.03 / 2
- About JevFound in material0.99
no-judgment band (0.40–0.60)
no-judgment band (0.40–0.60)
The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 26 Oct 2026.