Automated README summary
Automatically summarized from the README on 23 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
An agent skill that turns the main agent into an orchestrator: it splits a job into tasks, hands each to a subagent, and picks the cheapest model (Claude Haiku/Sonnet/Opus/Fable or Codex Luna/Sol/Astra) that can do the task.
How it uses Jev
Before each handoff, route.py asks Jev how hard the task is, using the task's brief and optional fields (attempt, prev_tier, min_tier, max_tier) plus settings and topic questions. Jev's probabilities set the tier; the chosen model and reasons are returned and logged.
Primitives:scorechoice
Technique worth stealing
Calibrated tier thresholds in models.json map Jev's probabilities to the cheapest trusted model, with quality and topic weights adjusting the bar.
Try it
npx skills add danekkalivoda/jev-skill, then export TYPESAFE_API_KEY.
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 material0.90
- Shows a System One patternFound in material0.65
- Describes handling uncertaintynot found in the excerpt0.03
- Reports measured numbersnot found in the excerpt0.01
- Is a runnable toolFound in material0.99
- Top-10 learning shortlist signalunclear0.42
- Is a replica of the modelnot found in the excerpt0.02
- Solves a common problem (0–2)score on a 0–2 scale1.24 / 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 23 Oct 2026.