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 packaged oh-my-pi (omp) configuration for developers: installs public plugins and skills, wires model roles and fallback chains, and adds a Jev Router that routes work to the smallest capable model.
How it uses Jev
Jev judges each main prompt and every proposed task subagent call. For main turns, Jev returns tier, complexity, safe-downgrade, and blast-radius scores; only when all conservative gates pass does the turn run on @smol, otherwise @default. For subagents, Jev classifies work as mechanical, bounded, reasoning, or architecture and picks the matching jev-* role; risky changes are floored to architecture. Fails open on error or timeout.
Primitives:choicescore
Technique worth stealing
Use calibrated Jev scores behind conservative thresholds to downgrade only when every gate passes, failing open to the default model.
Try it
npx omp-maestro (or npx omp-maestro anthropic / openai), then log in and set 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 projectnot found in the excerpt0.28
- Shows a System One patternnot found in the excerpt0.17
- Describes handling uncertaintynot found in the excerpt0.05
- Reports measured numbersnot found in the excerpt0.02
- Is a runnable toolFound in material0.98
- Top-10 learning shortlist signalnot found in the excerpt0.24
- Is a replica of the modelnot found in the excerpt0.25
- Solves a common problem (0–2)score on a 0–2 scale1.05 / 2
- About JevFound in material0.93
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.