Automated README summary
Automatically summarized from the README on 14 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A decision plugin that brings TypeSafe AI's Jev model to Agent Harnesses. It helps choose tools, Skills, and task owners, and score output quality, returning structured judgments and probabilities while the host Agent keeps planning and executing.
How it uses Jev
Jev answers typed questions (choice, score, noul) over a supplied state, e.g. which available Agent should own a deliverable, whether review is needed, or how clear a task is. Results return selections, probabilities, confidence, and usage; the plugin does not execute actions or switch models.
Primitives:choicescorenoul
Technique worth stealing
Keep the decision core shared and adapt it per Harness without modifying the engine or taking over the main Agent.
Try it
Install via dsh plugin add or iPolloWork import, set TYPESAFE_API_KEY, then ask Jev to check config and test connection.
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-1.13.0- Project signals
jev-1.13.0- Category
jev-1.13.0- Pattern tags
jev-1.13.0
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 material0.72
- Shows a System One patternnot found in the excerpt0.27
- Describes handling uncertaintynot found in the excerpt0.06
- Reports measured numbersnot found in the excerpt0.04
- Is a runnable toolFound in material0.98
- Top-10 learning shortlist signalnot found in the excerpt0.28
- Is a replica of the modelnot found in the excerpt0.10
- Solves a common problem (0–2)score on a 0–2 scale1.13 / 2
- About JevFound in material0.98
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 14 Oct 2026.