Automated README summary
Automatically summarized from the README on 24 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A plugin for CodeBuddy Code, Claude Code, and pi that audits subagent task text against configurable JEV questions before dispatch, blocking or warning on violations and failing open on errors.
How it uses Jev
Before a subagent starts, the task text is evaluated against configured rule sets in one typed Jev call using per-rule probability questions with below/above thresholds. Any hit blocks the dispatch with per-rule reasons; errors fail open to allow.
Primitives:score
Technique worth stealing
Gate agent dispatch by asking calibrated per-rule probability questions on task text and blocking on threshold hits, failing open on errors.
Try it
Clone the repo, install for your host (e.g. `pi install ~/subagents-jev`), then configure rules with the bundled skill.
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 material0.82
- Shows a System One patternFound in material0.94
- Describes handling uncertaintyFound in material0.96
- Reports measured numbersnot found in the excerpt0.02
- Is a runnable toolFound in material0.98
- Top-10 learning shortlist signalFound in material0.62
- Is a replica of the modelnot found in the excerpt0.09
- Solves a common problem (0–2)score on a 0–2 scale1.50 / 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 24 Oct 2026.