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 TypeScript plugin that audits subagent tasks before they start on CodeBuddy Code, Claude Code, and pi, blocking or warning on configured violations. It also offers an optional tool permission gate for Bash, Write, Edit, and MultiEdit.
How it uses Jev
Before a subagent starts, the dispatch gate checks the task against configurable JEV questions and blocks with reasons or warns in warn mode. The opt-in permission gate uses local checks plus JEV risk/approval questions to allow, ask, or deny tool calls. All errors fail open.
Primitives:choicescore
Technique worth stealing
Gate subagent dispatch and tool permissions with configurable JEV questions, failing open on any error.
Try it
Clone the repo, install for your host, then ask your agent to use the subagent-jev skill to configure rules.
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 projectunclear0.47
- Shows a System One patternFound in material0.69
- Describes handling uncertaintyFound in material0.89
- Reports measured numbersnot found in the excerpt0.02
- Is a runnable toolFound in material0.96
- Top-10 learning shortlist signalnot found in the excerpt0.27
- Is a replica of the modelnot found in the excerpt0.11
- Solves a common problem (0–2)score on a 0–2 scale1.50 / 2
- About JevFound in material0.96
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.