Automated README summary
Automatically summarized from the README on 11 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
Master-JEV Hook is a local service that connects Claude Code, Claude Desktop and Codex to JEV, TypeSafe's decision engine, through an MCP server. It lets agents delegate explicit choices to JEV and logs every query in a local dashboard.
How it uses Jev
JEV decides between options the agent already raised: which approach, source, or next action to take; labeling items in batch; checking whether a passage satisfies a condition; scoring risk, quality or urgency; and triaging items. The gateway builds Choice, Score or Noul questions, queries the TypeSafe API, applies risk thresholds, and returns accepted, abstain or fallback results to the MCP adapter.
Primitives:choicescorenoul
Technique worth stealing
Risk-based confidence thresholds (0.65/0.80/0.90) with abstain fallback, so low-confidence JEV answers are never used.
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 material0.92
- Shows a System One patternunclear0.49
- Describes handling uncertaintynot found in the excerpt0.06
- Reports measured numbersnot found in the excerpt0.05
- Is a runnable toolFound in material0.97
- Top-10 learning shortlist signalnot found in the excerpt0.38
- Is a replica of the modelnot found in the excerpt0.03
- Solves a common problem (0–2)score on a 0–2 scale1.08 / 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 11 Oct 2026.