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
A Stop hook for CodeX and Claude Code that detects multi-topic, multi-ask agent messages and forces the agent to present issues one at a time, adding context and missing info.
How it uses Jev
On the latest agent message from the Stop event, Jev answers two Choice questions: number of Asks (Zero/One/Two_or_more) and number of Points (Single_point/Two_or_three_points/More_than_three_points). Confidence-gated routing blocks the stop with one-issue-at-a-time instructions if both are Two_or_more and More_than_three_points with confidence >=0.80, or blocks with a cautious confirmation prompt if confidence >=0.50 but <0.80; otherwise allows normal stop.
Primitives:choice
Technique worth stealing
Confidence-gated routing: block only when Jev's confidence exceeds a threshold.
Try it
Copy hook file, configure TypeSafe API key and URL, enable in CodeX or Claude Code, install python-dotenv.
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 material0.61
- Shows a System One patternFound in material0.83
- Describes handling uncertaintynot found in the excerpt0.05
- Reports measured numbersnot found in the excerpt0.05
- Is a runnable toolFound in material0.97
- Top-10 learning shortlist signalnot found in the excerpt0.36
- Is a replica of the modelnot found in the excerpt0.06
- Solves a common problem (0–2)score on a 0–2 scale1.19 / 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.