Automated README summary
Automatically summarized from the README on 21 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
squint is a Claude Code PreToolUse hook for developers working in large files. It intercepts Read calls, asks a small fast model which chunk answers the question, and rewrites the tool's offset and limit before the file is opened.
How it uses Jev
On each intercepted Read, squint asks Jev which chunk answers the question, given the file and the request as state. Jev returns a chunk choice with a confidence score; squint uses that to rewrite the Read's offset and limit, and tells Claude what was narrowed and how to undo it.
Primitives:choicescore
Technique worth stealing
Rewrite the tool's offset and limit instead of advising the model to read less, so the saving does not depend on model cooperation.
Try it
git clone, npm install, npm run install-hook, then node dist/src/bin.js key
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 projectnot found in the excerpt0.05
- Shows a System One patternunclear0.60
- Describes handling uncertaintynot found in the excerpt0.04
- Reports measured numbersFound in material0.95
- Is a runnable toolFound in material0.95
- Top-10 learning shortlist signalnot found in the excerpt0.19
- Is a replica of the modelnot found in the excerpt0.05
- Solves a common problem (0–2)score on a 0–2 scale1.23 / 2
- About JevFound in material0.70
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 21 Sept 2026.