jevbooks

← All projects

jev-auto-approve

BasmaAbouzied0/jev-auto-approve

Claude Code hook: Jev auto-approves read-only shell commands.

Automated README summary

Automatically summarized from the README on 27 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.

What it is

A Claude Code PreToolUse hook for Bash that uses Jev (TypeSafe's System One model) to auto-approve read-only shell commands in a few hundred milliseconds, while everything else still triggers the normal permission prompt.

How it uses Jev

Jev scores whether a Bash command is read-only. If Jev is confident (p >= 0.95), the hook allows it; otherwise it stays silent and Claude Code shows its normal prompt. Risky commands (rm, git push, curl, installs, redirects, sudo) and comment/injection-style text are never sent to Jev.

Primitives:score

Technique worth stealing

Threshold a calibrated probability to auto-allow only read-only commands; fail safe by staying silent on any uncertainty.

Try it

Set TYPESAFE_API_KEY, add the hook to ~/.claude/settings.json, start with JEV_AUTO_APPROVE_DRY=1.

View on GitHub

Start using Jev: API key and your first request →

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 material0.71
  • Shows a System One patternFound in material0.87
  • Describes handling uncertaintyFound in material0.98
  • Reports measured numbersnot found in the excerpt0.16
  • Is a runnable toolFound in material0.96
  • Top-10 learning shortlist signalnot found in the excerpt0.38
  • Is a replica of the modelnot found in the excerpt0.05
  • Solves a common problem (0–2)score on a 0–2 scale1.01 / 2
  • About JevFound in material0.98
Signals
Jev is core to the project0.71Shows a System One pattern0.87Describes handling uncertainty0.98Reports measured numbers0.16Is a runnable tool0.96Top-10 learning shortlist signal0.38Is a replica of the model0.0500.51Solves a common problem (0–2)1.01 / 2012

no-judgment band (0.40–0.60)

Design patterns
Fail open, fail closed0.92Funnel0.86Grey zone0.61Traffic light0.38Viewfinder0.35Check-up0.2700.51

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 27 Sept 2026.