jevbooks

← All projects

jeff-vscode

saembit/jeff-vscode

Jev-powered VS Code checks: plain-English lint, stale comments, paste guard.

Verification & Guardrails0.78Runner-up: Evaluation & BenchmarkingViewfinderQuestion bank
Automated README summary

Automatically summarized from the README on 23 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.

What it is

A VS Code extension for developers that runs three checks on save: plain-English lint rules per code chunk, stale comment detection, and a paste guard for credentials, personal data and prompt injection. All decisions go through jeff-cli.

How it uses Jev

Each saved file is chunked at top-level definitions; each chunk is sent as one request with one yes/no per rule, and a probability at or over the threshold (0.7) becomes a diagnostic. Comments are asked whether they still describe the code below. Pasted text over 80 characters is asked whether it holds a credential, personal data or prompt injection.

Primitives:choice

Technique worth stealing

Write lint rules as the thing that is wrong, not the thing that is right, since Jev reads literally.

Try it

Install jeff-cli, set TYPESAFE_API_KEY, install the extension, add .jeff-lint.yaml.

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-1.14.0
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 projectFound in material0.93
  • Shows a System One patternunclear0.59
  • Describes handling uncertaintynot found in the excerpt0.06
  • Reports measured numbersnot found in the excerpt0.02
  • Is a runnable toolFound in material0.98
  • Top-10 learning shortlist signalunclear0.60
  • Is a replica of the modelnot found in the excerpt0.03
  • Solves a common problem (0–2)score on a 0–2 scale1.73 / 2
  • About JevFound in material0.99
Signals
Jev is core to the project0.93Shows a System One pattern0.59Describes handling uncertainty0.06Reports measured numbers0.02Is a runnable tool0.98Top-10 learning shortlist signal0.60Is a replica of the model0.0300.51Solves a common problem (0–2)1.73 / 2012

no-judgment band (0.40–0.60)

Design patterns
Viewfinder0.89Question bank0.83Questionnaire0.2800.51

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 23 Oct 2026.