jevbooks

← All projects

goextractlint

ksinistr/goextractlint

Go CLI flags functions worth reviewing for Extract Function using Jev.

Scoring & Ranking0.44Runner-up: Evaluation & Benchmarking
Automated README summary

Automatically summarized from the README on 20 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.

What it is

A small Go CLI for Go developers that highlights functions worth reviewing for Extract Function, following Martin Fowler's intent-versus-implementation principle. It emits JSONL findings and leaves source files unchanged.

How it uses Jev

Jev evaluates each parsed Go function with bounded package context, deciding whether the function is worth extracting. The verdict (extract, keep, or insufficient_context) and optional extract_probability are written as JSONL records; API failures produce an error record.

Primitives:choicescore

Technique worth stealing

Fit bounded package context under a token limit, dropping overflow and setting context_truncated, then cache decisions by exact request, endpoint, and model.

Try it

make install, export OPENROUTER_API_KEY, then run goextractlint ./internal; or use -provider ollama.

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 material0.72
  • Shows a System One patternnot found in the excerpt0.10
  • Describes handling uncertaintynot found in the excerpt0.07
  • Reports measured numbersnot found in the excerpt0.04
  • Is a runnable toolFound in material0.98
  • Top-10 learning shortlist signalnot found in the excerpt0.17
  • Is a replica of the modelnot found in the excerpt0.07
  • Solves a common problem (0–2)score on a 0–2 scale1.51 / 2
  • About JevFound in material0.95
Signals
Jev is core to the project0.72Shows a System One pattern0.10Describes handling uncertainty0.07Reports measured numbers0.04Is a runnable tool0.98Top-10 learning shortlist signal0.17Is a replica of the model0.0700.51Solves a common problem (0–2)1.51 / 2012

no-judgment band (0.40–0.60)

Design patterns
Fail open, fail closed0.24Inspection0.2300.51

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 20 Oct 2026.