#412412th of 455 in Skills, plugins and prompts

jev-browser-use

Codex skill that delegates browser clicks and scrolling to the Jev model

Stars
1.2k
License
MIT
Last commit
Oct 2026
Language
JavaScript
Stars, last 8 weeks+1,212
16 Sept 2026: 0 stars23 Sept 2026: 324 stars30 Sept 2026: 595 stars7 Oct 2026: 831 stars14 Oct 2026: 1,011 stars21 Oct 2026: 1,187 stars28 Oct 2026: 1,197 stars4 Nov 2026: 1,206 stars11 Nov 2026: 1,212 stars

0 on 16 Sept 20261,212 on 11 Nov 2026

From GitHub's daily star counts.

Checked on GitHub.

Overview

A Skill and Codex plugin that hands browser navigation, clicks, toggles and scrolling to TypeSafe's Jev model, which reads accessibility text rather than screenshots. Codex keeps text entry, visual checks and final verification. It runs inside the existing Codex Computer Use connection to Chrome or the in-app browser, with Jev accessed through TypeSafe or OpenRouter.

Who it is for: Codex users who want faster, cheaper browser automation during testing

Strengths

  • Action loop stays inside Computer Use, avoiding a host-model turn per click
  • Jev input priced at $0.042 per 1M tokens, output listed as free
  • Installs via one npx skills command or a native Codex plugin
  • Config and API keys live outside the Skill and survive updates

Weaknesses

  • Browser execution needs Codex Computer Use; Claude Code support is not yet available
  • Requires a paid Jev API key from TypeSafe or OpenRouter
  • Page text is sent to the chosen provider
  • Only exercised on macOS; 5–10x speedup is the authors' own estimate

What it needs

  • no GPU
  • Needs Node.js 22+, Codex with Computer Use, Chrome or Codex in-app browser, TypeSafe or OpenRouter Jev API key
  • Models: Jev 1.13 (TypeSafe), Jev (OpenRouter)

Also in Skills, plugins and prompts

See all 455
Also in Skills, plugins and prompts
RankProjectScore
1claude-memPersistent cross-session memory plugin for Claude Code and other coding agents116.4k stars+16,587 (+17%) in 30 daysApache-2.097 out of 100
2impeccableDesign skill with 24 slash commands for AI coding agents' frontend output Live demo ↗ (opens in a new tab)108.8k stars+28,464 (+35%) in 30 daysApache-2.097 out of 100
3gstackMarkdown slash-command skills that give Claude Code planning, review, QA and ship roles141.3k stars+5,544 (+4.1%) in 30 daysMIT96 out of 100
#4rufloAgent harness adding swarms, memory and hooks to Claude Code and Codex Live demo ↗ (opens in a new tab)81.5k stars+7,374 (+9.9%) in 30 daysMIT96 out of 100
#5cavemanShortens coding-agent replies and compresses tool output before the model reads it Live demo ↗ (opens in a new tab)119.3k stars+8,422 (+7.6%) in 30 daysApache-2.095 out of 100