by openqa-cn · Codex Skill · ★ 51
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is jev-browser safe to install? View the security audit →
CodexQA Jev Browser 简体中文 · How it works · Known limitations Jev Browser is one skill in CodexQA: local Agent Skills that check whether code is actually good after it is written. This repository is the standalone project. The same skill is also installed from the CodexQA catalog. GUI-model browser automation sends a screenshot to a vision model on every step. Recognition spends vision tokens, the loop waits for the model to read the image, and the click lands on coordinates. CodexQA Jev Browser finds controls from an index built inside the page and treats visible page evidence as the result. Replay, goal runs, case generation, and site exploration share that index. The browser is Playwright Chromium. This repository has no benchmark against vision GUI models. The rows below are the structural answers to those costs. On TypeSafe’s published System One comparison, a Jev decision is 40×–200× faster than a frontier LLM on the same kind of question (70–500 ms, against multi-second LLM calls). Their workflow demo is 193.6× faster and 444.6× cheaper: $0.000081 in 0.114 s versus $0.013880 in 8.566 s. TypeSafe calls that pair the high end of real-world gains.
npx codexqa-jev-browser observe examples/app/index.html
npx codexqa-jev-browser run cases/examples/search-docs.yaml cases/examples/login.yamlTaken from the project's README on GitHub. Check the security audit before running it.
No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
| Stars | 51 |
| Forks | 4 |
| Language | TypeScript |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 70.5029059759534/100 |
| Open Issues | 1 |
| Last Updated | 2026-09-28 |
| Created | 2026-09-23 |
| Platforms | browser, codex, node |
| Est. Tokens | ~17k |
Looking for a jev-browser alternative? If you're comparing jev-browser with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
QA Skills Directory QA Skills is a curated directory of testing-specific skills for AI coding agents (Claude C
Reusable project context and specialist workflows for the AI tools you already use. Agents, skills, rules and
Let Claude Code and other coding agents drive and debug Chrome from the shell. DOM, network, console and raw C
Rust CLI powered by Jev from TypeSafe.ai that ranks agent skills for the next step using live session context.
CLI, MCP server, and npm library that turns any website into an API — no docs, no SDK, no browser.
Local-first MCP plugin for continuous software-quality review by AI coding agents, powered by Jev.
Explore other popular codex skill tools:
jev-browser is Jev Browser — indexed browser automation. Jev chooses the control, Playwright acts. A CodexQA skill.. It is categorized as a Codex Skill with 51 GitHub stars.
jev-browser is primarily written in TypeScript. It covers topics such as agent-skills, browser-automation, codexqa.
The README on GitHub (github.com/openqa-cn/jev-browser) gives: npx codexqa-jev-browser observe examples/app/index.html , then npx codexqa-jev-browser run cases/examples/search-docs.yaml cases/examples/login.yaml. Usage details are in the same README.
jev-browser is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to jev-browser on Agent Skills Hub include qaskills, aiwg, browser-debugger-cli. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: