Browserless JavaScript Runner

What it does

When your agent uses it

• Computing a result from page JavaScript without launching a browser
• Running environment-probing scripts quickly and reproducibly in a sandbox
• Extracting state embedded in a page's JavaScript
• Checking what a script does with a simulated browser environment

Example prompts

• “Run the script in challenge.js in the sandbox and print the value it computes.”
• “Use js-run to execute this page's inline JavaScript and extract the embedded state object.”
• “Show me how to call JsRun from Python on an HTML file and a script file.”
• “Run the js-run test suite and report whether it meets the speed gate.”

Requirements

• Python 3.10 or newer
• The `mini-racer` package (`pip install mini-racer`)

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

1. 1产物只当线索不当正文：网络数据在垫片里没有真源，页面 JS 拿到的任何
2. 2反爬对抗谨慎：本车道用于已授权/自有场景的通行证计算；对第三方站点的
3. 3考卷驱动生长：环境面只按 tests/fixtures/ 里的真实考卷长，不为想象中的

What it can do on your machine

Read from SKILL.md and the folder at commit a6657b0. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 2 files in scripts/ (Python and JavaScript), which the agent can run.

  Shell commands in SKILL.md call:

  • python3
  • pip

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Browserless JavaScript Runner loads about 400 tokens when it runs. Until then it costs about 67 tokens; SKILL.md has 72 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~67

When it runs · the whole SKILL.md, loaded when a task matches

~400

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from taxueseek/argo at commit a6657b0, republished under its MIT licence (© taxueseek). 72 words, ~400 tokens.

name

js-run

description

js-run 是 argo 的 JS 运行时车道子技能：不开浏览器跑网页 JS。基于 mini-racer（ISC） + 自研浏览器环境垫片，让「环境探测 + 纯计算」型网页脚本（反爬挑战通行证、混淆数据 解算、JS 内嵌状态提取）在毫秒级、可复现、无真实网络的沙箱里执行。定位是取数链 curl_cffi 与渲染级之间的「算」车道，不替代浏览器（登录态/视觉/真实网络数据不在此车道）。 v0 为独立骨架，未接入主链。Triggers include 跑网页JS、挑战脚本、通行证、JS解密、 逻辑时间、无浏览器执行。

metadata.version

0.1.0

metadata.date

2026-10-03

metadata.parent

argo

metadata.upstream

原创（底座 py-mini-racer ISC；设计参照 iv8 思路，未使用其代码/二进制）

metadata.license_note

底座 mini-racer 为 ISC；本目录代码为原创

import sys; sys.path.insert(0, "sub-skills/js-run/scripts")
from jsrun import JsRun

with JsRun() as jr:
    jr.run(open("challenge.js").read())     # 跑目标脚本
    jr.advance(3000)                         # 逻辑时间推进
    cookie = jr.get_cookie()                 # 收通行证

python3 tests/test_jsrun.py   # 7 项金标测试（含速度门 <100ms，实测 P50 1.0ms）

© taxueseek, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files (scripts) in sub-skills/js-run of taxueseek/argo.

• SKILL.md
• scripts/jsrun.py
• scripts/shim.js
• tests/fixtures/challenge_like.js
• tests/test_jsrun.py

Open the folder on GitHubat commit a6657b0