# js-reverse-mcp-debugging

js-reverse-mcp-debugging points your agent at a live browser through the js-reverse-mcp server: breakpoints, call stacks, request initiators and WebSocket traffic. Useful when you need to take apart someone else's frontend.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 215 installs · ★ 9 repo stars
- Author: reason-machines
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/reason-machines/mcp-skills/tree/HEAD/skills/js-reverse-mcp-debugging/SKILL.md
- Updated: 2026-10-09
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/js-reverse-mcp-debugging

## What it does

The skill carries trigger phrases and step-by-step workflows for the js-reverse-mcp server. Its 21 tools cover script listing, regex search across sources, breakpoints placed on a text fragment inside minified code, paused-state inspection with call stack and scope, and stepping in, over or out. A second group handles traffic: the request list, the JavaScript stack that started a request, and WebSocket messages.

The browser runs headful, and the profile keeps cookies and localStorage across restarts. Anti-detection has two layers. Patchright sits at the CDP protocol level; the `--cloak` flag adds CloakBrowser with 49 patches in the binary, roughly 200MB downloaded on first launch unless you fetch it ahead with `npx cloakbrowser install`. Page JS is left alone, so there is no injected hook to give automation away. Two more flags: `--isolated` for a throwaway profile, `--browserUrl` to attach to your own Chrome at `http://127.0.0.1:9222`.

Instructions only, no browser of its own: the skill assumes the server is registered with your MCP client, either through `claude mcp add js-reverse npx js-reverse-mcp` in Claude or an `npx js-reverse-mcp` entry in the config. Nothing is callable until that exists. For anti-bot targets (Cloudflare, DataDome, FingerprintJS) the README suggests a second entry with `--cloak`, kept alongside the plain one and picked per site.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/mcp-skills --skill js-reverse-mcp-debugging -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/js-reverse-mcp-debugging/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/js-reverse-mcp-debugging/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/mcp-skills --skill js-reverse-mcp-debugging -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/js-reverse-mcp-debugging/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/mcp-skills --skill js-reverse-mcp-debugging -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/js-reverse-mcp-debugging/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install reason-machines/mcp-skills skills/js-reverse-mcp-debugging
```

2. **Manually: put the files in place**
- File: `.github/skills/js-reverse-mcp-debugging/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/mcp-skills --skill js-reverse-mcp-debugging -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/reason-machines/mcp-skills --path skills/js-reverse-mcp-debugging
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/js-reverse-mcp-debugging/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add reason-machines/mcp-skills --skill js-reverse-mcp-debugging -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/reason-machines/mcp-skills/tree/HEAD/skills/js-reverse-mcp-debugging/SKILL.md

## When to use it
- find the encryption routine inside a minified bundle
- set a breakpoint by code text instead of a line number
- read scope variables while execution is paused
- trace which script fires an XHR or fetch request
- decode the WebSocket frames a page sends

## Example prompts
- Set a breakpoint on the encryption function on this page and show me the arguments when it hits.
- Search the loaded scripts for crypto calls and tell me which one builds this request.
- Capture the WebSocket traffic on this page and walk me through the message format.

## Similar
- [browser-debugging](https://affpapa.org/en/nevibecode/skills/browser-debugging.md) — skill · 547 installs
- [reverse-engineering-tools](https://affpapa.org/en/nevibecode/skills/reverse-engineering-tools.md) — skill · 575 installs
- [frontend-testing-debugging](https://affpapa.org/en/nevibecode/skills/frontend-testing-debugging.md) — skill · 159 installs
- [jshookmcp](https://affpapa.org/en/nevibecode/mcp/jshookmcp.md) — MCP server · ★ 2123 repo stars
- [reverse-api-engineer](https://affpapa.org/en/nevibecode/skills/reverse-api-engineer.md) — skill · 1400 installs
- [mobile-debugging](https://affpapa.org/en/nevibecode/skills/mobile-debugging.md) — skill · 176 installs

From the same set: [reason-machines/mcp-skills](https://affpapa.org/en/nevibecode/by/reason-machines/mcp-skills.md) — 98 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
