Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add blessleon/electron-cdp-automation --skill electron-cdp-automationgit clone --depth 1 https://github.com/blessleon/electron-cdp-automationWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/blessleon/electron-cdp-automation/electron-cdp-automation)<a href="https://agentmods.dev/skills/blessleon/electron-cdp-automation/electron-cdp-automation"><img src="https://agentmods.dev/badge/skills/blessleon/electron-cdp-automation/electron-cdp-automation/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/blessleon/electron-cdp-automation/electron-cdp-automation"><img src="https://agentmods.dev/badge/skills/blessleon/electron-cdp-automation/electron-cdp-automation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00091 | $0.02474 |
| Opus 5 | $0.00046 | $0.01237 |
| Sonnet 5 | $0.00018 | $0.00495 |
| Haiku 4.5 | $0.00009 | $0.00247 |
Grade A, and why
electron-cdp-automation scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl http://localhost:9222/json/version How it starts
The opening of the file, as written. The whole thing — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Electron CDP Automation
Electron embeds Chromium, so packaged apps can be launched with --remote-debugging-port, then controlled from an external Node script via CDP to inject JS and manipulate the DOM. No source code access required.
Four traps are almost guaranteed to bite you, and all look "correct" — read this through before writing code, or you'll spend hours debugging an await that can never succeed.
Step 0: Verify the Debug Port Works First (Don't Skip This)
Validate this step before writing any automation code. The app may have debugging disabled, at which point the entire CDP route is impossible — better to find out early.
# Launch (any port 9000-65535)
./YourApp.exe --remote-debugging-port=9222 --remote-allow-origins=*
# Verify in another terminal
curl http://localhost:9222/json/version
Works — returns JSON containing webSocketDebuggerUrl:
{"Browser":"Chrome/120.0.6099.109","Protocol-Version":"1.3",
"webSocketDebuggerUrl":"ws://localhost:9222/devtools/browser/..."}
Doesn't work — connection refused / timeout / app reports "unsupported parameter" / app launches normally but port doesn't listen.
When it doesn't work, inform the user CDP automation is not possible and provide alternatives. Don't try to work around it (changing ports, adding --inspect, injecting DLLs won't solve build-time disabled debugging):
❌ This app has remote debugging disabled. CDP automation is not possible.
Possible reasons: Disabled during build / Enterprise security policy / ASAR hardening.
Alternatives:
1. OS-level automation — Windows UI Automation, pyautogui, AutoHotkey
(based on coordinates and control trees, doesn't depend on debug port)
2. If you have source access, add to main.js:
app.commandLine.appendSwitch('remote-debugging-port', '9222')
For testing builds only, never ship this
3. If the app has a CLI / HTTP API, use that instead
Also remind: Never open debug ports in production — any local process can completely control the app through it.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 251 lines · 91 tokens per session scan A 9e6c8bccebea
electron-cdp-automation is a skill published in the GitHub repository blessleon/electron-cdp-automation (4 stars, last pushed 1mo ago), licensed MIT. It adds 91 tokens to every session and 2,474 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
baoyu-url-to-markdown
Fetch any URL and convert to markdown using baoyu-fetch CLI (Chrome CDP with site-specific adapters). Built-in adapters for X/Twitter, YouTube transcripts, Hacker News threads, and generic pages via Defuddle. Handles login/CAPTCHA via interaction wait modes. Use when user wants to save a webpage as markdown.
playwright-cli
Automates browser interactions for testing and validating your own web applications using playwright-cli. Use when you need terminal-first browser control for navigation, form filling, screenshots, tracing, bound browser sessions, debugging, or generating Playwright test code. Only use against applications you own or…
prime-the-agent
Use when starting a session on an existing WordPress site, or when the user says 'prime yourself', 'what builder does this site use', or 'give me a site briefing'. Loads the active site, detects the builder, loads inline schemas, reads the stored per-site brief, and sets the do-not-write-raw-HTML rule.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
setup-playwright
Use when adding, extending, or repairing a repo-owned Playwright test harness across Node Playwright Test, Playwright Pytest, or .NET/Java test frameworks. Also use when explicitly persisting @playwright/cli developer tooling, or adding or regenerating Playwright Test Agent definitions for a compatible Node Playwright…
chrome-cdp-setup
Set up Google Chrome on macOS to always launch with the Chrome DevTools Protocol enabled (127.0.0.1:9222) via a Dock launcher app, so local AI agents (Playwright, Puppeteer, browser-use, OpenClaw) can drive the real logged-in browser with no per-connection approval prompt. Use when the user wants to enable a…