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 agentmods add skills/matrixages/polywise/chrome-cdpnpx skills add MatrixAges/polywise --skill chrome-cdpgit clone --depth 1 https://github.com/MatrixAges/polywiseWrote 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/matrixages/polywise/chrome-cdp)<a href="https://agentmods.dev/skills/matrixages/polywise/chrome-cdp"><img src="https://agentmods.dev/badge/skills/matrixages/polywise/chrome-cdp.svg" alt="Measured on agentmods" 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 | $0.00034 | $0.00799 |
| Opus 5 | $0.00017 | $0.00400 |
| Sonnet 5 | $0.00007 | $0.00160 |
| Haiku 4.5 | $0.00003 | $0.00080 |
Grade A, and why
chrome-cdp scanned grade A with 0 findings 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 today.
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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chrome CDP
Lightweight Chrome DevTools Protocol CLI. Direct connection via WebSocket, no Puppeteer required, supports 100+ tabs, instant connection.
Prerequisites
- Chrome (or Chromium, Brave, Edge, Vivaldi) with remote debugging enabled: open
chrome://inspect/#remote-debuggingand turn on the switch - Node.js 22+ (uses built-in WebSocket)
- If the browser's
DevToolsActivePortis in a non-standard location, setCDP_PORT_FILEto its full path
Commands
All commands use scripts/cdp.mjs. <target> is the unique targetId prefix from list output; copy the full prefix shown (e.g., 6BE827FA). CLI rejects ambiguous prefixes.
List Open Pages
scripts/cdp.mjs list
Screenshot
scripts/cdp.mjs shot <target> [file] # Default: screenshot-<target>.png in runtime directory
Only captures the viewport. If content outside the viewport is needed, use eval to scroll first. Output includes page DPR and coordinate transformation hints (see Coordinates section below).
Accessibility Tree Snapshot
scripts/cdp.mjs snap <target>
Execute JavaScript
scripts/cdp.mjs eval <target> <expr>
Note: Avoid using index-based selections (
querySelectorAll(...)[i]) across multipleevalcalls, as DOM may change between calls (e.g., after ignoring clicks, indices shift). Collect all data in oneevalor use stable selectors.
Other Commands
scripts/cdp.mjs html <target> [selector] # Full page or element HTML
scripts/cdp.mjs nav <target> <url> # Navigate and wait for load complete
scripts/cdp.mjs net <target> # Resource timing entries
scripts/cdp.mjs click <target> <selector> # Click element via CSS selector
scripts/cdp.mjs clickxy <target> <x> <y> # Click at CSS pixel coordinates
scripts/cdp.mjs type <target> <text> # Type text at current focus; works in cross-origin iframes
scripts/cdp.mjs loadall <target> <selector> [ms] # Repeatedly click "load more" until it disappears (default 1500ms interval)
scripts/cdp.mjs evalraw <target> <method> [json] # Raw CDP command passthrough
scripts/cdp.mjs open [url] # Open new tab (allows prompt per trigger)
scripts/cdp.mjs stop [target> # Stop daemon
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- today First seen · 78 lines · 34 tokens per session scan A acb2ac8d1b04
chrome-cdp is a skill published in the GitHub repository MatrixAges/polywise (659 stars, last pushed 2mo ago), licensed MIT. It adds 34 tokens to every session and 799 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other skills, from other repositories
computer-use
Read and drive native desktop applications through the accessibility layer — list on-screen apps, snapshot one window as a numbered element tree, then click / type / set a value / scroll / drag / run a named action, by element index or by screen coordinates. Use for work in a desktop app rather than a web page. Full…
feature-demo-recording
Record a demo video of a web feature from a real browser. Two modes -- a NARRATED film where measured voiceover drives the timeline (designed slides, subtitles, punch-in camera, rendered from an HTML timeline), and a SILENT evidence clip for a PR or a QA pass. Use when the user asks to record a video, demo, or screen…
web-browse
Open a REAL external web page so the user can see it in Kiro Crew's Browser panel. PRIMARY path is the browser MCP tool (drives the built-in native panel); playwright-cli is the fallback for remote/plain-browser sessions and for attached logged-in browsers. Use when the user wants to VIEW / verify / "show me" an…
web-verify
Look at your OWN front-end change before claiming it works -- navigate the loopback URL of a dev server or pod you started, screenshot the surface you changed, read the image to judge it, and embed it in chat. Three capture backends: playwright-cli (the session the dashboard Browser panel shows), the agent-browser CLI…
browser-auth
Browse sites that need a logged-in session with playwright-cli, using attach mode, saved storage state, or individual cookies. Use when a page is behind a login wall and a plain open lands on a sign-in screen.
browser-recording
Record a browser flow as a video/GIF for evidence — animations, transitions, and multi-step interactions that a still screenshot cannot prove. Drives the project's own Playwright through a bundled runner, then converts to mp4 + GIF via ffmpeg. Use when the user asks to record a demo, capture a GIF or video of the UI…