Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/bdmorin/the-no-shopnpx agentmods add skills/bdmorin/the-no-shop/cdp-cliWrote 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/bdmorin/the-no-shop/cdp-cli)<a href="https://agentmods.dev/skills/bdmorin/the-no-shop/cdp-cli"><img src="https://agentmods.dev/badge/skills/bdmorin/the-no-shop/cdp-cli/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/bdmorin/the-no-shop/cdp-cli"><img src="https://agentmods.dev/badge/skills/bdmorin/the-no-shop/cdp-cli.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 | $0.00053 | $0.00981 |
| Opus 5.5 | $0.00021 | $0.00392 |
| Sonnet 5.5 | $0.00011 | $0.00196 |
| Haiku 4.5 | $0.00005 | $0.00098 |
Grade A, and why
cdp-cli 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 1mo 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.
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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cdp-cli — Session Rider for Chromium Browsers
Connect to a running Chromium browser (Brave, Chrome, Edge, Arc) via Chrome DevTools Protocol. Access all authenticated sessions — Gmail, Slack, Hostinger, whatever the user is logged into — without credentials or re-authentication.
No MCP. No Playwright. No extension. Pure CDP over WebSocket.
Setup
The browser must be running with --remote-debugging-port=9222. Use cdp-cli ensure to auto-detect and relaunch on macOS:
cdp-cli ensure
Or launch manually:
open -a "Brave Browser Beta" --args --remote-debugging-port=9222
One-time dependency install:
bun add puppeteer-core
Commands
cdp-cli tabs # List all open tabs (title + URL)
cdp-cli content <match> # Extract text from matching tab
cdp-cli links <match> # Extract all links from matching tab
cdp-cli screenshot <match> [path] # Screenshot matching tab
cdp-cli eval <match> <js> # Run JavaScript in matching tab
cdp-cli navigate <match> <url> # Navigate matching tab to a URL
cdp-cli ensure # Ensure browser has CDP enabled (macOS)
The <match> argument finds a tab by case-insensitive substring on title or URL. Use "first" for the first tab, or a number for tab index.
When to Use This vs Playwright Skill
| Need | Use |
|---|---|
| Access a site the user is logged into | cdp-cli — rides existing session |
| Scrape a public URL | Playwright skill — headless, no session needed |
| Screenshot a deploy for verification | Either works — cdp-cli if already open |
| Fill forms on unknown sites | Playwright skill with Stagehand |
| Read content from user's open tabs | cdp-cli — already loaded, sub-second |
Examples
# What tabs are open?
cdp-cli tabs
# Get the inbox count from Gmail
cdp-cli eval "gmail" "document.title"
# Extract article text from a tab
cdp-cli content "medium.com"
# Screenshot the Hostinger dashboard
cdp-cli screenshot "hostinger" ./tmp/hostinger.png
# Get all links from a GitHub PR
cdp-cli links "github.com/pull"
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.
- 1mo ago First seen · 107 lines · 53 tokens per session scan A 7e3f5c2ecb57
cdp-cli is a skill published in the GitHub repository bdmorin/the-no-shop (10 stars, last pushed 7mo ago), licensed MIT. It adds 53 tokens to every session and 981 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
vast-ai-gpu-cloud
Safely inspect and operate Vast.ai marketplace instances with the vastai CLI, live offer data, and explicit approval before paid or destructive actions.
wrench
Use Wrench to give a bring-your-own coding agent bounded, local-first web capabilities: capture or scrape public and signed-in web pages into Markdown; archive authorized audio, video, and transcripts with verification; query encrypted cached email, contacts, inbox, and messaging views; resolve a live conversation…
fuse-browser-usage
Use when about to call any mcpfuse-browser tool. Routes fetch/crawl/SERP vs live browser session vs screenshot capture, and enforces the 4 ZERO-TOLERANCE rules -- read BEFORE the tool call.
flow
Verify a code change end-to-end in the current worktree: identify what changed, run the relevant tests, get the app running, drive a browser over the affected areas, and report a verdict with screenshots. Generic across project types (Laravel/Herd, Node/bun, frontend, CLI, library). Use when the user wants to…
qprobe
QUESTPIE Probe — dev testing CLI for AI coding agents. Start servers, test APIs, control browsers via agent-browser, record and replay regression tests with zero tokens. Use when testing web apps, starting dev servers, reading logs, debugging errors, making API calls, checking browser console/network, or composing…
imaging-data-commons
Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index. Use for accessing large-scale radiology (CT, MR, PET) and pathology datasets for AI training or research. No authentication required. Query by metadata, visualize in browser, check licenses.