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/jerseycheese/agent-skills/browser-debugger-clinpx skills add jerseycheese/agent-skills --skill browser-debugger-cligit clone --depth 1 https://github.com/jerseycheese/agent-skillsWhat 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 | $0.00116 | $0.00456 |
| Opus 5 | $0.00058 | $0.00228 |
| Sonnet 5 | $0.00023 | $0.00091 |
| Haiku 4.5 | $0.00012 | $0.00046 |
Grade A, and why
browser-debugger-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 2d 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.
What it actually says
browser-debugger-cli (bdg)
When to use
- Query specific DOM elements or attributes
- Run targeted CDP methods without full page snapshots
- Debug with minimal token overhead
Prerequisites
- Install:
npm install -g browser-debugger-cli@alpha - Chrome available locally, or connect via
--chrome-ws-url
Common workflow
- Start a session:
bdg http://localhost:3000
- Query DOM:
bdg dom query "button"bdg dom query "[data-testid='x']"
- Discover CDP methods:
bdg cdp --listbdg cdp --search dom
- Evaluate JS:
bdg cdp Runtime.evaluate --params '{"expression":"document.title"}'
- Stop the session:
bdg stop
Notes
- Use
bdg statusorbdg peekto inspect without stopping. - Use
bdg --no-headlesswhen you need a visible browser window. - macOS tiling window managers: When using
--no-headless, tiling window managers (AeroSpace, yabai, Amethyst, etc.) will constrain the browser window's viewport to whatever space the layout assigns. Float the window after it appears using the WM's float command. Without this, viewport-dependent CSS (media queries, responsive layouts) may not match expected breakpoints. - For full page snapshots or complex automation, use Chrome DevTools MCP.
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.
- 2d ago First seen · 41 lines · 116 tokens per session scan A c51a4665af8a
browser-debugger-cli is a skill published in the GitHub repository jerseycheese/agent-skills (1 stars, last pushed 16d ago), licensed MIT. It adds 116 tokens to every session and 456 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
bird
X/Twitter CLI for reading, searching, posting, and engagement via cookies.
remote-browser
Controls an isolated Browser Use Cloud browser from a sandboxed machine with the current Browser Use CLI.
opencli-browser
Use when an agent needs to drive a real Chrome window via opencli — inspect a page, fill forms, click through logged-in flows, or extract data ad-hoc. Covers the selector-first target contract, compound form fields, stale-ref handling, network capture, and the agent-native envelopes the CLI returns. Not for writing…
opencli-adapter-author
Use when writing an OpenCLI adapter for a new site or adding a new command to an existing site. Guides end-to-end from first recon through field decoding, adapter coding, and verify. Replaces opencli-oneshot / opencli-explorer. For ad-hoc browser driving (no adapter), see opencli-browser instead; for a top-level…
cloud
Documentation reference for using Browser Use Cloud — the hosted API and SDK for browser automation. Use this skill whenever the user needs help with the Cloud REST API (v2, v3, or v4), browser-use-sdk (Python or TypeScript), X-Browser-Use-API-Key authentication, cloud sessions, browser profiles, profile sync, CDP…
open-source
Documentation reference for writing Python code using the browser-use open-source library. Use this skill whenever the user needs help with Agent, Browser, or Tools configuration, is writing code that imports from browseruse, asks about @sandbox deployment, supported LLM models, Actor API, custom tools, lifecycle…