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 taslim/nanoclaw-gws-ea --skill browser-cdpgit clone --depth 1 https://github.com/taslim/nanoclaw-gws-eaWrote 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/taslim/nanoclaw-gws-ea/browser-cdp)<a href="https://agentmods.dev/skills/taslim/nanoclaw-gws-ea/browser-cdp"><img src="https://agentmods.dev/badge/skills/taslim/nanoclaw-gws-ea/browser-cdp/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/taslim/nanoclaw-gws-ea/browser-cdp"><img src="https://agentmods.dev/badge/skills/taslim/nanoclaw-gws-ea/browser-cdp.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 | $0.00037 | $0.00604 |
| Opus 5.5 | $0.00015 | $0.00242 |
| Sonnet 5.5 | $0.00007 | $0.00121 |
| Haiku 4.5 | $0.00004 | $0.00060 |
Grade A, and why
browser-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 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Host Browser via CDP
Real headed Chrome on the host. Use for sites that need login, persistent sessions, or have bot detection.
For simple public page lookups, use agent-browser instead (headless, faster).
Only available when $HOST_BROWSER is set (main and heartbeat groups).
Commands
browser-cdp tabs # List open pages
browser-cdp new [url] # Open new tab (optional URL)
browser-cdp go <page> <url> # Navigate to URL
browser-cdp go <page> back # Go back
browser-cdp go <page> forward # Go forward
browser-cdp go <page> reload # Reload
browser-cdp close <page> # Close tab
browser-cdp snapshot <page> # Accessibility tree (interactive elements)
browser-cdp click <page> <selector> # Click element
browser-cdp click <page> <selector> -g # Click with user gesture (fullscreen, WebXR)
browser-cdp fill <page> <text> <selector> # Clear and type into input
browser-cdp key <page> <key> # Press key (enter, tab, escape)
browser-cdp screenshot <page> # Screenshot to stdout
browser-cdp screenshot <page> --output f.png # Screenshot to file
browser-cdp eval <page> <expression> # Run JavaScript
browser-cdp console <page> # Recent console messages
browser-cdp console <page> --all # All console messages
browser-cdp network <page> # Recent network requests
Page addressing
Pages are matched by title, URL fragment, or numeric ID from browser-cdp tabs.
Output
NDJSON — one JSON object per line. Parse with jq if needed.
Workflow: login with 1Password
browser-cdp new https://example.com/login
browser-cdp snapshot 1
# Use 1Password MCP to get credentials
browser-cdp fill 1 "[email protected]" "[name=email]"
browser-cdp fill 1 "password123" "[name=password]"
browser-cdp click 1 "[type=submit]"
# Session cookies persist in the host Chrome profile
browser-cdp snapshot 1
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 · 68 lines · 37 tokens per session scan A bb0832ca82a8
browser-cdp is a skill published in the GitHub repository taslim/nanoclaw-gws-ea (11 stars, last pushed today), licensed MIT. It adds 37 tokens to every session and 604 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
interactive-login
Log a CLI in with a browser/device-code flow (aws sso, gh, glab, gcloud, …) and save the result to the keychain so later commands can request it through execute.credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
open-design-browser
Inspect and exercise local HTML design artifacts and library prototype previews with the existing agent-browser CLI, including screenshots, interaction checks, and rendered DOM snapshots. Use when rendered evidence helps author or review a design; excludes browser installation, remote services, and unrelated browser…