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 Peiiii/nextclaw --skill browser-controlgit clone --depth 1 https://github.com/Peiiii/nextclawWrote 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/peiiii/nextclaw/browser-control)<a href="https://agentmods.dev/skills/peiiii/nextclaw/browser-control"><img src="https://agentmods.dev/badge/skills/peiiii/nextclaw/browser-control/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/peiiii/nextclaw/browser-control"><img src="https://agentmods.dev/badge/skills/peiiii/nextclaw/browser-control.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 233 This pattern attempts to override system instructions or ignore safety constraints. Without LLM analysis, manual review is recommended.Fix: Remove or rewrite any text that instructs the agent to ignore prompts, override safety rules, or trust unverified content. Ensure skill content cannot be injected to alter agent behavior.
- medium MCP Rug Pull · line 58 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 247 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium Excessive Agency · line 108 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00058 | $0.03160 |
| Opus 5.5 | $0.00023 | $0.01264 |
| Sonnet 5.5 | $0.00012 | $0.00632 |
| Haiku 4.5 | $0.00006 | $0.00316 |
Grade A, and why
browser-control 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 — 342 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Control
Use this skill when the user wants the AI to inspect or operate Chrome pages that are already open in the user's normal browser.
This is a wrapped external tool skill:
- The skill owns setup guidance, readiness checks, safe workflow order, confirmation rules, and troubleshooting.
browser-connectorowns the Chrome Extension, Native Messaging Host, tab lease, JSON contract, screenshots, DOM snapshots, and browser actions.- Do not present this as a built-in NextClaw browser runtime or as direct model vision.
What This Skill Covers
- List currently open Chrome tabs.
- Open a new Chrome tab for an http or https URL.
- Keep new tabs in the background by default for temporary evaluation, research, and page-reading work.
- Ask the connected unpacked Browser Connector extension to reload itself after local or package updates.
- Read the selected tab or refresh metadata for a known tab.
- Claim a tab before reading or operating it.
- Read a bounded page snapshot.
- Locate ref-addressable interactive elements by text, label, placeholder, role, or kind.
- Capture a visible-tab screenshot, optionally writing it to a local PNG file.
- Navigate a claimed tab with goto, reload, back, and forward.
- Inspect elements, fill editable fields with verified state, click, type, press keys, scroll, wait, and read captured page logs through the connector.
- Release the tab lease when done.
What This Skill Does Not Cover
- Reading cookies, localStorage, sessionStorage, passwords, browser history, or extension private storage.
- Bypassing website authentication or permission prompts.
- Automatically confirming submit, send, upload, delete, payment, login, or permission actions.
- Long-running daemon management.
- Operating a separate Playwright browser instead of the user's current Chrome.
Readiness Check
First check whether browser-connector is available:
command -v browser-connector
browser-connector --version
If it is not installed, install the published package:
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.
- 1mo ago First seen · 342 lines · 58 tokens per session scan A 89642e81526f
browser-control is a skill published in the GitHub repository Peiiii/nextclaw (262 stars, last pushed today), licensed MIT. It adds 58 tokens to every session and 3,160 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 2026-09-03.
Other skills, from other repositories
ha-browser
Hope Agent browser automation — the standard status → tabs → snapshot → act loop, stale-ref recovery rules, and what to do when login / 2FA / captcha / camera-prompt / dialog blocks progress. Load this skill whenever you reach for the browser tool. Trigger on: user asks the agent to open / control / click / scrape /…
Abu-Browser
Browser controls for Abu's built-in visible web browser. They let an agent open pages, click, fill in forms, take screenshots, and extract information.
Abu-Chrome-Bridge
Browser controls that work with the user's existing Chrome tabs, sign-ins, and browsing data through the Abu Chrome extension.
browser-automation
A set of instructions for controlling a web browser, testing web interfaces, and collecting information from websites that load content dynamically.
search-craft
How to get real coverage out of a search engine that returns a handful of results per query, and when to reach for the crawler or the browser instead. Use at the start of any search that has to be thorough rather than quick.
add-tavily-tool
Add Tavily Search and Extract as keyless remote MCP tools for selected NanoClaw agent groups. Use when installing Tavily web search or URL extraction without an API key.