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 automateyournetwork/netclaw --skill browser-gui-inspectgit clone --depth 1 https://github.com/automateyournetwork/netclawWrote 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/automateyournetwork/netclaw/browser-gui-inspect)<a href="https://agentmods.dev/skills/automateyournetwork/netclaw/browser-gui-inspect"><img src="https://agentmods.dev/badge/skills/automateyournetwork/netclaw/browser-gui-inspect.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
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 →
- medium MCP Rug Pull · line 32 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 Rogue Agent · line 184 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium MCP Rug Pull · line 198 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]
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 | $0.00142 | $0.03573 |
| Opus 5 | $0.00071 | $0.01786 |
| Sonnet 5 | $0.00028 | $0.00715 |
| Haiku 4.5 | $0.00014 | $0.00357 |
Grade A, and why
browser-gui-inspect 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 9d 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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser GUI Inspect Skill
Purpose
Many controllers and web-based tools NetClaw talks to via REST API also have GUI-only reports, dialogs, or visualizations the API doesn't expose — and some tools (classic SDN controller consoles, vendor support portals, SaaS admin consoles) have no NetClaw API integration at all. This skill is the controller-agnostic fallback: it drives a real, persistent, manually-authenticated Chrome session to read, search, confirm, and capture whatever an operator needs from a web GUI.
This skill deliberately contains no per-vendor DOM/selector knowledge. Every invocation is directed by the operator's own target URL and intent at request time — nothing about any specific controller's page layout is hardcoded here (Constitution VI — Multi-Vendor Neutrality). See specs/048-chrome-devtools-browser-inspection/ for the full spec, research, and design behind this skill.
Golden Rule — Read/Confirm/Search Only, Never a Config-Change Mechanism
This skill's interactive tools (click, fill, fill_form, drag, press_key, type_text, handle_dialog, upload_file) are for reading, filtering, searching, and confirming state on a page — never for submitting, applying, or committing a configuration change to network infrastructure. If a request would require clicking something like "Commit," "Apply," "Submit," "Deploy," or "Save" on a controller's configuration workflow, stop and tell the operator that this must go through the relevant API-based skill instead (e.g., the ACI, Panorama, or FortiManager skill), which implements the proper observe→baseline→modify→verify workflow and ServiceNow CR gating (Constitution I, II, III, VIII). Using this skill to bypass that workflow would create an unaudited, unverified side door around NetClaw's safety model — see specs/048-chrome-devtools-browser-inspection/research.md R8 for the full rationale.
MCP Servers — Headless and Watch Mode
This skill uses tools provided by the chrome-devtools-mcp package (official Chrome DevTools team, chrome-devtools-mcp on npm), registered twice:
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.
- 9d ago First seen · 214 lines · 142 tokens per session scan A 1aeee8695615
browser-gui-inspect is a skill published in the GitHub repository automateyournetwork/netclaw (651 stars, last pushed 2d ago), licensed Apache-2.0. It adds 142 tokens to every session and 3,573 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
codex-browser
Control Chrome via Codex Desktop's browser bridge. 52 MCP tools for tabs, navigation, DOM, input, CDP, network, file upload, dialog handling, and diagnostics.
browser-automation
Use browser automation to inspect or interact with websites, test rendered interfaces, capture screenshots, and diagnose console or network behavior.
neo
Browse websites, read web pages, interact with web apps, call website APIs, and automate web tasks. Use Neo when: user asks to check a website, read a web page, post on social media (Twitter/X), interact with any web app, look up information on a specific site, scrape data from websites, automate browser tasks, or…
chrome-devtools-coexistence
Use when registering or troubleshooting the optional chrome-devtools-mcp server alongside pwa-debug — making its tools available (full restart for a direct MCP install vs. /reload-plugins for a plugin install) and handing the user a context note to paste back across a restart so the conversation continues seamlessly.
api-mapper
Reverse-engineer undocumented APIs using Chrome CDP and curl. Controls a real Chrome browser via Python scripts to intercept traffic, reverse-engineer JS bundles, and produce markdown docs per domain area in docs/apis/. Output is designed as input for a client or SDK-building agent -- complete enough that no browser…
codex-browser
Control Chrome or Edge via the ChatGPT desktop app's browser bridge (formerly Codex Desktop). 52 MCP tools for tabs, navigation, DOM, input, CDP, network, file upload, dialog handling, and diagnostics.