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/automateyournetwork/netclawnpx agentmods add skills/automateyournetwork/netclaw/desktop-gui-inspectWrote 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/desktop-gui-inspect)<a href="https://agentmods.dev/skills/automateyournetwork/netclaw/desktop-gui-inspect"><img src="https://agentmods.dev/badge/skills/automateyournetwork/netclaw/desktop-gui-inspect/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/automateyournetwork/netclaw/desktop-gui-inspect"><img src="https://agentmods.dev/badge/skills/automateyournetwork/netclaw/desktop-gui-inspect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 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 Rogue Agent · line 21 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 Agent Snooping · line 25 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00143 | $0.02684 |
| Opus 5 | $0.00072 | $0.01342 |
| Sonnet 5 | $0.00029 | $0.00537 |
| Haiku 4.5 | $0.00014 | $0.00268 |
Grade A, and why
desktop-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 11d 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Desktop GUI Inspect Skill
Purpose
browser-gui-inspect (spec 048) fills gaps in web-based controller dashboards NetClaw's API-based skills can't reach. But some legacy network/security tooling has no web GUI or API at all — only a native desktop application. Browser automation cannot reach those; this skill can. It drives OpenClaw's own ClawHub computer-use skill — a real virtual X11 desktop (Xvfb + XFCE) on this NetClaw host, controlled via xdotool-based mouse/keyboard/screenshot scripts — to read, navigate, and confirm state in a desktop-only application.
This skill deliberately contains no per-application knowledge. Every invocation is directed by the operator's own target_application/intent at request time — nothing about any specific legacy tool's UI layout is hardcoded here (Constitution VI — Multi-Vendor Neutrality), the same design principle browser-gui-inspect follows. See specs/050-computer-use-desktop/ for the full spec, research, and design behind this skill.
Golden Rule — Read/Confirm/Search Only, Never a Config-Change Mechanism
The underlying desktop actions (click, type, drag, key combinations, scrolling) are for reading, navigating, and confirming state on the virtual desktop — never for submitting, applying, or committing a configuration change to network infrastructure. If a request would require clicking something like "Apply," "Commit," "Save," or "Deploy" in a legacy tool's configuration workflow, stop and tell the operator that this must go through the relevant API-based skill instead, 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 — the same reasoning browser-gui-inspect documents for its own interactive tools (see that skill's own Golden Rule, and specs/048-chrome-devtools-browser-inspection/research.md R8).
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.
- 11d ago First seen · 154 lines · 143 tokens per session scan A 0bb8eac8e413
desktop-gui-inspect is a skill published in the GitHub repository automateyournetwork/netclaw (652 stars, last pushed 4d ago), licensed Apache-2.0. It adds 143 tokens to every session and 2,684 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
agent-orchestration
A guide for coordinating independent AI coding agents such as Claude Code, OpenCode, or Hermes. It explains how to register each agent, check which ones are running, choose one for a task, and record stable information about how to use it.
workflow-design
A method for designing and testing multi-step computer workflows, including their inputs, actions, conditions, and error handling.
release-poster
A fixed process for creating social-media release graphics in horizontal and vertical formats from a supplied template.
mcp-tools
A reference guide for connecting outside services to an AI workflow through MCP, a standard way for AI systems to call external tools. It describes how to identify a server and tool, provide inputs, and save the result for later workflow steps.
clawdcursor
FALLBACK ONLY — do not invoke unless you have already ruled out (1) a native API (Gmail API, GitHub API, Slack API …), (2) a CLI (git, gh, aws, npm, curl …), (3) direct file editing, and (4) existing browser automation (Playwright, Puppeteer). Only when all four are unavailable or have already failed should you use…
nova-grounding
AX-first reading and grounded activation workflow for Nova desktop automation on macOS and Windows. Use for reading UI, clicking controls, OCR fallback, screenshots, and coordinate input without guessing.