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/opencloudgaming/opennow/verifynpx skills add OpenCloudGaming/OpenNOW --skill verifygit clone --depth 1 https://github.com/OpenCloudGaming/OpenNOWWhat 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 | $0.00017 | $0.00701 |
| Opus 5 | $0.00009 | $0.00351 |
| Sonnet 5 | $0.00003 | $0.00140 |
| Haiku 4.5 | $0.00002 | $0.00070 |
Grade A, and why
verify 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.
How it starts
The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify OpenNOW desktop UI
Build and launch
- Build the current tree from the repository root:
npm --prefix opennow-stable run build - Launch Electron with Chrome DevTools Protocol enabled. Run this as a background command so Electron remains available:
$env:OPENNOW_REMOTE_DEBUG = '1'; & "opennow-stable\node_modules\electron\dist\electron.exe" "opennow-stable" - Wait for
http://127.0.0.1:9222/json/listto expose a page titledOpenNOW. The renderer URL should end inopennow-stable/dist/index.html.
Drive the renderer
Use CDP against the target's webSocketDebuggerUrl. Node in this environment provides the global WebSocket API. The working driver supports:
Runtime.evaluatewithawaitPromise: true,returnByValue: true, anduserGesture: truefor DOM inspection and clicks.Input.dispatchKeyEvent(keyDown, thenkeyUp) for real keyboard behavior. This is required for native range-input arrow-key changes; synthetic DOM keyboard events do not invoke browser default actions.Input.insertTextfor typing into the focused control.Page.captureScreenshotwith{ format: "png", fromSurface: true, captureBeyondViewport: false }.
The target can be found with:
const targets = await fetch("http://127.0.0.1:9222/json/list").then((response) => response.json());
const target = targets.find((item) => item.type === "page" && item.title === "OpenNOW") ?? targets[0];
Send CDP requests as incrementing { id, method, params } JSON messages and resolve responses by matching id.
Settings flows worth exercising
- Click the navbar
Settingsbutton; the modal root is.settings-modal. - Section navigation buttons are
.settings-nav-item. - Shared dropdowns use
[role="combobox"],aria-controls, andaria-activedescendant. - Region controls use
#settings-stream-region-trigger,.region-dropdown, and.region-dropdown-search-input. - Numeric mouse controls are
#settings-input-mouse-sensitivity-numberand#settings-input-mouse-acceleration-number. - Resize through
window.resizeTo(1024, 680)andwindow.resizeTo(1400, 900); verifyouterWidth/outerHeightafterward. - Switch Interface theme through
#appTheme, capture light and dark screenshots, then restore the original theme.
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 · 51 lines · 17 tokens per session scan A ca633e3efa02
verify is a skill published in the GitHub repository OpenCloudGaming/OpenNOW (2,400 stars, last pushed today), licensed MIT. It adds 17 tokens to every session and 701 once invoked, about $0.0001 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
nemoclaw-maintainer-e2e
Dispatches and reports trusted GitHub Actions E2E runs. Use for focused, full, staging Launchable, manual PR, and release-decision requests.
nemoclaw-maintainer-fix-e2e-failures
Fixes failures from automatic NemoClaw E2E runs on main through continuous maintainer coordination. Groups failures by root cause, assigns one PR to each cause, reviews peer changes, satisfies GitHub merge requirements, merges eligible PRs when authorized, and monitors new results. Use for continuous main E2E…
nemoclaw-hermes-skill-e2e
Verifies Hermes skill discovery and fresh-session execution.
agent-host-e2e-tests
Use when writing, recording, updating, or troubleshooting the agent host end-to-end tests under src/vs/platform/agentHost/test/node/e2e (black-box tests that drive the whole agent host over the AHP protocol, using a CapiReplayProxy record/replay system for Claude/Copilot/Codex). Covers adding a cross-provider test…
smoke-test
End-to-end smoke test skill for DeerFlow. Guides through: 1) Pulling latest code, 2) Docker OR Local installation and deployment (user preference, default to Local if Docker network issues), 3) Service availability verification, 4) Health check, 5) Final test report. Use when the user says "run smoke test", "smoke…
browse
Fast headless browser for QA testing and site dogfooding. (gstack).