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 bigduu/Nova --skill nova-groundinggit clone --depth 1 https://github.com/bigduu/NovaWrote 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/bigduu/nova/nova-grounding)<a href="https://agentmods.dev/skills/bigduu/nova/nova-grounding"><img src="https://agentmods.dev/badge/skills/bigduu/nova/nova-grounding/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/bigduu/nova/nova-grounding"><img src="https://agentmods.dev/badge/skills/bigduu/nova/nova-grounding.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 | $0.00040 | $0.01182 |
| Opus 5.5 | $0.00016 | $0.00473 |
| Sonnet 5.5 | $0.00008 | $0.00236 |
| Haiku 4.5 | $0.00004 | $0.00118 |
Grade A, and why
nova-grounding 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 19d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nova AX-first desktop grounding
Nova controls macOS and Windows. Treat ax_read as the first-class
ax:read capability. It reads Accessibility/UIA by default and does not take
a screenshot. read_ui is a compatibility alias.
Chrome routing
When the separately enabled nova-chrome-devtools server is available, use
its official Chrome DevTools tools for routine web-page automation, DOM and
network inspection, and performance debugging. Use Nova for browser chrome,
permission dialogs, other desktop apps, and pixel fallback. If the user needs
least-privilege access to one explicitly paired page, prefer Nova's separately
installed Secure Chrome Bridge instead of broad existing-profile DevTools
access.
For an already consented Secure Chrome Bridge page, call
ax_read(target="paired_page", mode="all"), then
ax_activate(snapshot_id, node_id) on an activate-capable canonical node.
target="native" or an omitted target keeps native selection; paired_page
rejects window=. This page-only snapshot reports provider=chrome_extension,
page/frame coverage and nativeWindowAssociation=unproven. It supplies no native
marks, browser toolbar, PID/window association or global coordinates. Do not
infer ownership from titles, URLs, Chrome window IDs or the frontmost window.
Only the already paired document is eligible, even when a decoy is frontmost.
Unknown/content-only/stale page IDs dispatch nothing. An accepted current page
token consumes its generation before I/O; route changes, reconnects, DOM errors,
no observed effect, ambiguity and timeout never restore or replay it. Read fresh
and inspect before choosing another action. Keep page failures on this path;
do not switch to native AX/UIA, AppleScript, app raising, OCR or coordinate input
to retry a failed DOM action. Direct chrome_* tools remain available.
Read in this order
- Call
ax_read(window?, mode="all")first for labels, controls, fields, headings, structured text, values, supported actions, and semantic state. It returns an ephemeralsnapshot_id, snapshot-local node IDs, optional bounds, and an explicit coverage/status. - If coverage is absent or partial and the missing information is rendered
text, call focused-window
ocr. OCR returns a grounded center for each recognized line. - Use
screenshot(window=...)orzoom_regiononly when pixels are semantically necessary: layout, icons, colors, images, canvas content, or visual verification.
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.
- 19d ago Changed · +20 lines 83b62b840773
- 1mo ago Changed · +10 lines 96df915d5840
- 1mo ago First seen · 82 lines · 40 tokens per session scan A 6491b869484b
nova-grounding is a skill published in the GitHub repository bigduu/Nova (22 stars, last pushed 7d ago), licensed MIT. It adds 40 tokens to every session and 1,182 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 2026-08-30.
Other skills, from other repositories
computer-use
A set of rules for controlling Windows desktop applications through screen observation and simulated mouse and keyboard actions. It also describes how to find and launch installed applications and verify the results.
web-navigator
A browser-automation routing guide for web tasks. It directs navigation, page inspection, and actions such as clicking or filling forms to the appropriate browser tool.
macos-harness
Read and operate the apps on this Mac from the shell. Use it when a task needs an app's UI and no API, CLI or purpose-built tool can do it.
computer-use
Control local macOS applications through the installed Computer Use MCP tools. Use for GUI work that is not better served by a dedicated API, connector, or CLI.
computer-use
Control local macOS applications through the installed Computer Use MCP tools. Use for GUI work that is not better served by a dedicated API, connector, or CLI.
computer-use-macos
Top-level macOS computer-use skill with a bundled standalone runtime that bootstraps itself without any local Claude installation, private native modules, or extracted app assets.