nova-grounding

nova-grounding is a skill for Claude Code, Codex from bigduu/Nova. It costs 40 tokens per session (799 once invoked), scanned A, original, MIT.

Instructions for grounding Nova desktop automation on macOS and Windows. Nova is a tool that reads accessible interface elements and can activate controls, with OCR and screenshots as fallbacks.

In plain words
What is it for?
Reading windows, fields, buttons, and headings; using OCR for missing text; inspecting visual details; and activating selected controls safely.
Why use it?
They reduce mistaken clicks by requiring the agent to identify the exact visible control and current interface state before acting.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/bigduu/nova/nova-grounding
Any agent
npx skills add bigduu/Nova --skill nova-grounding
Clone the repo
git clone --depth 1 https://github.com/bigduu/Nova

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for nova-grounding

README.md
[![agentmods](https://agentmods.dev/badge/skills/bigduu/nova/nova-grounding.svg)](https://agentmods.dev/skills/bigduu/nova/nova-grounding)
Your own site
<a href="https://agentmods.dev/skills/bigduu/nova/nova-grounding"><img src="https://agentmods.dev/badge/skills/bigduu/nova/nova-grounding.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 799 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00040 $0.00799
Opus 5 $0.00020 $0.00400
Sonnet 5 $0.00008 $0.00160
Haiku 4.5 $0.00004 $0.00080

Measured 3d ago against content hash 6491b869484b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 3d 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.

packaging/plugin/skills/nova-grounding/SKILL.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 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 directly and does not take a screenshot. read_ui is a compatibility alias.

Read in this order

  1. Call ax_read(window?, mode="all") first for labels, controls, fields, headings, structured text, values, supported actions, and semantic state. It returns an ephemeral snapshot_id, snapshot-local node IDs, optional bounds, and an explicit coverage/status.
  2. 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.
  3. Use screenshot(window=...) or zoom_region only when pixels are semantically necessary: layout, icons, colors, images, canvas content, or visual verification.

Do not treat permission_denied as an AX-less application. Grant Accessibility and retry; a screenshot or OCR call cannot repair the missing permission.

Act in this order

  1. Immediately before acting, run a fresh ax_read, select the exact actionable node, and call ax_activate(snapshot_id, node_id).
  2. Nova attempts semantic activation first (route=ax on macOS, route=uia on Windows, or route=web_dom for supported browser content). If that is unsupported, Nova may use the node's freshly revalidated center (route=element_center).
  3. For text absent from the semantic tree, click the center returned by OCR with left_click(x, y, source="ocr_center").
  4. Only then click coordinates read from a focused screenshot or zoom (source="visual_coordinate").

ax_activate fails closed when its snapshot generation is stale. Every activation attempt consumes the generation before provider dispatch, including attempts that return an error because the provider may have partially applied the action. Run ax_read again after any result and after navigation, refresh, scrolling, or any other UI change. click_mark(number=N) remains a compatibility action. Prefer generation-safe ax_activate. Legacy substring actions (ax_click, ax_focus, ax_set_value) reject ambiguous matches instead of selecting the first candidate.

Read the full file on GitHub · 82 lines

Changes

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.

  1. 3d ago First seen · 82 lines · 40 tokens per session scan A 6491b869484b

Subscribe to this mod's changes

nova-grounding is a skill published in the GitHub repository bigduu/Nova (17 stars, last pushed 4d ago), licensed MIT. It adds 40 tokens to every session and 799 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

web-navigator

Web 浏览器自动化路由规则。通过 webnavigator 将 Web 场景路由到 Playwright MCP 或 mcp-chrome。.

Plocr/Reasonix-computer-use · 30 tokens

macos-harness

Control a whole Mac from one persistent Python session with screenshots, PID-targeted input, an animated virtual pointer, targeted Apple Accessibility, Apple Events, Browser Harness CDP, and filesystem access. Use for native, Electron, browser, dialog, file, or cross-app tasks without moving the physical cursor or…

browser-use/macos-harness · 71 tokens

computer-use

Windows 桌面自动化执行规则。使用 screeninteractor 观察与操作原生桌面应用。.

Plocr/Reasonix-computer-use · 23 tokens

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.

wimi321/macos-computer-use-skill · 37 tokens

record-workflow

Record an automation workflow by performing actions, then replay it later as a playbook. Capture clicks, typing, navigation into reusable sequences. Use when: "record this", "capture steps", "make repeatable", "save automation", "create playbook", "record and replay", "macro", "record workflow".

manushi4/Screenhand · 68 tokens

fill-form

Fill out web forms with human-like anti-detection typing. Applications, registration, checkout, surveys, contact forms. Use when: "fill out form", "complete application", "register on", "submit form", "fill in details", "checkout", "sign up on".

manushi4/Screenhand · 59 tokens