automate-windows-accessibility

automate-windows-accessibility is a skill for Claude Code, Codex from aAAaqwq/AGI-Super-Team. It costs 42 tokens per session (792 once invoked), scanned A, original, MIT.

A Windows automation guide for interacting with desktop and web applications through accessibility information, browser page data, keyboard and mouse input, and application state. It also covers windows, processes, screen scaling, and downloads.

In plain words
What is it for?
Use it to find accessible controls, automate Chrome or Windows interfaces, handle scaling and stale elements, operate downloads, and verify that actions really took effect.
Why use it?
It reduces fragile automation based only on screen coordinates and treats a successful command as unproven until the application's new state is checked.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the agi-super-team plugin — 194 skills, 1 agent shipped together

Good fit Use it to find accessible controls, automate Chrome or Windows interfaces, handle scaling and stale elements, operate downloads, and verify that actions really took effect.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aaaaqwq/agi-super-team/automate-windows-accessibility
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.

Any agent
npx skills add aAAaqwq/AGI-Super-Team --skill automate-windows-accessibility
Clone the repo
git clone --depth 1 https://github.com/aAAaqwq/AGI-Super-Team

Made for: Claude Code, Codex.

Or install agi-super-team, the plugin that ships this one along with the rest of its 194 skills, 1 agent.

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 automate-windows-accessibility

README.md
[![agentmods](https://agentmods.dev/badge/skills/aaaaqwq/agi-super-team/automate-windows-accessibility/github.svg)](https://agentmods.dev/skills/aaaaqwq/agi-super-team/automate-windows-accessibility)
Your own site
<a href="https://agentmods.dev/skills/aaaaqwq/agi-super-team/automate-windows-accessibility"><img src="https://agentmods.dev/badge/skills/aaaaqwq/agi-super-team/automate-windows-accessibility/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.

agentmods 80×15 button for automate-windows-accessibility

Your own site · 80×15
<a href="https://agentmods.dev/skills/aaaaqwq/agi-super-team/automate-windows-accessibility"><img src="https://agentmods.dev/badge/skills/aaaaqwq/agi-super-team/automate-windows-accessibility.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 792 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00042 $0.00792
Opus 5 $0.00021 $0.00396
Sonnet 5 $0.00008 $0.00158
Haiku 4.5 $0.00004 $0.00079

Measured 7d ago against content hash c87ae9b885d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

automate-windows-accessibility 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 7d 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.

skills/automate-windows-accessibility/SKILL.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Automate Windows Accessibility

Separate perception, identity, action, and proof. A successful API return is never proof that the target application changed state.

Architecture

Use this default split:

Element semantics and geometry  -> native UI Automation
Stable web identity and DOM evidence -> read-only CDP
Mouse, keyboard, wheel, drag -> Win32 SendInput
Post-action truth -> fresh UIA/CDP/application state
Window, process, DPI, screenshot -> Win32 APIs

Keep business code behind a platform-neutral adapter. Do not leak HWNDs, screen coordinates, UIA runtime IDs, or CDP session objects into domain models.

Workflow

  1. Establish the window. Resolve the owning process and top-level HWND. Reject minimized, hidden, zero-sized, or sentinel off-screen windows. Restore and foreground only when an action needs it.
  2. Take a bounded snapshot. Read UIA through a worker or supervisor with a hard timeout. Include control type, accessible name, automation ID, class, rectangle, enabled/off-screen state, parent relation, and supported patterns.
  3. Bind by semantics and context. Match exact role/type plus normalized label, then bind through parent/child context to the intended card, row, panel, or dialog. Treat indexes and runtime tokens as snapshot-local.
  4. Make the target visible. If virtualized or off-screen, scroll the correct container, wait, and take a new snapshot. Never click coordinates from the pre-scroll snapshot.
  5. Compute screen coordinates once. Use Per-Monitor DPI awareness and virtual-desktop coordinates. Do not rescale an already physical screen origin. Support negative monitor coordinates.
  6. Deliver the action. Prefer SendInput for Chromium/web content. Use UIA patterns for native controls when their semantics are reliable, but still verify the result.
  7. Verify with fresh evidence. Poll for a target-specific state transition: selected identity, dialog appearance/disappearance, field value, button state, URL, attachment, or content signature.
  8. Retry safely. Reacquire the element before each retry. Bound attempts, capture diagnostics, and fail closed when identity or state is ambiguous.
  9. Clean up. Ensure UIA workers, process job objects, input state, previews, and foreground changes are recovered on normal exit, exception, timeout, or interruption.

Read the full file on GitHub · 54 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 7d ago First seen · 54 lines · 42 tokens per session scan A c87ae9b885d2

Subscribe to this mod's changes

automate-windows-accessibility is a skill published in the GitHub repository aAAaqwq/AGI-Super-Team (92 stars, last pushed yesterday), licensed MIT. It adds 42 tokens to every session and 792 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 2026-09-05.

Related

Other skills, from other repositories

browser-check

Drive a real browser and come back with a MEASUREMENT rather than an impression - console errors and >=400 responses as counts, computed styles as JSON when appearance is disputed. Use when work touches UI, when a review must verify one, or when fidelity-gate asks for its measurement.

jjanczur/tyran · 58 tokens

qa

QA testing skill with real browser automation. Use when asked to "test this site", "QA this page", "check for visual bugs", "verify the deploy", or when Hydra needs browser validation for UI changes. Requires the browse binary.

blueberrycongee/termcanvas · 50 tokens

chrome-devtools

Drive the machine Chrome debug browser via OpenClaw-managed MCP (chrome-devtools). Use for page navigation, snapshots, screenshots, clicks, forms, console/network inspection — not for host shell risk.

yunsii/wezdeck · 44 tokens

mission-control

Interact with Mission Control — AI agent orchestration dashboard. Use when registering agents, managing tasks, syncing skills, or querying agent/task status via MC APIs.

builderz-labs/mission-control · 34 tokens

flo

MoFlo ticket spell - analyze and execute GitHub issues.

eric-cielo/moflo · 13 tokens

prompt-tuning

Tune a prompt, or anything whose quality is measured by non-deterministic model output, without chasing noise - a noise baseline before the first edit, medians over repeated runs, enforcement AFTER generation rather than in the wording. Use when iterating on prompts or model-judged output.

jjanczur/tyran · 58 tokens