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 aAAaqwq/AGI-Super-Team --skill automate-windows-accessibilitygit clone --depth 1 https://github.com/aAAaqwq/AGI-Super-TeamWrote 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/aaaaqwq/agi-super-team/automate-windows-accessibility)<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.
<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>- NVIDIA SkillSpector pass
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 | $0.00042 | $0.00792 |
| Opus 5 | $0.00021 | $0.00396 |
| Sonnet 5 | $0.00008 | $0.00158 |
| Haiku 4.5 | $0.00004 | $0.00079 |
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.
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
- 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.
- 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.
- 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.
- 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.
- 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.
- Deliver the action. Prefer
SendInputfor Chromium/web content. Use UIA patterns for native controls when their semantics are reliable, but still verify the result. - 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.
- Retry safely. Reacquire the element before each retry. Bound attempts, capture diagnostics, and fail closed when identity or state is ambiguous.
- Clean up. Ensure UIA workers, process job objects, input state, previews, and foreground changes are recovered on normal exit, exception, timeout, or interruption.
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.
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.
- 7d ago First seen · 54 lines · 42 tokens per session scan A c87ae9b885d2
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.
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.
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.
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.
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.
flo
MoFlo ticket spell - analyze and execute GitHub issues.
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.