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 navig-run/core --skill windows-automationgit clone --depth 1 https://github.com/navig-run/coreWrote 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/navig-run/core/windows-automation)<a href="https://agentmods.dev/skills/navig-run/core/windows-automation"><img src="https://agentmods.dev/badge/skills/navig-run/core/windows-automation/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/navig-run/core/windows-automation"><img src="https://agentmods.dev/badge/skills/navig-run/core/windows-automation.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 | $0.00020 | $0.00625 |
| Opus 5 | $0.00010 | $0.00313 |
| Sonnet 5 | $0.00004 | $0.00125 |
| Haiku 4.5 | $0.00002 | $0.00063 |
Grade A, and why
windows-automation 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 10d 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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What ships with it
34 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.
- scripts/ahk/app_launcher.ahk 225 B
- scripts/ahk/click.ahk 435 B
- scripts/ahk/clipboard_monitor.ahk 291 B
- scripts/ahk/hotkey_daemon.ahk 196 B
- scripts/ahk/media_control.ahk 476 B
- scripts/ahk/send.ahk 243 B
- scripts/ahk/type.ahk 211 B
- scripts/ahk/window_close.ahk 226 B
- scripts/ahk/window_move.ahk 414 B
- scripts/ahk/window_tiler.ahk 1.3 KB
- scripts/click_element.py 6.7 KB runs code
- scripts/click_text.py 1.9 KB runs code
- scripts/click.py 602 B runs code
- scripts/close_window.py 763 B runs code
- scripts/drag.py 696 B runs code
- scripts/find_text.py 1.8 KB runs code
- scripts/focus_window.py 1015 B runs code
- scripts/get_active_window.py 452 B runs code
- scripts/handle_dialog.py 13 KB runs code
- scripts/key_press.py 577 B runs code
- scripts/list_windows.py 958 B runs code
- scripts/maximize_window.py 914 B runs code
- scripts/minimize_window.py 914 B runs code
- scripts/mouse_move.py 422 B runs code
- scripts/read_region.py 2.2 KB runs code
- scripts/read_ui_elements.py 6.0 KB runs code
- scripts/read_webpage.py 7.6 KB runs code
- scripts/read_window.py 2.1 KB runs code
- scripts/screenshot.py 509 B runs code
- scripts/scroll.py 673 B runs code
- scripts/type_text.py 512 B runs code
- scripts/wait_for_text.py 1.7 KB runs code
- scripts/wait_for_window.py 1.1 KB runs code
- windows-automation.skill.json 169 B
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.
- 10d ago First seen · 86 lines · 20 tokens per session scan A 4a84ce3d7179
windows-automation is a skill published in the GitHub repository navig-run/core (5 stars, last pushed 2d ago), with no licence file. It adds 20 tokens to every session and 625 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 2026-08-31.
Other skills, from other repositories
quicker-authoring-ui-automation-lite
A set of instructions for controlling a Windows application's foreground window and sending keyboard input through Quicker. Quicker is a Windows automation tool for running actions.
shell-scripting
A guide to writing Bash shell scripts, which automate command-line tasks on Linux and similar systems. It covers variables, arrays, conditions, loops, functions, and safer script structure.
static-rust
Use for Soma built-in Rust actions, scaffold intent collection, MCP elicitation flows, and CLI/REST action reference.
local-python-tools
Use when working with local-python-tools provider actions such as pythonruntimecheck.
gws-calendar
Google Calendar: Manage calendars and events.
gws-gmail-reply
Gmail: Reply to a message (handles threading automatically).