skillshare is a command-line tool that keeps AI coding-agent skills, agents, rules, commands, prompts, and other file-based resources synchronized from one source across many AI CLI tools. Individuals and teams use it to share and manage these resources across projects and organizations. The catalogue entries are skillshare commands and skills.
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 runkids/skillshare --skill skillshare-windows-utmgit clone --depth 1 https://github.com/runkids/skillshareWrote 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/runkids/skillshare/skillshare-windows-utm)<a href="https://agentmods.dev/skills/runkids/skillshare/skillshare-windows-utm"><img src="https://agentmods.dev/badge/skills/runkids/skillshare/skillshare-windows-utm/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/runkids/skillshare/skillshare-windows-utm"><img src="https://agentmods.dev/badge/skills/runkids/skillshare/skillshare-windows-utm.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 | $0.00112 | $0.01756 |
| Opus 5.5 | $0.00045 | $0.00702 |
| Sonnet 5.5 | $0.00022 | $0.00351 |
| Haiku 4.5 | $0.00011 | $0.00176 |
Grade A, and why
skillshare-windows-utm 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 17d 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Linux tests cannot show Windows link behavior. This skill drives the local UTM guest with
scripts/windows/utm.sh. Before acting, run python3 scripts/ai-context.py testing and follow its
"Windows Verification" section; it is the source of truth for the rules below.
Rules
- Build in the devcontainer from a pinned commit (
utm.sh build <ref>), never from the working tree: other work may be editing it. Report the commit hash with every result. - The host only drives the VM (
utmctl). Never runss,goorpnpmon the host. utmctl execruns as SYSTEM, which can always create symlinks. Product behavior must run as the desktop user throughutm.sh task(Interactive scheduled task). Use--basicfor the basic-user token (runas /trustlevel:0x20000), which has no symlink right. Never switch to S4U: its token differs from a real user's.- Isolate automated runs under
C:\Users\Public\sstest\. Clean up withutm.sh clean, which usesrmdir(it does not follow junctions). - Report which token (full or basic) and architecture each result came from.
1. Preflight
scripts/windows/utm.sh probe
| Output | Meaning and action |
|---|---|
stopped |
utmctl start Windows, then probe again after boot. |
OSStatus -1712 |
macOS Automation permission for the terminal app is missing; ask the user to allow it. |
OSStatus -2700 / guest agent error |
Guest still booting or agent not up. Wait, then retry. |
desktopUser= empty |
Nobody is logged in; Interactive tasks will not start. Ask the user to log in in the UTM window. Restarting the VM logs the user out. |
arch=ARM64 / AMD64 |
Use it as the build arch (arm64 / amd64). |
devMode=1 |
Developer Mode is on; the basic token may still create symlinks. Say so in the report. |
2. Build and push
scripts/windows/utm.sh build <ref> <arm64|amd64> # ss.exe, ss-ui-dist.zip, ss-version.txt in $OUT
The UI zip is unpacked into %APPDATA%\skillshare\ui\<version> so ss ui never downloads it.
utmctl file push needs an existing guest folder; create one with utm.sh ps first, or push to
C:\Users\Public\.
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.
- 17d ago First seen · 122 lines · 112 tokens per session scan A 25be99e8d798
skillshare-windows-utm is a skill published in the GitHub repository runkids/skillshare (2,789 stars, last pushed today), licensed MIT. It adds 112 tokens to every session and 1,756 once invoked, about $0.0004 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 2026-09-29.
Other skills, from other repositories
cli-tmux
Use tmux to run and test our interactive CLI/TUI end-to-end. Includes how to start, send keys, capture output, and cleanly stop (double Ctrl+C).
e2e-testing
Guide for running end-to-end tests of the Qwen Code CLI, including headless mode, MCP server testing, and API traffic inspection. Use this skill whenever you need to verify CLI behavior with real model calls, reproduce user-reported bugs end-to-end, test MCP tool integrations, or inspect raw API request/response…
verify
Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.
webapp-testing
Start/reuse a local app, wait for readiness, inspect rendered state/console/network, act from observed selectors, and verify with evidence.
winui-ui-testing
Write and run automated UI tests for Windows desktop apps (WinUI 3, WPF, WinForms, Win32) with the winapp ui harness: one batch script, assertions, input, file pickers, dialogs, screenshots, locally or in Windows Sandbox. Use when asked for UI tests or to verify a feature end to end.
tui-test
Control, inspect, test, and record real terminal apps with the tui-test CLI or its Rust, Python, and JavaScript APIs. Use for shells, TUI apps, text and style locators, keyboard or mouse input, terminal state, clipboard waits, screenshots, recordings, snapshots, and live terminal sessions.