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.
git clone --depth 1 https://github.com/yangswld/yangswld-claude-pluginsWrote 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/commands/yangswld/yangswld-claude-plugins/setup)<a href="https://agentmods.dev/commands/yangswld/yangswld-claude-plugins/setup"><img src="https://agentmods.dev/badge/commands/yangswld/yangswld-claude-plugins/setup/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/commands/yangswld/yangswld-claude-plugins/setup"><img src="https://agentmods.dev/badge/commands/yangswld/yangswld-claude-plugins/setup.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 | $0.00000 | $0.01251 |
| Opus 5.5 | $0.00000 | $0.00500 |
| Sonnet 5.5 | $0.00000 | $0.00250 |
| Haiku 4.5 | $0.00000 | $0.00125 |
Grade A, and why
setup 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 2mo 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Install BurntToast module, register the claude-notify:// protocol handler, and register notification identity.
Execution method: For each PowerShell code block below, save the code to a temporary .ps1 file (e.g., ~/.claude/work/setup-step.ps1), then execute via powershell.exe -NoProfile -ExecutionPolicy Bypass -File "<path>". Delete the temp file after each step succeeds. Do not pass PowerShell code inline via -Command — bash escaping will break it.
Prerequisites
- Windows 10 / 11
- Windows PowerShell 5.1 (built-in, no extra install needed)
Step 1: Install BurntToast Module
No Administrator required — -Scope CurrentUser installs for current user only. Check if already installed; skip if present:
if (Get-Module -ListAvailable -Name BurntToast) {
Write-Host "BurntToast already installed, skipping."
} else {
Install-Module -Name BurntToast -Scope CurrentUser -Force
Write-Host "BurntToast installed successfully."
}
If a certificate error occurs during install, retry with -SkipPublisherCheck:
Install-Module -Name BurntToast -Scope CurrentUser -Force -SkipPublisherCheck
Verify BurntToast
Import-Module BurntToast
New-BurntToastNotification -Text 'BurntToast works!'
You should see a test notification in the bottom-right corner of your screen.
Step 2: Register Click-to-Focus Protocol
This registers the claude-notify:// URI protocol so clicking a notification activates the terminal/IDE window. This is a one-time setup and does not require Administrator privileges (writes to HKCU only).
Execute directly without prompting the user:
# Auto-detect plugin root path (marketplace/plugin-name/version)
$pluginRoot = (Get-ChildItem "$env:USERPROFILE\.claude\plugins\cache\*\win-toast-notification\*" -Directory |
Where-Object { Test-Path (Join-Path $_.FullName "scripts") } |
Select-Object -Last 1).FullName
if (-not $pluginRoot) { throw "Plugin root not found. Is the plugin installed?" }
$scriptPath = Join-Path $pluginRoot "scripts\focus-terminal.ps1"
# Register protocol in HKCU (no admin needed)
# Reference: https://learn.microsoft.com/en-us/previous-versions/windows/internet-explorer/ie-developer/platform-apis/aa767914(v=vs.85)
$regPath = "HKCU:\Software\Classes\claude-notify"
New-Item -Path "$regPath\shell\open\command" -Force | Out-Null
Set-ItemProperty -Path $regPath -Name "(Default)" -Value "URL:Claude Notify Protocol"
Set-ItemProperty -Path $regPath -Name "URL Protocol" -Value ""
Set-ItemProperty -Path "$regPath\shell\open\command" -Name "(Default)" `
-Value "powershell.exe -WindowStyle Hidden -NoProfile -ExecutionPolicy Bypass -File `"$scriptPath`" `"%1`""
Write-Host "Registered protocol handler at: $scriptPath"
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.
- 2mo ago First seen · 109 lines · 0 tokens per session scan A 18246bc853ca
setup is a command published in the GitHub repository yangswld/yangswld-claude-plugins (2 stars, last pushed 8mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,251 tokens. 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.
setup compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| setupyangswld/yangswld-claude-plugins | Command | 2 | 8mo ago | MIT | A | 0 | Claude Code |
| checklistgithub/spec-kit | Command | 148k | today | MIT | A | 13 | Claude Code |
| clarifygithub/spec-kit | Command | 148k | today | MIT | A | 27 | Claude Code |
| specifygithub/spec-kit | Command | 148k | today | MIT | A | 13 | Claude Code |
| convergegithub/spec-kit | Command | 148k | today | MIT | A | 35 | Claude Code |
| speckit.bug.testgithub/spec-kit | Command | 148k | today | MIT | A | 13 | Claude Code |
| analyzegithub/spec-kit | Command | 148k | today | MIT | A | 26 | Claude Code |