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 agentmods add instructions/nsh1l/print-queue-app/agents-mdgit clone --depth 1 https://github.com/nsh1l/print-queue-appWhat 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 | $0.01488 | $0.01488 |
| Opus 5 | $0.00744 | $0.00744 |
| Sonnet 5 | $0.00298 | $0.00298 |
| Haiku 4.5 | $0.00149 | $0.00149 |
Grade A, and why
print-queue-app AGENTS.md 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 yesterday.
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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - AYP Print-Queue
Project overview
Windows用のスタンドアローン印刷キューアプリ。ローカルでXLSX / XLS / XLSM / PDFを追加し、一覧から選択したWindowsプリンターへ送信する。
公開API、Cloudflare Tunnel、HTTPサーバー、MCP連携はこのプロジェクトの範囲外。
Stack
- .NET 8 SDK / WinUI 3 (Windows App SDK); target
net8.0-windows10.0.19041.0, runtimewin-x64 Microsoft.WindowsAppSDK2.3.1, Windows Shellprinttoverb- Windows 10 version 2004 (build 19041)以降を対象にする
Build and test (Windows PowerShell)
Run from the repository root on Windows. The current runnable verification is the Program.cs self-test; there is no separate test project.
cd WinUIMCPServer
dotnet restore
dotnet build -c Debug
dotnet run -c Debug -- --self-test
dotnet run -c Debug
dotnet run -c Debug -- --print-test <file-path>
--self-test must print QueueItem self-test passed.. --print-test uses the default printer and exits non-zero when submission fails; it still depends on the file association's printto verb.
Distribution build
Use the complete self-contained folder; do not distribute the executable alone because WinUI native DLLs and resources are required.
cd WinUIMCPServer
dotnet publish -c Release -r win-x64 --self-contained true `
-p:WindowsAppSDKSelfContained=true `
-p:PublishSingleFile=false `
-o ..\dist\AYP-Print-Queue-win-x64
ZIP dist\AYP-Print-Queue-win-x64 as the release artifact. bin/, obj/, and dist/ are generated and ignored.
Source layout
WinUIMCPServer/Program.cs— application entry point,--self-test, and--print-testWinUIMCPServer/MainWindow.xaml(.cs)— local WinUI queue UI, drag/drop, dialogs, accessibility status, and printer refreshWinUIMCPServer/QueueItem.cs— supported-format validation, queue persistence, bounded submission, Win32 printer catalog/health, and self-test
Design constraints
- Keep the app local-only. Do not add a server, token, remote control, or public endpoint.
Submittedmeans the request was accepted by Windows Shell, not physical print completion; physical status remains a printer/spooler concern.- PDF/Excel submission depends on an associated Windows application exposing the Shell
printtoverb. - Use native Windows capabilities before dependencies or abstractions. Keep P/Invoke and Windows printer handling in the existing catalog instead of adding a new library.
- Duplicate identity is the normalized absolute path, compared case-insensitively. Supported extensions are
.xlsx,.xls,.xlsm, and.pdf. - Normal submission is bounded to four concurrent Shell launches; the preserve-order option submits sequentially.
- IMPORTANT: Do not write overly defensive code. Always prefer simplicity over pathological complexity.
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.
- yesterday First seen · 100 lines · 1,488 tokens per session scan A f1ec8d957d45
print-queue-app AGENTS.md is an instructions file published in the GitHub repository nsh1l/print-queue-app (1 stars, last pushed 6d ago), licensed MIT. It adds 1,488 tokens to every session, about $0.0074 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 instructions, from other repositories
Fluence.Wpf AGENTS.md
AGENTS.md instructions for sintaxasn/Fluence.Wpf, covering fluence.wpf - developer handbook, 1. project overview, solution layout, clr namespaces and 2. coding standards.
Fluence.Wpf copilot-instructions.md
Copilot instructions for sintaxasn/Fluence.Wpf, covering fluence.wpf -- copilot instructions, project at a glance, non-negotiable rules, theme architecture (3-slot layout -- do not break) and reference priority.
Fluence.Wpf CLAUDE.md
Claude Code instructions for sintaxasn/Fluence.Wpf, a project described as: Fluence.Wpf is a modern theming and control library based on WinUI 3, but for WPF on .NET 4.7.2 / .NET 10.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.