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/sintaxasn/fluence.wpf/copilot-instructionsgit clone --depth 1 https://github.com/sintaxasn/Fluence.WpfWrote 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/instructions/sintaxasn/fluence.wpf/copilot-instructions)<a href="https://agentmods.dev/instructions/sintaxasn/fluence.wpf/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/sintaxasn/fluence.wpf/copilot-instructions.svg" alt="Measured on agentmods" 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 | $0.01563 | $0.01563 |
| Opus 5 | $0.00781 | $0.00781 |
| Sonnet 5 | $0.00313 | $0.00313 |
| Haiku 4.5 | $0.00156 | $0.00156 |
Grade A, and why
Fluence.Wpf copilot-instructions.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 3d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fluence.Wpf -- Copilot Instructions
Condensed guidance for Copilot, Gemini, and similar assistants. Full detail is in AGENTS.md -- read it before making any non-trivial change.
Project at a glance
WPF control library reproducing Windows 11 Fluent / WinUI 3 visuals on .NET
Framework 4.7.2 and .NET 10. Four projects: Fluence.Wpf (library),
Fluence.Wpf.Demo (gallery), Fluence.Wpf.Demo.Mvvm (MVVM demo),
Fluence.Wpf.Tests (xunit.v3 3.2.2, multi-TFM).
XML namespace: http://schemas.fluencewpf.com (prefix: fluence)
Non-negotiable rules
-
File encoding: All
.cs,.xaml,.csprojfiles must be UTF-8 with BOM + LF line endings. The PostToolUse hook enforces this -- violations block writes. -
Zero warnings:
TreatWarningsAsErrors=True. Never suppress a warning with#pragma; fix the root cause. -
Banned API:
string.IsNullOrEmpty()is banned (RS0030). Always usestring.IsNullOrWhiteSpace(). -
BSD header: Every
.csfile starts with the 27-line BSD 3-Clause header. Copy it from any existing library file. -
XML docs: All
publicAPI members need///XML doc comments. Missing comments fail the build. -
Nullable clean:
Nullable=enableproject-wide. Annotate?only where genuinely nullable. -
DynamicResource for theme values: Any brush, color, corner radius, or typography that must react to theme changes uses
DynamicResource. Static assets only useStaticResource. -
No hard-coded colors: Never write hex values in XAML templates. Use canonical WinUI-style resource keys. Hex literals belong only in the Color tables
Themes/Colors/Theme.{Light|Dark|HighContrast}.xaml; templates bind the auto-generated*Brushtwin viaDynamicResource. -
Overflow in Win32 bit-math: Wrap HIWORD/LOWORD extractions in
unchecked { }.CheckForOverflowUnderflow=Trueis active. -
Discard return values:
_ = method()for non-void returns you are not using. Ignored returns are build errors (CA1806).
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.
- 3d ago First seen · 137 lines · 1,563 tokens per session scan A 0fcdde5fb12d
Fluence.Wpf copilot-instructions.md is an instructions file published in the GitHub repository sintaxasn/Fluence.Wpf (11 stars, last pushed yesterday), licensed BSD-3-Clause. It adds 1,563 tokens to every session, about $0.0078 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 2026-08-30.
Other instructions, from other repositories
tik4net CLAUDE.md
Instructions for danikf/tik4net, a project described as: Manage mikrotik routers with .NET C# code via ADO.NET like API or enjoy O/R mapper like highlevel api.
maui integration-tests.instructions.md
Guidance for GitHub Copilot when working with .NET MAUI integration tests.
maui public-api.instructions.md
Instructions for dotnet/maui, covering public api surface design, api addition rules, publicapi.unshipped.txt, obsolescence and removal and visibility decisions.
maui performance-hotpaths.instructions.md
Instructions for dotnet/maui, covering performance-critical path rules, hot paths in maui, allocation avoidance, caching and invalidation and collection iteration.
moorestech AGENTS.md
AGENTS.md instructions for moorestech/moorestech, covering コーディングの指針, qa(必須), 互換性とパフォーマンス, 既知の制約(設計上の割り切り) and regionの活用.
nina AGENTS.md
Instructions for isbeorn/nina, covering agents.md, scope, documentation boundary, repository knowledge and code style and formatting.