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/christosk92/waveemusic/claude-mdgit clone --depth 1 https://github.com/christosk92/WaveeMusicWrote 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/christosk92/waveemusic/claude-md)<a href="https://agentmods.dev/instructions/christosk92/waveemusic/claude-md"><img src="https://agentmods.dev/badge/instructions/christosk92/waveemusic/claude-md.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 5.1 | $0.01589 | $0.01589 |
| Opus 5 | $0.00794 | $0.00794 |
| Sonnet 5 | $0.00318 | $0.00318 |
| Haiku 4.5 | $0.00159 | $0.00159 |
Grade A, and why
WaveeMusic CLAUDE.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 2d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What this repository is
Wavee — a Spotify desktop client for Windows, built on the FluentGpu engine (a from-scratch NativeAOT,
GPU-rendered UI engine for .NET 10). This repo holds the app only: src/apps/{Wavee, Wavee.Core, Wavee.Sdk, Wavee.Tests, Wavee.ReleaseTool, modules/*, vendor/*}, the release tooling (ops/), the app docs
(docs/guide, docs/plans) and the app skills (.claude/skills). It was split out of the engine repo on
2026-08-30 (docs/plans/wavee/wavee-repo-split-plan.md); history before that commit is the retired WinUI-era app.
The engine is a sibling checkout, not a package. Directory.Build.props resolves it as
$(EngineRoot) = ..\fluent-gpu\ (C:\wavee\fluent-gpu next to C:\wavee\WaveeMusic), and every engine
ProjectReference goes through that property. Clone https://github.com/christosk92/fluent-gpu beside this repo
first; the build fails with one clear sentence otherwise. Engine rules live in the engine repo — read
..\fluent-gpu\CLAUDE.md and use its fluentgpu skill (..\fluent-gpu\.claude\skills\fluentgpu\SKILL.md) for
how to build UI (signals, hooks, Element records, motion, the zero-alloc discipline). Engine changes are made
in ..\fluent-gpu and verified there (dotnet build src/FluentGpu.slnx Debug + Release, VerticalSlice).
There is no CI. Nothing builds on GitHub: releases are cut locally by ops/release/wavee-release.ps1
(both arches, Azure Trusted Signing, uploaded with gh). The wavee-stable feed and wavee-v* tags live on
this repository (github.com/christosk92/WaveeMusic).
Out-of-scope paths — do NOT read, search, edit, or summarize
The PlayPlay (Spotify DRM) derivation lives in the separate private repo wavee-playplay-private
(docs/guide/playplay-private-split.md). Unless the user names a specific file below and confirms it for
this session, do not read, grep, edit, or summarize:
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.
- 2d ago Changed · +3 lines · +90 tokens per session 3af67aecfa5c
- 6d ago First seen · 77 lines · 1,499 tokens per session scan A 5928e253de17
WaveeMusic CLAUDE.md is an instructions file published in the GitHub repository christosk92/WaveeMusic (50 stars, last pushed 2d ago), licensed MIT. It adds 1,589 tokens to every session, about $0.0079 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
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.
dotnet-skills AGENTS.md
AGENTS.md instructions for managedcode/dotnet-skills, covering agents.md, purpose, solution topology, rule precedence and path and linking rules.
BlazorBindings.Maui AGENTS.md
AGENTS.md instructions for Dreamescaper/BlazorBindings.Maui, covering mobile guidelines, platform, razor and component conventions and blazor bindings generation.
hex1b AGENTS.md
AGENTS.md instructions for mitchdenny/hex1b, covering ai coding agent guidelines for hex1b, 🛠️ available skills, 📋 project overview, key technologies and repository layout.