Borrowing it
Nothing to install: this file belongs to kaltinril/ShadowDusk. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/kaltinril/ShadowDusk/main/CLAUDE.mdgit clone --depth 1 https://github.com/kaltinril/ShadowDuskWrote 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/kaltinril/shadowdusk/claude-md)<a href="https://agentmods.dev/instructions/kaltinril/shadowdusk/claude-md"><img src="https://agentmods.dev/badge/instructions/kaltinril/shadowdusk/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 | $0.04460 | $0.04460 |
| Opus 5 | $0.02230 | $0.02230 |
| Sonnet 5 | $0.00892 | $0.00892 |
| Haiku 4.5 | $0.00446 | $0.00446 |
Grade A, and why
ShadowDusk 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 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ShadowDusk — Cross-Platform MonoGame Shader Compiler
THE PURPOSE (read this first)
The product is a drop-in mgfxc replacement: a self-contained library a user adds to their MonoGame/KNI project on Linux, macOS, or Windows, that compiles .fx → .mgfx in memory at runtime, requiring nothing but the library itself — no fxc.exe, no mgfxc, no Wine, no Windows SDK, no native toolchain the user has to install separately. Its output loads and renders identically to mgfxc's in the real MonoGame/KNI runtime. One faithful compiler; the same mgfxc-equivalent result everywhere.
The distinctions that carry the most weight — internalize these, they have drifted before (full detail, success criteria, and the backend table in docs/the-purpose.md):
- The library is the product. The deliverable is the in-memory compiler called at runtime (
IShaderCompiler.CompileAsync(fx) → .mgfx bytes). The CLI and MGCB plugin are delivery shapes of the same library; the browser / WASM shader-fiddle is ONLY a sample of reach — never the product. Don't let sample work redefine the goal. - One pipeline, everywhere — NO substitute compilers. Every host runs the same faithful pipeline (HLSL →
[DXC]→ SPIR-V →[SPIRV-Cross]→ GLSL →[managed rewrite + MGFX writer]→.mgfx; orvkd3d-shader→ DXBC for DirectX). A host must not swap in a different frontend/compiler to make a platform "work" — different compiler ⇒ different output ⇒ silently breaks the "identical tomgfxc" promise. If a faithful component can't run on a host yet, that host's runtime-compile is not done — never a licence to substitute. - "Self-contained" is a hard requirement. Native pieces ride inside the NuGet package (transitive native assets), never a separate manual install. "Add the package, call the API" is the entire setup.
- The bar is the real runtime, not our tests. Only ShadowDusk's
.mgfxloading in MonoGame'sEffectand rendering likemgfxc's proves the promise. Tests/our-own-renderer images are proxies, not the bar. Compare same-backend only (GL↔GL, DX↔DX), never cross-backend. "Same asmgfxc" = behaviorally equivalent +Effect-loadable, NOT byte-identical (that's a non-goal).
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 · 159 lines · 4,460 tokens per session scan A db3a9e46bd11
ShadowDusk CLAUDE.md is an instructions file published in the GitHub repository kaltinril/ShadowDusk (14 stars, last pushed 23d ago), licensed MIT. It adds 4,460 tokens to every session, about $0.0223 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 2026-09-04.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
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.