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/commands/shader-review.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/commands/kaltinril/shadowdusk/shader-review)<a href="https://agentmods.dev/commands/kaltinril/shadowdusk/shader-review"><img src="https://agentmods.dev/badge/commands/kaltinril/shadowdusk/shader-review/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/kaltinril/shadowdusk/shader-review"><img src="https://agentmods.dev/badge/commands/kaltinril/shadowdusk/shader-review.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 | $0.00638 |
| Opus 5 | $0.00000 | $0.00319 |
| Sonnet 5 | $0.00000 | $0.00128 |
| Haiku 4.5 | $0.00000 | $0.00064 |
Grade A, and why
shader-review 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 4d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/shader-review — Deep review of shader or transpilation code
Reviews either a .fx shader source file or C# transpilation/compilation code for correctness, cross-API compatibility, and MonoGame compatibility.
Usage
/shader-review <path>
- If path is a
.fx/.hlslfile: review the shader source - If path is a
.csfile: review the C# shader pipeline code - If no path: review all modified files in the current git diff
Shader Source Review Checklist
Syntax & Structure
- All techniques have at least one pass
- VS and PS entry points declared in each pass match defined functions
- Shader model version (
vs_3_0,ps_3_0, etc.) is appropriate for MonoGame target - No
discardin vertex shader
Semantics
- Vertex input semantics use correct MonoGame names (
POSITION0,TEXCOORD0,COLOR0, etc.) - Pixel shader output uses
SV_TARGET(notCOLORfor SM4+) -
SV_POSITIONused for VS output clip position -
TEXCOORDslots don't exceed SM 3.0 limit (8 for SM3, 16 for SM4+)
Cross-API Concerns
- No assumptions about UV coordinate origin (document if flipping is needed)
- cbuffer / uniform layout is explicit (no implicit padding surprises)
- Sampler state declared with
SamplerStatenot legacysampler2D - No DX-only intrinsics without fallback (
ddx_fine,ddy_fine→ useddx/ddy) - Texture arrays, geometry shaders, compute shaders: flag as DX-only if present
MonoGame Compatibility
- Parameter names match what the game code will set via
Effect.Parameters["name"] - Matrix parameters use
float4x4notmatrixalias (both work but be consistent) - Texture parameters paired with a named
SamplerStatefor MonoGame's sampler binding
C# Transpilation Code Review Checklist
- SPIR-V intermediate is generated correctly from HLSL input
- SPIRV-Cross options set correctly for target (combined samplers for GL, etc.)
- Y-flip applied (or documented as not needed) for OpenGL path
- cbuffer → uniform block mapping is correct for std140 layout
- Error from native tool is parsed and mapped to
ShaderErrorwith correct line/col - Temp files cleaned up in all code paths
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.
- 4d ago First seen · 51 lines · 0 tokens per session scan A bc2d11ec0511
shader-review is a command published in the GitHub repository kaltinril/ShadowDusk (14 stars, last pushed 25d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 638 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 2026-09-04.
Other commands, from other repositories
accessibility-pass
Review accessibility coverage for input, readability, audio, and difficulty options against design intent.
animation-pass
Review animation implementation, state machines, transitions, and gameplay readability.
art-2d-pass
Review 2D art assets for naming, resolution, atlas config, animation, tilemap rules, and placeholder readiness.
art-3d-pass
Review 3D art assets for export conventions, rigs, animation clips, materials, lighting, and LOD compliance.
audio-pass
Functional audio review for implementation, mix coverage, clarity, and player feedback.
cert-check
Review the current state against certification and platform compliance expectations.