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-compile.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-compile)<a href="https://agentmods.dev/commands/kaltinril/shadowdusk/shader-compile"><img src="https://agentmods.dev/badge/commands/kaltinril/shadowdusk/shader-compile.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 | $0.00000 | $0.00401 |
| Opus 5 | $0.00000 | $0.00200 |
| Sonnet 5 | $0.00000 | $0.00080 |
| Haiku 4.5 | $0.00000 | $0.00040 |
Grade A, and why
shader-compile scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
/shader-compile — Compile a single .fx shader file
Compiles one HLSL Effect (.fx) file to a target platform using ShadowDusk CLI, then reports the result.
Usage
Invoke as: /shader-compile <path-to-fx-file> [platform]
If no platform is specified, default to OpenGL (the most cross-platform target).
Steps
-
Verify the input file exists and has a
.fxor.hlslextension. -
Run the compiler:
dotnet run --project src/ShadowDusk.Cli -- \
--input "$INPUT_FILE" \
--platform "$PLATFORM" \
--output "$INPUT_FILE_WITHOUT_EXTENSION.mgfx"
Valid --platform values: OpenGL, DirectX, Metal
-
On success, report:
- Output file path and size
- Compilation time
- Techniques and passes found in the effect
- Target platform
-
On failure, report:
- The exact error message from the compiler
- Source file, line number, and column
- The raw compiler diagnostic output
- Suggested fix if the error pattern is recognized (e.g., undeclared identifier, wrong semantic name, unsupported feature)
Common HLSL .fx errors to recognize:
error X3004: undeclared identifier→ typo or missing declarationerror X3000: syntax error→ malformed syntax, often a missing semicolonerror X4507: maximum temp register index exceeded→ shader too complex for SM 3.0 targeterror X3501: 'main': entrypoint not found→ wrong entry point name in technique declaration- Sampler type mismatch →
sampler2DvsSamplerState(useSamplerStatefor DX10+)
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 · 42 lines · 0 tokens per session scan A 4247e5042ffd
shader-compile is a command published in the GitHub repository kaltinril/ShadowDusk (14 stars, last pushed 23d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 401 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
troubleshoot
Diagnose a Poppify reel that came out wrong. Walks the symptom → root cause → action decision tree.
qa-changes
This skill should be used when the user asks to "QA a pull request", "test PR changes", "verify a PR works", "functionally test changes", or when an automated workflow triggers QA validation of code changes. Provides a structured methodology for setting up the environment, exercising changed behavior, and reporting…
brand-generate
Generate an on-brand document from a saved Brand Profile.
fix
Universal debugging and fix application with semantic code analysis.
list
List available Piper TTS TTS voices with optional filtering.
http-service
Build, review or debug a Bun HTTP service. Loads the http-service skill, then works the task through its workflow.