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/krispuckett/swiftuishaders/agents-mdgit clone --depth 1 https://github.com/krispuckett/SwiftUIShadersWrote 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/krispuckett/swiftuishaders/agents-md)<a href="https://agentmods.dev/instructions/krispuckett/swiftuishaders/agents-md"><img src="https://agentmods.dev/badge/instructions/krispuckett/swiftuishaders/agents-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 | $0.02320 | $0.02320 |
| Opus 5 | $0.01160 | $0.01160 |
| Sonnet 5 | $0.00464 | $0.00464 |
| Haiku 4.5 | $0.00232 | $0.00232 |
Grade A, and why
SwiftUIShaders AGENTS.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 5d 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md: architecture for coding agents
This file is for an AI agent (Claude Code, Codex, etc.) asked to use, extend, modify, or rebuild these shaders. It explains exactly how the package is wired so you can work without re-deriving the conventions.
What this package is
- A SwiftPM library,
SwiftUIShaders, with two source files:Sources/SwiftUIShaders/Shaders/SwiftUIShaders.metal: 41[[ stitchable ]]SwiftUI fragment shaders plus 5 shared helper functions. This is the source of truth.Sources/SwiftUIShaders/ShaderEffects.swift: one typedViewmodifier per shader, plus two privateViewModifiers (_StaticShaderEffect,_AnimatedShaderEffect) that do the actuallayerEffectplumbing.
- No third-party dependencies. No app code. The
bcs_prefix is just a namespace (it originated as "book cover shaders").
How SwiftUI Metal shader effects work (the mental model)
SwiftUI exposes three shader entry points on View: .colorEffect, .layerEffect, and .distortionEffect. Every shader here is a layerEffect, because they all need to sample neighboring pixels (blur, displacement, refraction). A layerEffect Metal function has this fixed signature shape:
[[ stitchable ]] half4 bcs_name(
float2 position, // pixel being computed (SwiftUI supplies this)
SwiftUI::Layer layer, // the source view, sample it with layer.sample(coord) (SwiftUI supplies this)
float2 size, // view size in pixels <- first user argument
float time, // seconds, for animation (only on animated shaders)
float param1, // ...effect-specific knobs
...
) { ... }
position and layer are provided by SwiftUI automatically. Everything after layer is provided in order by the Swift call, via Shader.Argument values (.float, .float2, .color, …). The arguments must match the Metal parameter order exactly.
At runtime the shaders live in a compiled default.metallib inside the package's resource bundle. You reach them with:
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.
- 5d ago First seen · 143 lines · 2,320 tokens per session scan A e6f256414b7a
SwiftUIShaders AGENTS.md is an instructions file published in the GitHub repository krispuckett/SwiftUIShaders (328 stars, last pushed 3mo ago), licensed MIT. It adds 2,320 tokens to every session, about $0.0116 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
MarkdownView AGENTS.md
Instructions for keitaoouchi/MarkdownView, covering agents, technical components, relationships (data/event flow overview), extension points (overview) and platform / distribution.
AniShelf AGENTS.md
Instructions for samuelhe52/AniShelf, covering anishelf - developer notes, workflow, code style, testing and commits.
swift-architecture-skill CLAUDE.md
Instructions for efremidze/swift-architecture-skill, covering swift architecture skill, project structure, how the skill works and key conventions.
hermex AGENTS.md
AGENTS.md instructions for uzairansaruzi/hermex, covering hermex, what makes hermex special?, 1. open at the core, 2. performance without compromise and 3. remote ready.
swift-architecture-skill AGENTS.md
Instructions for efremidze/swift-architecture-skill, covering agents guidelines for swift architecture skill, working with this repository, 1. understanding the skill, 2. modifying architecture playbooks and 3. testing and validation.
everything-claude-code-mobile copilot-instructions.md
Copilot instructions for ahmed3elshaer/everything-claude-code-mobile: Use this repository's mobile guidance for Android, iOS, and Kotlin Multiplatform work.