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 skills add memi-design/design-skills --skill shader-design-engineeringgit clone --depth 1 https://github.com/memi-design/design-skillsWrote 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/skills/memi-design/design-skills/shader-design-engineering)<a href="https://agentmods.dev/skills/memi-design/design-skills/shader-design-engineering"><img src="https://agentmods.dev/badge/skills/memi-design/design-skills/shader-design-engineering/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/skills/memi-design/design-skills/shader-design-engineering"><img src="https://agentmods.dev/badge/skills/memi-design/design-skills/shader-design-engineering.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 | $0.00049 | $0.00856 |
| Opus 5 | $0.00024 | $0.00428 |
| Sonnet 5 | $0.00010 | $0.00171 |
| Haiku 4.5 | $0.00005 | $0.00086 |
Grade A, and why
shader-design-engineering 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 9d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shader Design Engineering
Build a shader only when it clarifies state, supports a visual system, communicates spatial change, or creates bounded delight. Treat the shader as product behavior with a fallback, not as decoration that can obscure content.
Workflow
- Inspect the rendering surface, deployment targets, existing renderer, asset licenses, design tokens, accessibility settings, and performance tooling.
- Write an effect contract: visual purpose, input and coordinate spaces, uniforms, textures, output color and alpha semantics, animation clock, quality tiers, fallback, and acceptance evidence.
- Choose the smallest compatible effect:
- Use a color effect when output depends only on the current pixel.
- Use a distortion effect when the shader changes sample coordinates.
- Use a layer or texture effect only when neighboring samples are necessary.
- Use a separate render pass only when the effect cannot fit the host framework's bounded effect API.
- Normalize coordinates explicitly. Keep pixel, normalized device, UV, view, and texture spaces named rather than relying on implicit conversions.
- Keep time and randomness controllable. Accept a clock and seed from the host so tests, reduced motion, screenshots, and replays remain deterministic.
- Perform lighting and interpolation in a documented working color space. Preserve premultiplied alpha when the host requires it, and convert only at known boundaries.
- Add dithering after the intended tone or color mapping and before final quantization. Match the technique to the artifact: ordered patterns for deterministic low-cost output, noise-shaped methods when visible structure is unacceptable.
- Provide reduced-motion, reduced-transparency, low-power, unsupported-platform, and renderer-failure behavior before polishing the full effect.
- Profile the target interaction with realistic content. Record frame time, GPU work, resolution, device, browser or OS, and quality tier.
- Verify the effect visually and structurally. Capture deterministic frames, inspect compilation and validation messages, exercise the fallback, and report any untested platform honestly.
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 64 lines · 49 tokens per session scan A ea907b8225e7
shader-design-engineering is a skill published in the GitHub repository memi-design/design-skills (7 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 856 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
animate
Build a web animation: whether it should animate at all, the purpose, the tool, the properties, the easing curve, the duration, interruption and exit. Writes the CSS or Motion code for dropdowns, modals, toasts, tooltips, accordions, press feedback, stagger and scroll reveals. Use to animate something or make a…
accessibility
Use when making a web UI conform to WCAG 2.2 Level AA — axe-core or Lighthouse a11y violations, keyboard operability, focus management, ARIA roles/names/live regions, contrast, tap-target size. NOT palette or visual intent (that is design), NOT test-runner setup (that is testing-web), NOT LCP/page-speed (that is…
motion-lexicon
Design, build, compose, implement, review, and contribute polished product interfaces with Motion Lexicon components and motion primitives. Use this skill when a user asks for a complete React page, landing page, dashboard, settings screen, or product surface in the Motion Lexicon visual language; asks what motion…
motion-craft
Use when an interface moves and the movement has to feel right — durations and easing, what must never animate, fixing motion that reads sluggish, cheap or janky, and reduced-motion. Web and native. NOT the visual system (that is design), NOT the graded critique (that is design-loop).
animejs-animation-v2
Anime.js Animation Skill workflow skill. Use this skill when the user needs Advanced JavaScript animation library skill for creating complex, high-performance web animations and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.
design-engineering
Premium design engineering skill for agentic workflows — produces high-end, distinctive UI designs using DESIGN.md as the portable contract across Pencil MCP (in-IDE canvas), Figma MCP (team handoff + design tokens), and Google Stitch (vibe exploration + AI generation). Enforces anti-generic principles, WCAG 2.2 AA…