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 howdeploy/kisa-stack --skill shoji-shadersgit clone --depth 1 https://github.com/howdeploy/kisa-stackWrote 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/howdeploy/kisa-stack/shoji-shaders)<a href="https://agentmods.dev/skills/howdeploy/kisa-stack/shoji-shaders"><img src="https://agentmods.dev/badge/skills/howdeploy/kisa-stack/shoji-shaders/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/howdeploy/kisa-stack/shoji-shaders"><img src="https://agentmods.dev/badge/skills/howdeploy/kisa-stack/shoji-shaders.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 | $0.00050 | $0.00952 |
| Opus 5.5 | $0.00020 | $0.00381 |
| Sonnet 5.5 | $0.00010 | $0.00190 |
| Haiku 4.5 | $0.00005 | $0.00095 |
Grade A, and why
shoji-shaders 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 17d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shoji shader workflow
Find the user's current config first. Public source and detailed map:
https://github.com/howdeploy/kisa-stack/tree/main/dotfiles ; read
docs/shaders.md and sources.json there or in a local checkout. No private
project memory or author-specific path is required by this skill.
Read the reference and define the effect
Separate observed motion, code evidence and assumptions. A still image proves appearance, not trajectory or timing. For Shadertoy, inspect Image and the actual buffer dependencies when available; do not copy an unbounded simulation into a finite transition without lifecycle control. If a requested reference cannot be read, explain that limit instead of inventing what it shows.
Before editing, describe the intended geometry, material, motion and endpoints. Identify where the reveal starts, what remains fixed, whether particles carry source pixels or only sampled colors, and how the effect reverses. Preserve the user's accepted aesthetic; do not substitute a different effect based on keywords.
Select the real pipeline
| Pipeline | Contract |
|---|---|
ShojiWM src/effect/*.frag |
GLSL ES 1.00 body; vec4 shader_main(EffectContext effect); texture2D(tex, effect.texture_uv) |
Quickshell shaders/*.frag |
GLSL 440 with Qt uniform/sampler bindings; compile to .frag.qsb; QML ShaderEffect |
The compositor does not accept Qt's #version 440 program or Shadertoy mainImage
unchanged. Choose compileEffect, compileWindowEffect, compileLayerEffect or
compilePopupEffect according to the target. Match the source type: a window
replacement reads windowSource(), a backdrop reads backdropSource().
Read src/index.tsx assignments, the closest existing effect module and its callers.
Read the fork's docs/docs/configuration/effects.md and shader API types for exact
contracts. Paths passed to loadShader resolve from the config package root.
Use texture UV for sampling, content-space coordinates for geometry. Framebuffer
*_px and logical capture/damage padding are different units, especially on scaled
outputs. Explicitly bind uniforms/textures; there is no automatic Shadertoy clock.
What ships with it
1 file 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.
- 17d ago First seen · 82 lines · 50 tokens per session scan A f1dd9d988621
shoji-shaders is a skill published in the GitHub repository howdeploy/kisa-stack (55 stars, last pushed 11d ago), licensed MIT. It adds 50 tokens to every session and 952 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-29.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.