Borrowing it
Nothing to install: this file belongs to rbstxt/agent-shader. 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/rbstxt/agent-shader/main/.agents/skills/panzoid-shader/SKILL.mdgit clone --depth 1 https://github.com/rbstxt/agent-shaderWrote 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/rbstxt/agent-shader/panzoid-shader)<a href="https://agentmods.dev/skills/rbstxt/agent-shader/panzoid-shader"><img src="https://agentmods.dev/badge/skills/rbstxt/agent-shader/panzoid-shader/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/rbstxt/agent-shader/panzoid-shader"><img src="https://agentmods.dev/badge/skills/rbstxt/agent-shader/panzoid-shader.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 | $0.00119 | $0.02301 |
| Opus 5.5 | $0.00048 | $0.00920 |
| Sonnet 5.5 | $0.00024 | $0.00460 |
| Haiku 4.5 | $0.00012 | $0.00230 |
Grade A, and why
panzoid-shader 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 2mo 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Panzoid Shader
Use the repository CLI or MCP tools to produce a complete, tested Panzoid Shader Object. Treat the shader contract as mandatory.
Workflow
- Start from
assets/base.glslor inspectassets/circle.glsl. - Write the fragment shader with the contract below.
- Choose explicit defaults that usually make every nonstandard parameter's behavior easy to understand. An unchanged default is acceptable when it is intentional and appropriate for the effect.
- Run
agent-shader test <shader.glsl> --out-dir <directory>and inspect every normal and RGB-only PNG plus the report. - Fix the shader or defaults until the report passes and the alpha diagnostics are visually clean. If
default-no-visible-changeappears, either choose a clearer default or confirm that the unchanged default is appropriate. - Run
agent-shader build <shader.glsl> --out <shader.json>. Build performs the full test again and writes JSON only on success. - Prefer the equivalent MCP tools when available. Return the Shader Object JSON as complete only after
agent-shader testpasses andagent-shader buildsucceeds.
Shader contract
- Start with
precision highp float;andprecision highp int;. - Declare
uniform sampler2D tDiffuse;andvarying vec2 vUvScaled;. - Prefer
vUvScaledas the screen-space UV source. Add a resolution-like uniform only when the user explicitly requests it or the effect genuinely needs externally supplied dimensions. - Map effect space with
vec2 p = vUvScaled * 2.0 - 1.0;only when centered effect coordinates are useful. - When
Positionis present, subtract it before applying the16.0 / 9.0centered-x correction needed by aspect-sensitive geometry. - When
Rotationis present, express it in clockwise degrees. - When
Scaleis present, treat it as avec2multiplier with[1, 1]as the default. - Sample the source with
texture2D(tDiffuse, vUvScaled)unless intentional distortion requires modified UVs. - Composite drawn pixels over
tDiffuseusing source-over and output premultiplied-alpha. Do not divide the resulting RGB by the output alpha. - Do not add anti-aliasing unless the user explicitly asks for it. This is an agent decision, not a validator rule.
- Omit shader comments by default. Include them when the user explicitly requests them or they are materially useful for the requested delivery.
- Assign the result to
gl_FragColor.
What ships with it
3 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.
- 2mo ago First seen · 115 lines · 119 tokens per session scan A 349b8e14ba64
panzoid-shader is a skill published in the GitHub repository rbstxt/agent-shader (0 stars, last pushed 2mo ago), licensed MIT. It adds 119 tokens to every session and 2,301 once invoked, about $0.0005 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 2026-08-31.
panzoid-shader compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| panzoid-shaderrbstxt/agent-shader | Skill | 0 | 2mo ago | MIT | A | 119 | Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |