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 tdimino/claude-code-minoan --skill atmosphere-shadergit clone --depth 1 https://github.com/tdimino/claude-code-minoanWrote 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/tdimino/claude-code-minoan/atmosphere-shader)<a href="https://agentmods.dev/skills/tdimino/claude-code-minoan/atmosphere-shader"><img src="https://agentmods.dev/badge/skills/tdimino/claude-code-minoan/atmosphere-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/tdimino/claude-code-minoan/atmosphere-shader"><img src="https://agentmods.dev/badge/skills/tdimino/claude-code-minoan/atmosphere-shader.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00096 | $0.03076 |
| Opus 5 | $0.00048 | $0.01538 |
| Sonnet 5 | $0.00019 | $0.00615 |
| Haiku 4.5 | $0.00010 | $0.00308 |
Grade A, and why
atmosphere-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 11d 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 — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Atmosphere Shader Skill
Render physically-accurate skies, sunsets, and planetary atmospheres through atmospheric scattering — Rayleigh, Mie, and Ozone models composed via raymarching in GLSL fragment shaders. Four progressive modes from flat backdrop to LUT-optimized planetary pipeline.
Modes
| Mode | Output | Complexity |
|---|---|---|
sky-dome |
Single-pass fragment shader, flat sky backdrop | Entry point |
atmosphere-post |
Depth-aware post-processing effect with atmospheric fog | Intermediate |
planet |
Spherical atmosphere shell around a mesh, logarithmic depth | Advanced |
lut |
Transmittance + Sky View + Aerial Perspective LUTs, FBO pipeline | Production |
Gotchas — What Claude Gets Wrong
These are the highest-signal items in this skill. Every one is a concrete, reproducible failure mode.
1. Wrong scattering coefficients
Claude invents plausible-looking but physically incorrect beta values. Use these exact constants for Earth:
const vec3 BETA_R = vec3(5.8e-3, 13.5e-3, 33.1e-3); // Rayleigh scattering (1/km)
const float BETA_M_SCATTER = 21e-3; // Mie scattering
const float BETA_M_EXT = 21e-3 * 1.1; // Mie extinction (scatter + absorb)
const vec3 BETA_OZONE_ABS = vec3(0.65e-3, 1.881e-3, 0.085e-3); // Ozone absorption
const float RAYLEIGH_SCALE_HEIGHT = 8.0; // km
const float MIE_SCALE_HEIGHT = 1.2; // km
const float MIE_G = 0.76; // Henyey-Greenstein anisotropy
const float ATMOSPHERE_HEIGHT = 100.0; // km (Karman line)
See references/scattering-coefficients.md for Mars and custom planet parameter sets.
2. Missing nested light march
Claude implements only the view-ray loop, producing a blue gradient but no sunsets. The critical missing piece: at each sample point along the primary ray, a secondary march toward the sun accumulates sunOD (optical depth between sample and sun). Without this, tau only contains view-direction extinction and the sky is uniformly blue regardless of sun angle.
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.
- 11d ago First seen · 289 lines · 96 tokens per session scan A 82ce4f1c3380
atmosphere-shader is a skill published in the GitHub repository tdimino/claude-code-minoan (41 stars, last pushed today), licensed MIT. It adds 96 tokens to every session and 3,076 once invoked, about $0.0005 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 skills, from other repositories
manager
A session-to-GitHub tracker that creates, updates, and reads issues across repositories, including their labels, parent epics, and project-board placement.
art-director
Orchestrate iterative visual style searches with branch prompts, decision graphs, feedback loops, and final direction selection.
idea
Use when capturing ONE new idea the user voices and wants recorded — "save this idea", "I have an idea", "log this idea", "/idea", "idea: ...". Creates a provenance-tracked folder (one folder per idea) in your ideas repo, dedups against an index, optionally mirrors to a GitHub Project view filtered by label:idea. NOT…
pm-feedback
A feedback-analysis aid that turns spreadsheet data, CSV files, pasted text, or review screenshots into organized product insights. It groups themes, identifies sentiment, examines trends and sources, calculates NPS, and extracts user types.
pm-metrics
A product-metrics review aid that examines trends, unusual changes, possible causes, and recommended actions. It can organize a main product metric into lower-level measures, inspect retention and funnels, read A/B tests, and compare results with goals.
weekly-planning
A planning workflow that turns a completed weekly review and existing backlog into prioritized outcomes for one ISO calendar week.