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 luminary19/atelier --skill codex-imagegen-tastegit clone --depth 1 https://github.com/luminary19/atelierWrote 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/luminary19/atelier/codex-imagegen-taste)<a href="https://agentmods.dev/skills/luminary19/atelier/codex-imagegen-taste"><img src="https://agentmods.dev/badge/skills/luminary19/atelier/codex-imagegen-taste/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/luminary19/atelier/codex-imagegen-taste"><img src="https://agentmods.dev/badge/skills/luminary19/atelier/codex-imagegen-taste.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 | $0.00200 | $0.02656 |
| Opus 5 | $0.00100 | $0.01328 |
| Sonnet 5 | $0.00040 | $0.00531 |
| Haiku 4.5 | $0.00020 | $0.00266 |
Grade A, and why
codex-imagegen-taste 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 8d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- 8d ago First seen · 178 lines · 200 tokens per session scan A 82bedaf88fad
codex-imagegen-taste is a skill published in the GitHub repository luminary19/atelier (2 stars, last pushed 2mo ago), with no licence file. It adds 200 tokens to every session and 2,656 once invoked, about $0.0010 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 2026-08-31.
Other skills, from other repositories
paint
Paint a complete visual universe with genjutsu - art direction brainstorm, design system, implementation, audit. Anti-AI-slop design pipeline. Adapts to Web, Android (Compose), Apple (SwiftUI).
morphous-catalog
Create or refresh Morphous website design-system/theme bundles from animal, insect, plant, landscape, mineral, weather, or other nature motifs. Use when Codex is asked to generate Morphous motif images, light/dark design-system boards, reusable image prompts, generated web assets, shadcn/tweakcn theme exports, or the…
design-carousel-slide
Generate a LinkedIn / Instagram multi-slide carousel — single HTML file with N square 1080×1080 .canvas divs, each representing one slide. Default N=5 (cover + 3 content + closing CTA). Cover and closing always use the brand's most distinctive treatments; middle slides are content-led. Reads ./design/ /DESIGN.md…
design-quote-card
Generate a pull-quote / insight card — TWO pixel-exact HTML canvases in one file: 1080×1080 (square, default) AND 1080×1920 (story variant). Text-dominant, Fraunces-led, no chrome. The quote IS the artifact. Reads ./design/ /DESIGN.md, tokens.css, and components.html. Triggers include "quote card for X", "pull quote"…
design-twitter-card
Generate a Twitter/X card artifact — pixel-exact HTML canvas at 1600×900 (in-feed image) by default, with 1200×630 (Open Graph link card) opt-in. Reads ./design/ /DESIGN.md, tokens.css, and components.html. Triggers include "twitter card for X", "x card for X", "twitter post about X", "OG card", "/twitter-card"…
design-youtube-channel-art
Generate a YouTube channel banner — pixel-exact 2560×1440 full canvas + 1546×423 safe-zone preview canvas in a single HTML file. The full banner bleeds to the edges (TV display uses it all); the safe zone (1546×423 centered) is the cross-device area where critical content MUST sit. Reads ./design/ /DESIGN.md…