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 jirathip-dev/morsel --skill food-artgit clone --depth 1 https://github.com/jirathip-dev/morselWrote 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/jirathip-dev/morsel/food-art)<a href="https://agentmods.dev/skills/jirathip-dev/morsel/food-art"><img src="https://agentmods.dev/badge/skills/jirathip-dev/morsel/food-art/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/jirathip-dev/morsel/food-art"><img src="https://agentmods.dev/badge/skills/jirathip-dev/morsel/food-art.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 | $0.00016 | $0.01382 |
| Opus 5.5 | $0.00006 | $0.00553 |
| Sonnet 5.5 | $0.00003 | $0.00276 |
| Haiku 4.5 | $0.00002 | $0.00138 |
Grade A, and why
food-art 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 1mo 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Morsel food art
Add original generic food illustrations to the approved V1 library. This is an offline authoring workflow, not runtime generation or meal recognition. It never changes app assets, databases, profiles or nutrition records.
When to Use
- Add a new food or refine one existing illustration in this library.
- Export both Paper and Night ink with stable IDs and honest provenance.
- Do not use for actual meal photos, portion estimation, new art directions, app integration, or publishing without authorization.
Prerequisites
Run through terminal at the Morsel repository root. Existing Python 3 with
Pillow and rsvg-convert are required. No network, API keys, paid service or
model-specific tool is involved. Do not install dependencies on the host;
escalate missing prerequisites. Exact exercised versions are in the evidence.
Read docs/art/food-library/ART-SPEC.md and inspect both approved-reference
PNGs in its references/ directory with vision_analyze. Reuse the source
JSON and layer vocabulary in docs/art/food-library/sources/, particularly
mango.json for fruit or jasmine-rice.json for a vessel.
How to Run
Short designer invocation: “Use food-art to add ; keep approved V1.”
-
Author one JSON spec with
write_file, usingskills/food-art/templates/food.json. Choose an unused stable slug, useful aliases, a category, a food-specific silhouette and layered original paths.layersis SVG path geometry, not a prompt. Start from shared vessel geometry only when the food genuinely uses that vessel. No imported stock drawing. -
Run through
terminal:PYTHONDONTWRITEBYTECODE=1 python3 skills/food-art/scripts/library.py add path/to/new-food.jsonThis single command registers the source, renders two editable SVG masters and transparent PNGs at 64/192/512, updates the versioned catalog, refreshes both galleries and contact sheets, copies approved controls, and validates. The command must exit 0. Inspect stdout's rebuilt/skipped IDs and PASS report.
-
Inspect the refreshed contact sheets with
vision_analyze, sequentially, and view the art at 64 and 40 CSS pixels in both galleries. Keep the shape quiet like the approved controls. A mechanical PASS is not visual approval. -
If a named defect exists, edit only that source JSON with
patch, then run thebuildcommand below. Record each manual step and retry. Never rename an existing ID to hide a revision. New silhouette work is manual design time, not included in a renderer-only speed claim. -
For delivery, run the capture command below for fresh 390×844 contexts. Retain elapsed wall time, changed/unchanged hashes and mtimes, raw exits, and visual caveats. Update the package manifest after final evidence edits. Owner reviews the art before any app integration.
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.
- 1mo ago First seen · 121 lines · 16 tokens per session scan A 7a3e7488e855
food-art is a skill published in the GitHub repository jirathip-dev/morsel (0 stars, last pushed 26d ago), licensed MIT. It adds 16 tokens to every session and 1,382 once invoked, about $0.0001 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 2026-09-14.
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.
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.
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.