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 vinsonconsulting/claude-skill-foundry --skill textmode-jsgit clone --depth 1 https://github.com/vinsonconsulting/claude-skill-foundryWrote 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/vinsonconsulting/claude-skill-foundry/textmode-js)<a href="https://agentmods.dev/skills/vinsonconsulting/claude-skill-foundry/textmode-js"><img src="https://agentmods.dev/badge/skills/vinsonconsulting/claude-skill-foundry/textmode-js.svg" alt="Measured on agentmods" 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 | $0.00211 | $0.01862 |
| Opus 5 | $0.00105 | $0.00931 |
| Sonnet 5 | $0.00042 | $0.00372 |
| Haiku 4.5 | $0.00021 | $0.00186 |
Grade A, and why
textmode-js 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.
How it starts
The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
textmode-js
textmode.js is a zero-dependency TypeScript creative-coding library for real-time
ASCII / textmode graphics. It renders to a grid of character cells on a WebGL2
canvas with p5.js-like ergonomics. Use it to author, debug, and export
glyph-grid sketches.
Mental model
- The canvas is a grid of cells, not pixels. Each cell holds one glyph, a char color (the glyph's foreground), and a cell color (its background).
- You draw with p5-style primitives, but coordinates and sizes are in cells.
- The origin
(0,0)is the grid CENTER. +x is right, +y is down, -y is up. This is the single biggest trip-up — arect/pointwith no transform lands at the center, not the top-left. - A sketch is a lifecycle:
create()once →setup()once →draw()every frame. State setters (char,charColor,cellColor, transforms) are sticky — they apply to every draw call until changed or untilpop()restores them.
Minimal sketch (ESM)
import { textmode } from "textmode.js";
const t = textmode.create({
width: window.innerWidth,
height: window.innerHeight,
fontSize: 16,
frameRate: 60,
});
t.setup(() => {
// Runs once after the renderer + grid exist.
// Load fonts / images / shaders here (these are async — await them).
});
t.draw(() => {
t.background(18, 20, 28); // clear the grid every frame
t.char("@"); // glyph used by following draw calls
t.charColor(120, 220, 160); // glyph (foreground) color
t.cellColor(0, 0, 0); // cell (background) color
// (0,0) is the grid CENTER; rect(w,h) is centered there, sized in CELLS.
t.rect(t.grid.cols / 2, t.grid.rows / 2);
});
t.windowResized(() => t.resizeCanvas(window.innerWidth, window.innerHeight));
UMD is identical minus the import — load the script, then use the global
textmode:
<script src="https://cdn.jsdelivr.net/npm/textmode.js@latest/dist/textmode.umd.js"></script>
<script>
const t = textmode.create({ width: 800, height: 600, fontSize: 16, frameRate: 60 });
t.draw(() => { t.background(0); t.char("#"); t.charColor(0, 255, 0); t.rect(10, 6); });
</script>
What ships with it
8 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 · 149 lines · 211 tokens per session scan A 6114a9200b08
textmode-js is a skill published in the GitHub repository vinsonconsulting/claude-skill-foundry (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 211 tokens to every session and 1,862 once invoked, about $0.0011 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
p5js
Use when users request: p5.js sketches, creative coding, generative art, interactive visualizations, canvas animations, browser-based visual art, data viz, shader effects, or any p5.js project.
remotion
Render a short (10s) video on any topic with Remotion - the agent writes a storyboard JSON, a bundled React/Remotion project renders it to an MP4, and the clip is committed to the repo and delivered by URL. No editor, no external generative API.
animate
Generate animated videos and motion graphics from natural language descriptions. Creates a standalone Vite + React project with Framer Motion scenes that auto-play in the browser. Use when the user wants to create animations, motion graphics, video intros, animated presentations, or product demos.
scroll-hero-video
Build Apple-style scroll-driven video hero sections. A full-screen video scrubs frame-by-frame as the user scrolls, with text overlay fade, mobile fallback, and buttery-smooth rAF lerp.
scroll-scrub-video
Build scroll-driven video hero sections where a video scrubs frame-by-frame as the user scrolls. Covers video encoding, blob preloading, rAF-driven playback, mobile fallback, and the two common modes (fast Soleiman-style vs. full-section chronological).
scroll-scrub-hero
Build a hero section where a video scrubs frame-by-frame driven by scroll position — Apple-product-page style. Covers video encoding, rAF lerp loop, mobile fallback, and Safari/iOS priming.