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 dapih/visualkan --skill visualkan-wizardgit clone --depth 1 https://github.com/dapih/visualkanWrote 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/dapih/visualkan/visualkan-wizard)<a href="https://agentmods.dev/skills/dapih/visualkan/visualkan-wizard"><img src="https://agentmods.dev/badge/skills/dapih/visualkan/visualkan-wizard/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/dapih/visualkan/visualkan-wizard"><img src="https://agentmods.dev/badge/skills/dapih/visualkan/visualkan-wizard.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 | $0.00078 | $0.01170 |
| Opus 5.5 | $0.00031 | $0.00468 |
| Sonnet 5.5 | $0.00016 | $0.00234 |
| Haiku 4.5 | $0.00008 | $0.00117 |
Grade A, and why
visualkan-wizard 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Guide the user through the Visualkan Controls, one step at a time, then start the run. Use this skill only when the user names it. A plain request to visualize something belongs to the visualkan skill.
Why this skill exists
The visualkan skill takes a flag for every Control, and several more besides. A user who does not know them has to read the documentation before every run. This skill replaces that reading with a short sequence of choices.
Step 1: Read the Control Catalog
Read references/controls.md from this skill's own directory. Resolve that relative path against the directory this skill was loaded from, not against the current working directory, and write it with forward slashes:
<this skill's own directory>/references/controls.md
The output lists every Control, every legal value, and the default.
Never write the value lists into this file, and never recite them from memory. The Control Catalog is generated directly from the code constants, so it cannot be out of date.
Step 2: Ask for the Controls
Ask one question at a time. Present the values as a numbered list. Mark the default. Accept a number or a name.
Offer this escape on every question: "Accept the remaining defaults." If the user takes it, stop asking and go to Step 3.
Ask in this order:
- Style. Show all seven, each with the one-line description from Step 1.
- Device. Ask this only if the user chose
mockup. Skip it otherwise. - Draw Level. Show the three values with their descriptions.
- Complexity. Show the three values with their Section counts.
Do not ask about the native Backend. When the user names no Backend, Step 1 of the visualkan skill detects the platform's own image generation tool and prefers it, at no cost, before this question ever matters. The confirmation block states which Backend won, so the user can still redirect it there.
Do not ask about Mode. Multi-frame runs call the image API three to five times, and a user who needs this skill cannot judge that cost. A user who wants multi-frame can pass --mode multi-frame to the visualkan skill.
What ships with it
2 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.
- 1mo ago First seen · 87 lines · 78 tokens per session scan A 3666c13e2b3a
visualkan-wizard is a skill published in the GitHub repository dapih/visualkan (2 stars, last pushed 2mo ago), licensed MIT. It adds 78 tokens to every session and 1,170 once invoked, about $0.0003 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.
Other skills, from other repositories
photographic-icon-set-generator
Generates consistent, locked-style sets of photographic, textured, or 3D-material-rendered icons via Ideogram — 3D-rendered, claymation, hand-painted, or isometric-with-material-texture icon packs that hold a shared style recipe across every icon in the batch. Use when the user asks for "3D icon set," "claymation…
brand-identity-sheet
Generates a single polished "brand identity sheet" image — a Dribbble-style board showing a UI card with the wordmark, a grid of textured app icons, pill-shaped buttons, a giant central wordmark treatment, and a secondary lockup with a brand glyph — and actually renders it via the ideogram MCP tools, not just drafts a…
character-model-sheet
Generates a single polished "character model sheet" image — a multi-panel character design board showing a full-body turnaround (front / 3-4 / side / back), a head & detail close-up sheet (face, hair/headwear, hands/props), a color palette, an overview text block (name, role, personality, wardrobe), and an optional…
moodboard-generator
Generates a single polished "moodboard" image — a 3×3 grid brand-exploration board (Color Palette, Typography, Logo Exploration, Iconography Style, Photography & Graphics, Material Samples, Abstract Patterns, Mood Imagery, Application Mockup) — and actually renders it via the ideogram MCP tools, not just drafts a…
concept-grid-generator
Generates a single "concept grid" image — a labeled comparison sheet showing several DISTINCT motif/icon concepts as tiles side by side, one locked palette and one locked rendering technique held constant across every tile — and actually renders it via the ideogram MCP tools, not just drafts a prompt. Use whenever the…
logo-prompting
Living reference for writing logo and brand-mark image-generation prompts (Ideogram-first, via ideogram-pack:ideogram-core-workflow-a). Use whenever the user asks for a logo prompt, a wordmark/icon direction, or wants feedback on a logo image-gen prompt they've drafted — even if they just paste a prompt and say "is…