visualkan-wizard

A guided setup for the Visualkan visual-explanation tool. It asks for its display choices one at a time before starting a run.

In plain words
What is it for?
Use it only when someone explicitly asks to run the Visualkan wizard; ordinary requests for diagrams, sketches, or visual explanations belong to the main Visualkan tool.
Why use it?
It helps users choose the tool's available settings without needing to read and remember the full control list first.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/dapih/visualkan/visualkan-wizard
Any agent
npx skills add dapih/visualkan --skill visualkan-wizard
Clone the repo
git clone --depth 1 https://github.com/dapih/visualkan

Made for: Claude Code, Codex.

Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,170 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00078 $0.01170
Opus 5 $0.00039 $0.00585
Sonnet 5 $0.00016 $0.00234
Haiku 4.5 $0.00008 $0.00117

Measured 2d ago against content hash 3666c13e2b3a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 2d 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.

skills/visualkan-wizard/SKILL.md · 87 lines

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:

  1. Style. Show all seven, each with the one-line description from Step 1.
  2. Device. Ask this only if the user chose mockup. Skip it otherwise.
  3. Draw Level. Show the three values with their descriptions.
  4. 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.

Read the full file on GitHub · 87 lines

Files

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.

Changes

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.

  1. 2d ago First seen · 87 lines · 78 tokens per session scan A 3666c13e2b3a

Subscribe to this mod's changes

visualkan-wizard is a skill published in the GitHub repository dapih/visualkan (2 stars, last pushed 9d ago), licensed MIT. It adds 78 tokens to every session and 1,170 once invoked, about $0.0004 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.

Related

Other skills, from other repositories