visualize

visualize is a command for Claude Code from danielraffel/generous-corp-marketplace. It costs 16 tokens per session (2,250 once invoked), scanned B, original, MIT.

A command that creates high-resolution images from design ideas using OpenAI DALL-E 3 or Google Gemini Imagen.

In plain words
What is it for?
Use it to make interface mockups, concept illustrations, or other prototype images based on a design brief and selected idea.
Why use it?
It turns written product ideas into visual material for inspection and discussion, when an image-generation provider is configured.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool; positional $N argument.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the design-partner plugin — 1 skill, 4 commands, 1 agent shipped together

Good fit Use it to make interface mockups, concept illustrations, or other prototype images based on a design brief and selected idea.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add danielraffel/generous-corp-marketplace
Claude Code
/plugin install design-partner

Made for: Claude Code.

Or install design-partner, the plugin that ships this one along with the rest of its 1 skill, 4 commands, 1 agent.

Wrote 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.

agentmods badge for visualize

README.md
[![agentmods](https://agentmods.dev/badge/commands/danielraffel/generous-corp-marketplace/visualize/github.svg)](https://agentmods.dev/commands/danielraffel/generous-corp-marketplace/visualize)
Your own site
<a href="https://agentmods.dev/commands/danielraffel/generous-corp-marketplace/visualize"><img src="https://agentmods.dev/badge/commands/danielraffel/generous-corp-marketplace/visualize/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.

agentmods 80×15 button for visualize

Your own site · 80×15
<a href="https://agentmods.dev/commands/danielraffel/generous-corp-marketplace/visualize"><img src="https://agentmods.dev/badge/commands/danielraffel/generous-corp-marketplace/visualize.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,250 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00016 $0.02250
Opus 5.5 $0.00006 $0.00900
Sonnet 5.5 $0.00003 $0.00450
Haiku 4.5 $0.00002 $0.00225

Measured 2mo ago against content hash e3e03a026f10, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

visualize scanned grade B with 2 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 2mo 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.

Asks the agent to reveal its instructionsmediumSystem prompt leakage

Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.

### 5. Show Prompt and Offer Copy Option

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -o "${images_dir}/${filename}" "${imageUrl}"
plugins/design-partner/commands/visualize.md · 349 lines

How it starts

The opening of the file, as written. The whole thing — 349 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design Partner Visualize Command

For Claude: Generate actual images using DALL-E 3 or Gemini Imagen based on design ideas.

Process

1. Check API Key Availability

# Run detection script
node ${CLAUDE_PLUGIN_ROOT}/scripts/detect-api-keys.js

If no keys found, inform user:

No image generation providers configured.

To generate images, you'll need an API key from:
- OpenAI DALL-E 3: https://platform.openai.com/api-keys (~$0.04/image)
- Google Gemini: https://aistudio.google.com/app/apikey (~FREE/image)

Run /dp:providers setup to configure.

2. Load Context

  • Read .claude/dp.local.md to get:
    • Current idea (if idea-id provided, load that specific idea)
    • Design Brief (users, job, constraints)
    • Current budget and spend

3. Use AskUserQuestion (2 questions)

{
  "questions": [
    {
      "question": "What type of image should I generate?",
      "header": "Image Type",
      "multiSelect": false,
      "options": [
        {
          "label": "UI Mockup",
          "description": "Realistic product screenshot or interface"
        },
        {
          "label": "Concept Illustration",
          "description": "Artistic representation of the idea"
        },
        {
          "label": "User Scenario",
          "description": "Person using the product in context"
        },
        {
          "label": "Marketing Visual",
          "description": "Hero image for landing page or presentation"
        }
      ]
    },
    {
      "question": "Which provider should I use?",
      "header": "Provider",
      "multiSelect": false,
      "options": [
        {
          "label": "DALL-E 3 (OpenAI) - $0.04",
          "description": "Best quality, photorealistic (Recommended)"
        },
        {
          "label": "Gemini 3 Pro - Free (preview)",
          "description": "Good quality, budget-friendly"
        },
        {
          "label": "Use my default",
          "description": "Auto-select based on your settings"
        }
      ]
    }
  ]
}

Read the full file on GitHub · 349 lines

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. 2mo ago First seen · 349 lines · 16 tokens per session scan B e3e03a026f10

Subscribe to this mod's changes

visualize is a command published in the GitHub repository danielraffel/generous-corp-marketplace (12 stars, last pushed 2mo ago), licensed MIT. It adds 16 tokens to every session and 2,250 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 2 findings (asks the agent to reveal its instructions, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

visualize compared with commands from other repositories

visualize next to 6 commands from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
visualizedanielraffel/generous-corp-marketplaceCommand122mo agoMITB16Claude Code
checklistgithub/spec-kitCommand149ktodayMITA13Claude Code
clarifygithub/spec-kitCommand149ktodayMITA27Claude Code
specifygithub/spec-kitCommand149ktodayMITA13Claude Code
convergegithub/spec-kitCommand149ktodayMITA35Claude Code
implementgithub/spec-kitCommand149ktodayMITA14Claude Code
speckit.bug.fixgithub/spec-kitCommand149ktodayMITA12Claude Code