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 devkindhq/ideogram-ai-toolkit --skill photographic-icon-set-generatorgit clone --depth 1 https://github.com/devkindhq/ideogram-ai-toolkitWrote 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/devkindhq/ideogram-ai-toolkit/photographic-icon-set-generator)<a href="https://agentmods.dev/skills/devkindhq/ideogram-ai-toolkit/photographic-icon-set-generator"><img src="https://agentmods.dev/badge/skills/devkindhq/ideogram-ai-toolkit/photographic-icon-set-generator/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/devkindhq/ideogram-ai-toolkit/photographic-icon-set-generator"><img src="https://agentmods.dev/badge/skills/devkindhq/ideogram-ai-toolkit/photographic-icon-set-generator.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 | $0.00202 | $0.03374 |
| Opus 5 | $0.00101 | $0.01687 |
| Sonnet 5 | $0.00040 | $0.00675 |
| Haiku 4.5 | $0.00020 | $0.00337 |
Grade A, and why
photographic-icon-set-generator 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 9d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Photographic Icon Set Generator
Ideogram's generate_images_bulk, remix_image, and edit_image tools let you batch-generate and correct consistent icon sets. This skill orchestrates those calls to hold a shared "style block" — a paragraph of prompt text describing the render technique, lighting, material, and visual language — repeated byte-identical across every icon prompt in the batch, ensuring the set reads as a unified design, not a scatter of unrelated renders.
The single load-bearing technical fact this skill rests on: on Ideogram's default v4 pipeline (no custom_model_uri set), the parameters style_type, negative_prompt, magic_prompt_option, and seed are all ignored. Consistency has to be carried entirely by holding the style block as a repeated, byte-identical string in the prompt text of every generate_images_bulk entry — not by any generation parameter. This means accuracy and discipline in the locked style description is everything.
This is a hybrid skill — prompt-composition discipline (like logo-prompting and character-model-sheet) plus a multi-call orchestration workflow (like collections-management). The output is both a "set style spec" JSON (so later sessions can extend the set without re-deriving the recipe) and a project markdown file tracking generations, corrections, and extensions.
Before you start
Read these three reference files in order before your first generation and before any correction or extension:
references/style-lock-recipe.md— how to draft, lock, and hold the style block identical across every prompt. Read this before step 2 (Lock the style block).references/icon-anti-slop-discipline.md— the pre-generation gate scoring table. Run your drafted prompts through this before callinggenerate_images_bulk(step 4).references/set-consistency-workflow.md— the full batch → review → correct → extend loop, including when and how to useedit_imagewith multi-reference anchoring and when thecustom-model-trainingescalation path applies.
What ships with it
13 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.
- evals/evals.json 4.3 KB
- examples/claymation-recipe-app-icons/icon-camera.png 25 KB
- examples/claymation-recipe-app-icons/icon-favorites.png 29 KB
- examples/claymation-recipe-app-icons/icon-home.png 27 KB
- examples/claymation-recipe-app-icons/icon-notifications-extension.png 25 KB
- examples/claymation-recipe-app-icons/icon-profile.png 23 KB
- examples/claymation-recipe-app-icons/icon-search.png 17 KB
- examples/claymation-recipe-app-icons/icon-settings.png 27 KB
- examples/claymation-recipe-app-icons/RESULT.md 11 KB
- examples/claymation-recipe-app-icons/set-style-spec.json 12 KB
- references/icon-anti-slop-discipline.md 6.2 KB
- references/set-consistency-workflow.md 10 KB
- references/style-lock-recipe.md 7.6 KB
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.
- 9d ago First seen · 120 lines · 202 tokens per session scan A 52159e3389e8
photographic-icon-set-generator is a skill published in the GitHub repository devkindhq/ideogram-ai-toolkit (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 202 tokens to every session and 3,374 once invoked, about $0.0010 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
visualkan
Generate visual explanations (whiteboard, infographic, presentation, diagram, mindmap, mockup) from any content, via native subscription image generation or an API backend (OpenAI, Gemini, OpenRouter, Grok).
mangou-ai-motion-comics
Manages AI motion comic production projects with YAML assets and storyboards. Use when users need to initialize Mangou projects, edit storyboard or asset YAML, generate images or videos, split grid shots, stitch final videos, or debug task backfill.
gpt-image
Use this skill whenever a user asks to generate, create, draw, render, or edit images with GPT Image 2 / gpt-image-2, text-to-image, reference-image editing, inpainting, posters, typography, Chinese text, UI mockups, diagrams, or gallery prompts. Analyze the user's prompt, search the bundled Reference Gallery/craft…
ip-as-logo
Generate extremely simple, cute, personified square character images with rounded heavy forms, two purposeful character colors, one solid background color, and a dominant lower-corner composition. Use when creating an animal, creature, robot, ghost, plant, object, or other character image, including when the agent…
get-prompt-from-image
Analyze user-provided reference images and reverse-engineer high-fidelity AI image-generation prompts. Use when the user asks to recreate, imitate, reverse-engineer, or extract prompts from photographs, illustrations, 3D renders, products, characters, landscapes, typography, logos, posters, or other visual references.…
frontend-slides
Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a talk/pitch. Helps non-designers discover their aesthetic through visual exploration rather than abstract choices.