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 concept-grid-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/concept-grid-generator)<a href="https://agentmods.dev/skills/devkindhq/ideogram-ai-toolkit/concept-grid-generator"><img src="https://agentmods.dev/badge/skills/devkindhq/ideogram-ai-toolkit/concept-grid-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/concept-grid-generator"><img src="https://agentmods.dev/badge/skills/devkindhq/ideogram-ai-toolkit/concept-grid-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 | $0.00255 | $0.02146 |
| Opus 5.5 | $0.00102 | $0.00858 |
| Sonnet 5.5 | $0.00051 | $0.00429 |
| Haiku 4.5 | $0.00026 | $0.00215 |
Grade A, and why
concept-grid-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 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Concept Grid Generator
A concept grid is a single generated image that puts several genuinely distinct
motif/icon concepts side by side as labeled tiles, with the palette and the rendering
technique held identical across every tile. It exists to make choosing between
candidate ideas cheap: one generation, one review pass, instead of running a full
brand-identity-sheet or character-model-sheet for every candidate and comparing
finished boards after the fact.
Why this exists — cheap N-distinct-concepts comparison vs. N expensive full boards
A full identity sheet or character sheet is a composition-heavy, multi-panel,
QUALITY-rendered generation — it's the right tool once a direction is picked, but
it's the wrong tool for picking between directions. Running three full boards to
compare three candidate motifs triples the cost and the review burden for a decision
that doesn't need six-panel context, it needs to see the marks next to each other.
A concept grid answers "which of these ideas is worth developing" in one generation
by holding everything except the concept itself constant, so the only variable a
reviewer has to judge is the idea.
This is different from varying a locked idea (bulk-image-generation-workflow, which
holds style_description byte-for-byte identical and varies pose/prop/angle within
one concept) and different from exploring a whole brand loosely (moodboard-generator,
which explores nine categories — palette, type, imagery, mood — with the palette
itself still open). Here, the palette and the rendering technique are the two things
locked before drafting a single tile, and what varies is the concept — the actual
form/idea each tile represents.
The two-stage handoff — Set A (this skill) → Set B (lock-in)
Treat this skill as Set A and brand-identity-sheet / character-model-sheet as
Set B. Never skip straight to a full board for every candidate concept — that's the
expensive path this skill exists to avoid. And never treat the grid image itself as a
finished deliverable — a tile in a comparison sheet is a rough, small, same-technique
sketch next to five others; it hasn't been rendered at the scale, polish, or
system-context a shipped identity sheet or character sheet needs.
What ships with it
3 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 · 146 lines · 255 tokens per session scan A 21f120e6bff7
concept-grid-generator is a skill published in the GitHub repository devkindhq/ideogram-ai-toolkit (2 stars, last pushed 6d ago), licensed Apache-2.0. It adds 255 tokens to every session and 2,146 once invoked, about $0.0010 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
appllama-usage
Use the Appllama MCP (mcp.appllama.io) well — research real top-grossing mobile apps, their screens, flows, and UI elements, then build from what you learn. Load when the Appllama MCP is connected and the task involves building a mobile app or screen, researching app design patterns, studying…
appllama-app-design-skill
Build native-feeling, benchmark-quality mobile app screens (Expo / React Native). Use when designing or implementing any mobile UI — screens, flows, onboarding, paywalls, tab bars, sheets, settings, empty states — or when polishing motion, navigation, typography, dark mode, or perceived performance. Enforces Apple HIG…
excalidraw
Use when user requests diagrams, flowcharts, architecture charts, or visualizations. Also use proactively when explaining systems with 3+ components, complex data flows, or relationships that benefit from visual representation. Generates .excalidraw files and exports to PNG/SVG via Kroki API or locally using…
build-for-good-ux
Audit, build, or refactor frontend UI components, pages, forms, and interactive flows to implement complete UX states (loading, success, error, empty), resilient async degradation, accessible button interactions, error recovery, Fitts's Law mobile touch targets, and choice simplification. Use when creating or…
html-slides
A workflow for creating a presentation as one self-contained HTML file sized for a 1920×1080 screen. It supports several visual styles and can export to PPTX when requested.
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).