ideate

ideate is a skill for Claude Code, Codex from agentlas-ai/agentlas-desktop. It costs 34 tokens per session (677 once invoked), scanned A, original, Apache-2.0.

A design-exploration workflow that creates three different visual concepts for a product screen, refines the chosen concept, and saves it as the visual reference for implementation.

In plain words
What is it for?
Use it to explore a mobile app, dashboard, SaaS product, or landing page, compare three layouts, and pin the selected design for developers to follow.
Why use it?
It lets a team agree on the layout and interaction direction before code is written, reducing changes caused by unclear design decisions.

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/agentlas-ai/agentlas-desktop/ideate
Any agent
npx skills add agentlas-ai/agentlas-desktop --skill ideate
Clone the repo
git clone --depth 1 https://github.com/agentlas-ai/agentlas-desktop

Made for: Claude Code, Codex.

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 ideate

README.md
[![agentmods](https://agentmods.dev/badge/skills/agentlas-ai/agentlas-desktop/ideate.svg)](https://agentmods.dev/skills/agentlas-ai/agentlas-desktop/ideate)
Your own site
<a href="https://agentmods.dev/skills/agentlas-ai/agentlas-desktop/ideate"><img src="https://agentmods.dev/badge/skills/agentlas-ai/agentlas-desktop/ideate.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 677 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 $0.00034 $0.00677
Opus 5 $0.00017 $0.00338
Sonnet 5 $0.00007 $0.00135
Haiku 4.5 $0.00003 $0.00068

Measured today against content hash 6a0667456e33, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ideate 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 today.

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.

plugins/design/skills/ideate/SKILL.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Purpose

Explores product concepts by generating 3 distinct, production-quality visual design options, refines them based on user feedback, and persists the selected option as the pinned visual target (target-design.png) for faithful code implementation.

Preconditions

  • The minimum design brief (target product/screen and intended user outcome) must be resolved via $get-context.
  • No code scaffolding or file modifications are permitted prior to visual concept selection.
  • Strictly adhere to $critical-overrides.

Steps

  1. Analyze Brief & Context: Review the resolved design brief, existing design tokens, brand palettes, and any reference screenshots.
  2. Determine Target Dimensions:
    • Mobile app: 390 x 844
    • Tablet app: 834 x 1194
    • Desktop app / Dashboard / SaaS: 1440 x 1024
    • Landing / Marketing page: 1440 wide scrollable
  3. Generate 3 Distinct Visual Directions:
    • Construct 3 separate prompt concepts with distinct information hierarchy, layout strategies, and interaction models.
    • Run generation for each concept independently using the built-in image generation tool (do not combine multiple ideas into one image).
    • For mobile apps, generate content-only views without device bezels, notches, status bars, or home indicators.
  4. Order and Present Selection:
    • Number the results strictly in the order they appear in the chat context: Option 1, Option 2, Option 3.
    • Send the concise selection prompt: "Which option should I build: 1, 2, or 3? Or tell me what you'd like to refine or personalize first."
  5. Incorporate Feedback Loop: If the user requests refinements or remixes between options, generate updated visual concepts before proceeding.
  6. Pin Target Design:
    • Once the user confirms Option N, save that image file to assets/target-design.png as the persistent single source of truth.
    • Acknowledge the selection (e.g., "Option 2 confirmed and pinned as target design! Building the interactive prototype now...").
  7. Handoff to Build: Immediately transition to $image-to-code with assets/target-design.png bound as the active visual anchor.

Read the full file on GitHub · 48 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. today Changed · +4 lines 6a0667456e33
  2. 4d ago First seen · 44 lines · 34 tokens per session scan A 0aa8663d13e6

Subscribe to this mod's changes

ideate is a skill published in the GitHub repository agentlas-ai/agentlas-desktop (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 34 tokens to every session and 677 once invoked, about $0.0002 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

shadcn

Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for…

ensemblr-hq/ensemblr · 90 tokens

accessibility

Primary accessibility skill for VS Code. REQUIRED for new feature and contribution work, and also applies to updates of existing UI. Covers accessibility help dialogs, accessible views, verbosity settings, signals, ARIA announcements, keyboard navigation, and ARIA labels/roles.

microsoft/vscode · 54 tokens

frame-macos-notification

拟真 macOS 通知 banner + app icon + 标题正文, 适合 video overlay / 产品发布预告.

nexu-io/html-anything · 31 tokens

visualize

Render a polished visual inline in the chat as part of your answer — a diagram, a chart, an interactive explainer, or a UI mockup. Load it proactively whenever an explanation would land better as a picture than as prose. Do not wait to be asked.

vellum-ai/vellum-assistant · 57 tokens

gui-settings-ui

GUI desktop app only. How to build a Settings page in the Warp client (app/src/settingsview) so its widgets and settings search behave correctly — picking a PageType, deciding whether a heading belongs in the page-title slot or inside a widget, gating a widget, and scoping searchterms per widget. Use when adding or…

warpdotdev/warp · 86 tokens

figma-code-connect-components

Connects Figma design components to code components using Code Connect mapping tools. Use when user says "code connect", "connect this component to code", "map this component", "link component to code", "create code connect mapping", or wants to establish mappings between Figma designs and code implementations. For…

warpdotdev/warp · 81 tokens