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 agentmods add skills/manalkaff/opendesign/interactive-prototypenpx skills add manalkaff/opendesign --skill interactive-prototypegit clone --depth 1 https://github.com/manalkaff/opendesignWhat 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 | $0.00045 | $0.00559 |
| Opus 5 | $0.00023 | $0.00280 |
| Sonnet 5 | $0.00009 | $0.00112 |
| Haiku 4.5 | $0.00005 | $0.00056 |
Grade A, and why
interactive-prototype 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.
How it starts
The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Loaded when the user asks for a working, clickable prototype — something that behaves like a real app rather than a static mockup.
Output location
Write all output files to ./opendesign/mockups/<task-slug>/. Derive the slug from the feature name (e.g. checkout-flow, settings-panel).
Role framing
The output is a prototype that feels like a real product, not a storyboard. State transitions work. Forms validate. Buttons route to something. If an interaction is visible in the UI, it actually happens.
It is still a prototype. Cut corners on backend, real persistence, and edge cases. Fake data is fine. Real logic for the happy path is required.
Stack and structure
- React with
useStateanduseEffectfor local state and effects. Keep state colocated. No global store unless the prototype genuinely needs one. - Split the prototype into small, readable components. Files over ~400 lines get broken up.
- Inline JSX via Babel is fine for a single-file prototype. For anything multi-screen, split into per-screen component files and compose them.
- Wrap the prototype in an appropriate device or window frame — phone bezel, browser chrome, desktop window — so it reads as a product, not a web page.
Required interaction surface
- Hover states on every interactive element.
- Click and tap handlers that route to the next state. No dead controls.
- Form validation on the happy path: buttons disabled until inputs are valid, visible error states when they are not.
- Animated transitions between states and screens. Short, purposeful, not decorative.
- Multi-step flows work end to end. The user can walk the intended happy path without hitting a dead end.
- Loading and empty states where the real product would have them. Do not skip straight to populated views.
Realism rules
- Realistic fake data. No lorem ipsum. No "John Doe." Names, copy, numbers, and timestamps fit the product's world.
- Mobile frames: hit targets minimum 44px.
- Persist critical state — current screen, active tab, demo playback position — in
localStorageso a refresh during iteration does not lose the user's place.
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.
- 2d ago First seen · 45 lines · 45 tokens per session scan A cea6ea4ce568
interactive-prototype is a skill published in the GitHub repository manalkaff/opendesign (255 stars, last pushed 2mo ago), licensed MIT. It adds 45 tokens to every session and 559 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…