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/dkeken/codex-skills-alternative/design-prototypenpx skills add DKeken/codex-skills-alternative --skill design-prototypegit clone --depth 1 https://github.com/DKeken/codex-skills-alternativeWrote 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/dkeken/codex-skills-alternative/design-prototype)<a href="https://agentmods.dev/skills/dkeken/codex-skills-alternative/design-prototype"><img src="https://agentmods.dev/badge/skills/dkeken/codex-skills-alternative/design-prototype.svg" alt="Measured on agentmods" 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 | $0.00087 | $0.00889 |
| Opus 5 | $0.00044 | $0.00445 |
| Sonnet 5 | $0.00017 | $0.00178 |
| Haiku 4.5 | $0.00009 | $0.00089 |
Grade A, and why
design-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 6d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design — Prototype
Turn static screens into a working clickable flow that demonstrates the experience end to end. A prototype's job is to let someone experience the flow and give feedback — not to be production-hardened. Stubs are fine and expected; broken navigation is not.
When to use
- You have screens/components (from image-to-code, url-to-code, or ideate) and need them connected.
- "Make it clickable", "wire the flow", "let me click through it".
- Validating a UX flow with stakeholders before real backend work.
When NOT to use
- No screens exist yet → build them first (
design-image-to-code/design-url-to-code). - You need production code with real data/auth — that's an engineering task, not a prototype.
- Just checking a built prototype against the design →
design-qa.
Inputs
- The screens/components to connect.
- The flow to demonstrate: happy path + key states.
./design/context.mdfor the JTBD (the flow should make that easy).
Workflow
- Map the flow graph: screens are nodes, actions are edges (click → navigate, submit → state change). Write it down before wiring.
- Wire routing/navigation between screens.
- Add interaction states: hover, active, disabled, loading, empty, error, success. Cover at least the happy path + one error state (the most-skipped, most-important state).
- Stub data so it's clickable without a backend; clearly mark where real data plugs in.
- Verify: drive the whole happy path in a browser-automation tool — click every step, confirm nothing dead-ends. Fix what breaks.
- Keep it runnable with one command.
Worked example
Flow (JTBD: create first project in <2 min): Welcome → Choose template → Name it → Dashboard.
flow graph:
Welcome --[Get started]--> Template --[select]--> Name --[Create]--> Dashboard
Name --[empty submit]--> Name(error: "Name required")
Template --[back]--> Welcome
states wired: hover on cards, loading on Create (300ms stub), error on empty name,
success → Dashboard with the new project card
stubs: templates = 3 fixtures; "Create" writes to in-memory store (TODO: real API)
verify (browser): clicked Welcome→Template→Name→Create→Dashboard ✓;
empty-name error shows ✓; back nav works ✓; no dead ends
run: `npm install && npm run dev` → :5173
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.
- 6d ago First seen · 67 lines · 87 tokens per session scan A d847cfa2fd47
design-prototype is a skill published in the GitHub repository DKeken/codex-skills-alternative (15 stars, last pushed 3mo ago), licensed MIT. It adds 87 tokens to every session and 889 once invoked, about $0.0004 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
data-charts-tako
Search and visualize the world's data - get charts, insights, and embeddable knowledge cards for finance, economics, demographics, sports, and more.
apollo-lead-finder
Two-phase Apollo.io prospecting: free People Search to discover ICP-matching leads, then selective enrichment to reveal emails/phones (credits per contact). Creates Apollo lists. Deduplicates against existing contacts by LinkedIn URL.
monorepo-management
Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.
browse-and-evaluate
Use when exploring the ai-agent-skills catalog to find, compare, and evaluate skills before installing. Always use --fields to limit output size and --dry-run before committing to an install.
render-3d-product-showcase
Assemble a premium 3D product-showcase ad from a config — four beat clips (an orbiting hero rotation, a macro push-in, a physics reveal, a typographic close) normalized to the brand-color canvas, hard-concatenated in order, closed on a deterministic Playwright brand end card, and mixed under one instrumental bed at…
render-airdrop-carousel
Assemble a viral iOS "AirDrop" notification-carousel video ad (≈6–8s, 9:16) from a brand line plus 6–16 real product photos — a native AirDrop share-sheet card ("Brand would like to share a · Decline / Accept") springs up and its preview window CYCLES through the products, landing on a range/lineup payoff with an…