design-engineer:prototype

A command for generating a clickable, single-file HTML prototype from planning documents, existing designs, or an idea. A prototype is an interactive draft used to explore how a product or feature should work.

In plain words
What is it for?
Use it to prototype a new product, a feature in an existing product, or a redesign, using project documents and connected design files when available.
Why use it?
It turns available product context into something people can click through before building the final software.

Command

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 commands/volomydyr/design-engineer-plugin/prototype
Clone the repo
git clone --depth 1 https://github.com/volomydyr/design-engineer-plugin
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 625 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 $0.00025 $0.00625
Opus 5 $0.00013 $0.00313
Sonnet 5 $0.00005 $0.00125
Haiku 4.5 $0.00003 $0.00063

Measured 2d ago against content hash d149f67f7a15, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

design-engineer: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.

commands/prototype.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prototype

Plugin paths

Your conversation context contains a line DESIGN_ENGINEER_PLUGIN_ROOT: <absolute path> injected by the plugin's UserPromptSubmit hook. Whenever this command references ${DESIGN_ENGINEER_PLUGIN_ROOT}/..., substitute the absolute path from that context line. No shell commands are run from this command body.

Context

#$ARGUMENTS

Generate a single-file HTML prototype using the dev-prototyping skill.

Step 1: Read project context

  1. Read .design-engineer-plugin/config.yaml for mode (guided/autopilot)
  2. Check what design deliverables exist (design/ – problem statement, IA, user flows, etc.)
  3. Check if Figma is connected

Step 2: Plan

Present what the prototype will be based on:

Here's what I have to work with:

{List available context: design docs, Figma designs, user description, etc.}

I'll build a clickable HTML prototype that covers {scope}. Want to adjust?

If an argument was provided:

  • new → prototype for a new product from scratch
  • feature → prototype for a new feature in the existing product
  • redesign → prototype to replace an existing feature

Confirm the selection: "Starting a prototype for {type} – correct?"

In Guided mode: discuss scope and approach before building. In Autopilot: show plan briefly, then build.

Step 3: Execute

Read ${DESIGN_ENGINEER_PLUGIN_ROOT}/skills/dev-prototyping/SKILL.md and follow its full 7-step flow. Do NOT use the Skill tool — plugin skills set disable-model-invocation: true.

In Guided mode: pause after the initial prototype for review, iterate based on feedback. In Autopilot: build the prototype, present it, ask for feedback.

Note: do NOT run /simplify on prototype HTML. Prototypes are throwaway visual artifacts; code quality is irrelevant in this phase. /simplify applies only during /design-engineer:development implementation.

Step 4: Test

Use the test-writer agent to create test scripts that verify prototype behavior. Run tests to confirm they pass.

Read the full file on GitHub · 73 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. 2d ago First seen · 73 lines · 25 tokens per session scan A d149f67f7a15

Subscribe to this mod's changes

design-engineer:prototype is a command published in the GitHub repository volomydyr/design-engineer-plugin (19 stars, last pushed 1mo ago), licensed MIT. It adds 25 tokens to every session and 625 once invoked, about $0.0001 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.