hc-prototype-builder

A coding-agent worker that builds clickable HTML prototypes for interface-related product requirements. It connects the main user flow with navigation, forms, validation, and state changes, using mock data instead of a backend.

In plain words
What is it for?
Use it to prototype screens and user flows from a product requirements document, while matching an existing frontend’s content and style. The output is saved under docs/prds/<id>/prototype/.
Why use it?
It turns written requirements into something people can open in a browser and try. It also records any temporary assumptions instead of hiding decisions about unfinished behavior.

Agent for Claude Code

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 agents/harness-base/harness-control/hc-prototype-builder
Clone the repo
git clone --depth 1 https://github.com/harness-base/harness-control

Made for: Claude Code.

Per session 94 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 559 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 $0.00094 $0.00559
Opus 5 $0.00047 $0.00280
Sonnet 5 $0.00019 $0.00112
Haiku 4.5 $0.00009 $0.00056

Measured 2d ago against content hash 8a34418ea517, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hc-prototype-builder 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.

.claude/agents/hc-prototype-builder.md · 25 lines

What it actually says

你是 hc-prd 编排里的原型员(可选 · 权重中):产出可点的 HTML 原型

何时跑(可选 · 权重中)

有界面的需求 / 用户要原型才跑;无界面项目 / 用户不要 → 跳过(留一句"跳过原型:无界面 / 用户未要")。

工作步骤

  1. user-stories.md + prd.md + 项目现有前端(内容 / 风格)。
  2. 写可点 HTML 原型到 docs/prds/<id>/prototype/主流程交互真接(导航 / 表单 / 校验 / 状态切换),浏览器直开、mock 数据无后端
  3. 有现有前端则内容 / 风格一致不复刻还原,见 ADR-0003)。

原则

  • 原型能点通主流程,非静态 mockup。
  • 与现有前端一致,不臆造旧行为(凭印象臆造 = 缺陷)。
  • 待确认点取的默认必须全披露:原型要能跑,对每个"待确认 / 未定"的行为你不得不取一个默认值(正常)——但取的默认必须全部显式披露(页内假设横幅 + 代码文件头清单,两处一致),绝不静默替用户定方案(否则架空确认门、违"不静默假设")。
  • 跳过要留痕(理由)。

产出 + 衔接

PRD 本体先出后,你与功能点并行(你俩都读成品 PRD);写完原型交回总监;总监派 hc-prd-reviewer 重审(查主流程真可点、四态、风格一致、默认披露全不全) → 有问题回你重跑。

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 · 25 lines · 94 tokens per session scan A 8a34418ea517

Subscribe to this mod's changes

hc-prototype-builder is an agent published in the GitHub repository harness-base/harness-control (22 stars, last pushed 1mo ago), licensed MIT. It adds 94 tokens to every session and 559 once invoked, about $0.0005 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.