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/creativedswork/dscode/prototype-workflownpx skills add creativedswork/dscode --skill prototype-workflowgit clone --depth 1 https://github.com/creativedswork/dscodeWhat 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 | $0.00034 | $0.01281 |
| Opus 5 | $0.00017 | $0.00641 |
| Sonnet 5 | $0.00007 | $0.00256 |
| Haiku 4.5 | $0.00003 | $0.00128 |
Grade A, and why
prototype-workflow 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prototype 产出规范
前端 UI 变更在 explore 或 propose 阶段生成 HTML 原型时的完整流程和约束。 任何涉及可见组件、渲染、布局、CSS、交互或用户状态的变更都必须产出 HTML； 纯文字视觉说明不能替代原型，只有严格非 UI 变更才能使用 prototype stub。
触发条件
当 explore 讨论涉及以下关键词时触发： UI, 页面, 界面, 组件, 交互, 样式, 视觉, CSS, frontend, landing, dashboard, 原型, prototype, redesign, 动效
目录约定
- 产出目录:
docs/prototypes/ - 命名规范:
<change-name>-<descriptor>.html- 示例:
mcp-tool-progress-execution-view.html - 同一 change 的多个原型用不同 descriptor 区分
- 示例:
格式要求
- 自包含单文件 HTML（inline CSS + JS）
- 无需构建工具，浏览器直接打开即可预览
- 文件头部注释标注对应的 change name 和生成日期
风格对齐
- 读取
web/index.css中的--color-*CSS 自定义属性作为 design tokens - 字体: Geist Sans（正文/UI） + Geist Mono（代码/工具名）
- 遵循
warm-design-system规范（12px 圆角气泡、8px 面板、6px 按钮、1px solid分割线、无阴影、无渐变） - 色板参考:
- 背景:
--color-bg(#f8f7f5) - 表面:
--color-surface(#f3f2ef) - 边框:
--color-border(#e6e4e0) - 文字:
--color-text(#2d2a26) - 强调:
--color-accent(#ca8a04)
- 背景:
生成步骤
- 读取
docs/prototypes/README.md了解上下文 - 提取
web/index.css中的实际 CSS 变量值 - 生成自包含 HTML →
docs/prototypes/<change-name>-<descriptor>.html - HTML 文件必须包含多状态切换按钮（如 waiting / in-progress / done / error），便于视觉迭代
- 在浏览器中打开原型，验证交互、控制台、亮暗主题和关键响应式状态
- 在原型上直接接收视觉反馈并迭代，直到用户确认
- explore 阶段确认后引导用户运行
/opsx:propose；propose 阶段则继续生成 prototype manifest
生命周期
docs/prototypes/ 是 explore/propose 阶段的暂存区，不是永久归档目录。
原型在实现完成后必须逐文件判定，禁止默认永久保留。
实现完成后的判定
对当前 change 的每个 HTML 原型执行两道门：
- 长期价值门：至少满足一项
- 定义可被后续 change 复用的跨功能交互或视觉契约；
- 提供代码、测试和文字 Spec 无法等价表达的可执行状态矩阵或方案比较；
- 是后续视觉回归、设计评审或架构讨论仍需直接运行的证据。
- 有效性门：必须全部满足
- 与最终实现和当前 design tokens 一致；
- 已完成浏览器验证；
- 没有被更新版本替代；
- 能明确归属到当前 OpenSpec change。
两道门都通过时标记 archive；否则标记 delete。无法确定时默认
delete，不要以“以后可能有用”为理由积累文件。
在当前 change 的 prototype.md 中维护：
## Prototype Retention
| File | Decision | Rationale |
|---|---|---|
| `docs/prototypes/<file>.html` | `archive` 或 `delete` | 具体依据 |
delete：在实现完成、验证通过后立即删除 HTML，移除docs/prototypes/README.md索引，并更新当前 change 中的引用，禁止留下断链。archive：apply 阶段继续留在暂存区；到 OpenSpec archive 阶段移动到docs/prototypes/archive/YYYY-MM-DD-<change-name>/，更新仓库内所有引用后提交。- 实现未完成或仍在进行视觉反馈时不得提前删除。
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 · 111 lines · 34 tokens per session scan A 2a03737f89f1
prototype-workflow is a skill published in the GitHub repository creativedswork/dscode (10 stars, last pushed 18d ago), licensed MIT. It adds 34 tokens to every session and 1,281 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.
Other skills, from other repositories
dsh-doc-site-sync
Use when publishing, updating, moving, or removing DeepSeek Harness documentation website pages; editing website/docs.ts mappings or navigation; diagnosing a page missing from the VitePress site; fixing projected documentation links; or running the docs:dev, docs:check, and doc-sync workflow after website-content…
dsh-trim-cot-leakage
Use when auditing or fixing prose that reads like a leaked reasoning transcript — dead design-session citations such as (decision N), audit item codes, or §N of uncommitted drafts; change narration such as "used to", "no longer", "this cut"; stack or review vantage ("a later PR in this stack", "rejected in review")…
dsh-doc-standards
Use when writing, moving, reviewing, or auditing documentation in the deepseek-harness repo — choosing hierarchy and detail, separating tutorials from references, checking tutorial progression, trimming doc slop, responding to a verify-doc-budgets failure, or requests like "improve the docs", "audit the docs", "where…
deepseek-harness
Use when building AI agent applications with a plugin-based architecture — Web UI, CLI, Python SDK, Cordis plugin system, multi-model orchestration. DeepSeek Harness (dsh): open-source agent harness by DeepSeek AI where everything is a plugin, powered by Cordis for spatiotemporal composability.
deepseek-harness
Use this skill whenever the user wants to call DeepSeek V4-Pro / V4-Flash (or its legacy aliases deepseek-chat / deepseek-reasoner), or you see code that imports from openai import OpenAI with baseurl="https://api.deepseek.com". This skill teaches you the 10 protocol contract rules required to avoid the 16 documented…
dsh-pre-push-checks
Use before pushing, force-pushing, marking ready for review, or claiming checks pass on a deepseek-harness branch, and immediately after gh stack sync publishes rewritten branches, to select the smallest tests and checks that cover the outgoing or just-published diff without reflexively running the full repository…