hf-to-product-architecture

hf-to-product-architecture is a skill for Claude Code from hujianbest/harness-flow. It costs 127 tokens per session (1,513 once invoked), scanned A, original, MIT.

A repository-level product architecture design step that creates a short map of how a software product is organized and expected to evolve.

In plain words
What is it for?
Use it to document the product architecture before writing feature specifications, including design principles, change-sensitive areas, cross-cutting rules, and evolution checks.
Why use it?
It reduces the cost of future changes by defining important quality goals, module boundaries, development locations, key scenarios, and architectural decisions.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the harness-flow plugin — 14 skills shipped together

Good fit Use it to document the product architecture before writing feature specifications, including design principles, change-sensitive areas, cross-cutting rules, and evolution checks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hujianbest/harness-flow/hf-to-product-architecture
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.

Any agent
npx skills add hujianbest/harness-flow --skill hf-to-product-architecture
Clone the repo
git clone --depth 1 https://github.com/hujianbest/harness-flow

Made for: Claude Code.

Or install harness-flow, the plugin that ships this one along with the rest of its 14 skills.

Wrote 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.

agentmods badge for hf-to-product-architecture

README.md
[![agentmods](https://agentmods.dev/badge/skills/hujianbest/harness-flow/hf-to-product-architecture/github.svg)](https://agentmods.dev/skills/hujianbest/harness-flow/hf-to-product-architecture)
Your own site
<a href="https://agentmods.dev/skills/hujianbest/harness-flow/hf-to-product-architecture"><img src="https://agentmods.dev/badge/skills/hujianbest/harness-flow/hf-to-product-architecture/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for hf-to-product-architecture

Your own site · 80×15
<a href="https://agentmods.dev/skills/hujianbest/harness-flow/hf-to-product-architecture"><img src="https://agentmods.dev/badge/skills/hujianbest/harness-flow/hf-to-product-architecture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 127 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,513 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00127 $0.01513
Opus 5 $0.00063 $0.00757
Sonnet 5 $0.00025 $0.00303
Haiku 4.5 $0.00013 $0.00151

Measured 13d ago against content hash 14d9d3ef1183, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

hf-to-product-architecture 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 13d 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.

skills/hf-to-product-architecture/SKILL.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

hf-to-product-architecture

把「系统长什么样」钉成可继承的产品级地图,供后续特性增量架构与切片对齐。不是特性实现设计。敌人是复杂度——变更放大、认知负荷、未知的未知(Ousterhout);判据是长期演进成本。

前置

  1. 绿地:已按 product-layer-templates 落盘,且 hf-grill-with-docs 已确认 CONTEXT.md(及台账)。
  2. product/progress.md(若有),确认当前在产品架构阶段或尚未确认架构。
  3. 加载 hf-codebase-design 词汇;领域边界不清时加载 hf-domain-modeling(可升 CONTEXT-MAP.md)。
  4. 方法论细节(质量属性场景、易变性清单、适应度函数、ATAM-lite)见 references/architecture-methodology.md,按需加载。
  5. 更新 product/progress.md:当前阶段 to-product-architecture

流程

  1. 架构特征(驱动力):从 grill 结论、CONTEXT.md、台账提炼 3~5 个驱动性架构特征(可演进性、可测试性、伸缩、容错、安全……),各配一条可检验的质量属性场景(刺激→响应→度量)。拿不准记入假设台账。特征先于风格:后续每步取舍都必须能回应这些特征。
  2. 原则与风格:选定架构风格(分层 / 六边形 / 整洁等)与依赖硬规则,声明它如何服务第 1 步的特征;难逆转点写 ADR。
  3. 逻辑划分(按易变性):3~7 个模块或限界上下文;每个一句话职责 + 它封住的易变性(哪个可能变化的设计决策被藏进内部)。按业务易变性切,不按纯技术层切蛋糕;只为有证据的易变性开缝。多上下文维护 CONTEXT-MAP.md
  4. 开发视图:目录/多模块划分、源码与测试放置、命名约定。须让「新代码放哪」有唯一显然答案(对抗未知的未知)。
  5. 关键场景:2~5 条端到端路径,作为垂直切片判据;每条标注它验证哪个架构特征。建造模式建议第一片为行走骨架(feature.md- 骨架: 是)。
  6. 横切与 ADR:错误、鉴权、持久化、观测等只写约定与链接,不写字段级细节。
  7. 演进与适应度:为已识别易变性写演进路径(变化真发生时改哪里、不改哪里)与量化复核触发(吞吐、延迟、模块数、团队数等信号,触发即重开本阶段);为依赖硬规则与关键特征配适应度函数,写清校验方式与频率(CI / 评审项 / 定期)。
  8. 落盘 product/architecture.md(≤120 行),确认行先留空。
  9. 送审 hf-review(产品架构)→ product/reviews/product-architecture-review.md
  10. 用户确认后写入架构与评审的确认行;更新 product/progress.mdready

技法(按需)

  • 复杂度三问:比较候选划分——一次典型变更波及几个模块(变更放大)?理解一个模块要先懂几个其他模块(认知负荷)?新会话能否不扫全库就知道代码放哪(未知的未知)?选三问总和最小的方案。
  • 可逆性分类:双向门(易逆转)→ 快速给默认并记 product/assumptions.md;单向门(存储引擎、事件契约、对外 API 等)→ 放慢,按 ADR 三条件进 docs/adr/。最后责任时刻之前不锁死,但推迟的决策要用接缝隔离成局部。
  • ATAM-lite:特征互相冲突(一致 vs 可用、性能 vs 简单)时写明取舍与敏感点,敏感点进 ADR,正文只链接;当前最可能让架构返工的 1~3 个风险宜早验证,常是行走骨架的内容。
  • 备选设计:风格或划分存在实质分歧时,用 hf-codebase-design 的 design-it-twice 出两个对立方案,按深度/局部性/接缝位置与复杂度三问评分后定。
  • 彩色/多色建模:在 grill/本阶段澄清领域角色与状态时使用,结论写入逻辑划分与 CONTEXT,不单独成阶段。
  • 4+1:默认合并为逻辑 + 开发 + 场景三块;物理/过程视图仅在部署/并发成为硬约束时追加 ADR。

红线

  • 无 CONTEXT 确认不得宣称产品架构已确认
  • 不把特性级接口签名、字段表、票级细节写入产品架构
  • 不在本阶段实现业务代码或拆完整特性票单
  • 每条结构决策可追溯到某个架构特征或已识别易变性,禁止无驱动力的风格与划分
  • 演进 ≠ 投机:不为未确认的未来引入抽象层与接缝;演进节只写路径与触发,不预写未来设计
  • 欠定 → product/assumptions.md,不静默填补

Read the full file on GitHub · 48 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 13d ago First seen · 48 lines · 127 tokens per session scan A 14d9d3ef1183

Subscribe to this mod's changes

hf-to-product-architecture is a skill published in the GitHub repository hujianbest/harness-flow (53 stars, last pushed 12d ago), licensed MIT. It adds 127 tokens to every session and 1,513 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens