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 skills add hujianbest/harness-flow --skill hf-to-product-architecturegit clone --depth 1 https://github.com/hujianbest/harness-flowWrote 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/hujianbest/harness-flow/hf-to-product-architecture)<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.
<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>- NVIDIA SkillSpector pass
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 | $0.00127 | $0.01513 |
| Opus 5 | $0.00063 | $0.00757 |
| Sonnet 5 | $0.00025 | $0.00303 |
| Haiku 4.5 | $0.00013 | $0.00151 |
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.
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
- 绿地:已按
product-layer-templates落盘,且hf-grill-with-docs已确认CONTEXT.md(及台账)。 - 读
product/progress.md(若有),确认当前在产品架构阶段或尚未确认架构。 - 加载
hf-codebase-design词汇;领域边界不清时加载hf-domain-modeling(可升CONTEXT-MAP.md)。 - 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。 - 更新
product/progress.md:当前阶段to-product-architecture。
流程
- 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。 - 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。
- 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。 - 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)。
- 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标- 骨架: 是)。 - 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。
- 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)。
- 落盘
product/architecture.md(≤120 行),确认行先留空。 - 送审
hf-review(产品架构)→product/reviews/product-architecture-review.md。 - 用户确认后写入架构与评审的确认行;更新
product/progress.md→ready。
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
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.
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.
- 13d ago First seen · 48 lines · 127 tokens per session scan A 14d9d3ef1183
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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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.
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…
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…