Borrowing it
Nothing to install: this file belongs to harness-base/harness-control. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/harness-base/harness-control/main/.agents/skills/hc-tech-design/SKILL.mdgit clone --depth 1 https://github.com/harness-base/harness-controlWrote 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/harness-base/harness-control/hc-tech-design)<a href="https://agentmods.dev/skills/harness-base/harness-control/hc-tech-design"><img src="https://agentmods.dev/badge/skills/harness-base/harness-control/hc-tech-design.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00184 | $0.03969 |
| Opus 5 | $0.00092 | $0.01985 |
| Sonnet 5 | $0.00037 | $0.00794 |
| Haiku 4.5 | $0.00018 | $0.00397 |
Grade A, and why
hc-tech-design 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 7d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
交互式产出研发方案（hc-tech-design）
本 skill 管"把需求落成可执行的技术设计（有对外接口再附接口契约）"——填 hc-prd（产需求）与 hc-dev（写代码）之间的设计空档。链条：hc-prd → hc-tech-design →（api 用例 / hc-dev）；它产出的接口契约（若有）被 api 用例消费。
形态 = 交互式设计（主 agent 当设计者），评审回改循环同各 skill 惯例（做 → 派 reviewer 挑刺 → 回改到过）；不是 hc-prd / hc-dev（ADR-0021 后）那种总监 + 并行 worker——设计是一条连贯的推演对话、不可拆并行。依据 ADR-0009（同批姊妹件；hc-dev 形态后由 ADR-0021 演进为编排式，本 skill 不变）。
① 何时用 / 何时不用
- 用：手上有需求（PRD / 原型 / 用户故事，或用户当场口述），要把它落成技术设计（有对外接口再附接口契约）；选型 / 接口怎么切 / 数据怎么存 这类方向性 / 不可逆 / 影响大 / 有明显取舍的设计决策需要拍板（低风险、有唯一合理解的细节由设计者自决，不逐个打断用户，见 ④ / ⑧）。
- 不用：产出需求走
hc-prd（那是上游）；直接写代码 / 改 bug / 重构走hc-dev（那是下游）；产测试用例走hc-test；纯控制面 / 文档 / 脚本改动。 - 一句话边界：
hc-tech-design只设计，不写实现代码、不产需求、不写测试用例。
② 输入（需求来源不限 + 必读项目现状）
- 需求来源不限：之前的 PRD（
docs/prds/<id>/）、原型图、用户故事，或用户当场用别的方式说，都能当需求来源。缺需求来源就查（仓内找）或问用户，不假设（rule-0008）。 - 必读项目资产 + 代码：设计前读
projects/<工程>/的真实代码与资产，基于现状设计、不凭空。要先知道现有的模块边界、数据模型、接口风格、技术栈，再在其上设计。 - 进某目录读 / 动文件前，按启动顺序加载向上最近的
AGENTS.md/ 先读该目录README.md（就近规则）。
③ 怎么设计（交互推演，不可拆并行）
一条连贯对话，主 agent 当设计者，逐步推演、与用户来回收敛：
- 读现状：读需求来源 +
projects/<工程>/真实代码与资产，摸清现有边界 / 数据 / 接口 / 技术栈。 - 提方案：基于现状提出设计草案——讲前因后果、不抽象：把"为什么这么设计、取舍是什么"讲清楚，不甩一堆结论让用户猜。
- 不确定就查 + 问，不静默假设（rule-0008）：信息不足 →
- 查：去事实源找（仓内代码 / 资产 / 正式文档）；
- 问：查不到就摆出来问用户，把不确定点显式列出来，绝不拿"已有信息 + 想要的结果"硬编。
- 决策点让用户拍（只升级方向性 / 不可逆 / 影响大 / 有取舍的）：选型 / 接口怎么切 / 数据怎么存这类岔路，只有当它方向性 / 不可逆 / 影响大 / 有明显取舍时才让用户拍板，不替用户定——把选项 + 各自取舍摆清楚，等用户点头；其余有唯一合理解 / 低风险的设计细节由设计者按现状自决、不逐个打断用户。无论用户拍的还是设计者自决的，决策都留痕进 design.md 第 ⑥ 段（选了什么 / 备选 / 为什么）。
- 收敛：把查 / 问 / 决策点逐个消解，直到全明确。
真相源优先级（信息冲突时裁）：① 用户当场直说 > ② 仓内现有代码 / 现状 > ③ 用户提交的外部材料（外部 / 粘贴材料先过 rule-0008 验收才算数）。
④ 产出门槛（全明确才落 + 用户审核门）
- 全明确才落可执行方案：③ 的查 / 问 / 决策点把不确定消解干净，全明确 + 用户审核通过，才落方案。
- 方案定稿必须可执行、零 TBD / 待确认：定稿里不留"待确认 / TBD / 看情况"段——还有没拍的，回 ③ 继续查 / 问，别带着窟窿落稿。
- 落稿前 producer 自检（"全明确"正面清单）：逐条过——① 有接口必有数据模型（design.md ③ 数据模型对得上 ④ 接口）；② 有写操作必有 ⑧ 业务码；③ 字段表无空格、无 TODO；④ ⑥ 每条决策有备选 + 取舍。任一不满足即未全明确，回 ③ 补。含糊措辞「合理处理 / 视情况 / 按需 / 暂定 / 待联调 / 后续优化 / TODO / 待补 / 留待实现」与残留 TBD 同级、算未消解，不许带进定稿。（此为设计者落稿前自查；判断层由 hc-tech-design-reviewer ⑤ 的正面清单复核，见 ⑥。）
- 用户审核门：方案落稿要用户点头才算定稿（同
hc-prd的确认门精神）。
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.
- 7d ago First seen · 83 lines · 184 tokens per session scan A b3107f05cbaa
hc-tech-design is a skill published in the GitHub repository harness-base/harness-control (22 stars, last pushed 1mo ago), licensed MIT. It adds 184 tokens to every session and 3,969 once invoked, about $0.0009 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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…