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-prd/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-prd)<a href="https://agentmods.dev/skills/harness-base/harness-control/hc-prd"><img src="https://agentmods.dev/badge/skills/harness-base/harness-control/hc-prd.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 | $0.00160 | $0.02389 |
| Opus 5 | $0.00080 | $0.01195 |
| Sonnet 5 | $0.00032 | $0.00478 |
| Haiku 4.5 | $0.00016 | $0.00239 |
Grade A, and why
hc-prd 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 6d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
编排式产出需求（用户故事 → PRD → 原型）
本 skill 管"产出需求"（hc-dev 的上游）。重构为编排式：产品总监（编排逻辑，主 agent 当）按本总谱调度一队专职 worker，每个 worker 各配模型 / 提示词。依据 ADR-0010。常驻自主"产品总监 agent"押后。
何时用 / 何时不用
- 用：从模糊想法或现有系统理出需求；要用户故事 / PRD / 原型。
- 不用：需求已清晰、只是写代码（走
hc-dev）；纯 bug / 控制面改动。
贯穿全程的约束（不是某一步）
- 不静默假设：信息不足，去查事实源（仓内代码 / 资产 / 文档）或摆出来问用户确认，绝不拿"已有信息 + 想要的结果"硬编（rule-0008）。
- 两套优先级（信息冲突时裁）：真相源 ① 用户当场直说 > ② 仓内现有代码 / 现状 > ③ 用户提交的信息源；需求源 ① 用户直说 > ② 提交源 > ③ 现状。
优先级与权重模型
三层（高 → 低）：用户明确指令（覆盖一切默认，含必选；AGENTS.md"用户指令 > 本文件"）> 必选（默认 always）> 可选·权重（按权重 + 触发判据）。
- 覆盖必选：先提示后果 → 用户坚持就照办 → 留痕（标"用户强制跳过 X，已告知后果"；审稿 / eval 不当缺陷扣分）。
- 跳过可选步：留一句为什么（审稿 / eval 抽查理由）。
worker（产品总监调度）
| worker | 干啥 | 标 | 触发 / 形态 |
|---|---|---|---|
| 需求采集员 | 多轮引导对话收需求（JTBD / 页面 / 数据 / 四态 / 边界 / 验收 / 非目标） | 必选 | 交互 · 人在环 |
| 外部调研员 | 查外部 SOP / 事实（过 rule-0008 验收再喂入） | 可选 · 权重低 | 用户要查 / 有市场 SOP 且摸不透；走 deep-research skill（可用的 research skill，由通用 subagent 调 Skill 工具跑，不另建专属 subagent） |
| 用户故事+AC 员 | 写 docs/prds/<id>/user-stories.md（US-NN + 可观测 AC） |
必选 | 轻审 → 确认门 |
| PRD 本体员 | 写 prd.md（合已确认故事，套 templates/prd.md）；正文按功能描述、不造 FP 号 |
必选 | 先出（功能点 / 原型依赖它） |
| 功能点清单员 | FP 编号唯一权威：读成品 prd.md 抽功能点编号 + 建 US↔FP↔正文 三级双向映射 |
必选 | 并行（与原型） |
| 原型员 | 可点 HTML 原型 docs/prds/<id>/prototype/（mock 无后端，与现有前端一致，不复刻）；待确认点取的默认全披露 |
可选 · 权重中 | 并行（与功能点）/ 有界面 |
| PRD 审稿员 | 对抗挑刺整套，rubric = eval 013 / rule-0010 | 必选 | review loop |
时序（总监按此编排；模板见 references/orchestration-workflow.js）
- 需求采集（人在环）→（可选·权重低）外部调研 → rule-0008 验收 → 喂入。
- 用户故事+AC → 轻审 loop（1-2 轮：AC 可观测可验证 / 故事完整无遗漏 / 内部一致 / 对齐采集需求） → 修 → 确认门（用户 approved）才往下。
- PRD 本体先出（FP 单一权威：本体员正文不造 FP 号）→ 并行 [ 功能点（读成品 PRD 抽号 + 锚映射）∥（可选·权重中）原型（待确认默认全披露）]。功能点 / 原型都依赖 PRD 正文，故不三者齐并行。
- PRD 审稿员重审 loop（框住并行产出）：审整套 → 挑出有问题的 worker 回原 worker 角色重跑（每轮只重跑被审出问题的 worker）→ 复审 → 到零；独立性靠审稿员每轮复审；"方向整个错"才回更上游（重采集 / 重写）。
- 收尾确认（用户）。
- 软提醒（不强制、可跳过）：PRD 齐了，提醒用户「要不要进
hc-test生成测试用例？」——只提醒，用户可不做（测试链与需求松耦合，见hc-test/docs/harness/testing-flow.md、ADR-0014）。
What ships with it
2 files 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.
- 6d ago First seen · 69 lines · 160 tokens per session scan A 848d0902eb8c
hc-prd is a skill published in the GitHub repository harness-base/harness-control (22 stars, last pushed 1mo ago), licensed MIT. It adds 160 tokens to every session and 2,389 once invoked, about $0.0008 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
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
monorepo-management
Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.