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 mileson/openprd --skill openprd-requirement-intakegit clone --depth 1 https://github.com/mileson/openprdWrote 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/mileson/openprd/openprd-requirement-intake)<a href="https://agentmods.dev/skills/mileson/openprd/openprd-requirement-intake"><img src="https://agentmods.dev/badge/skills/mileson/openprd/openprd-requirement-intake.svg" alt="Measured on agentmods" 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 | $0.00144 | $0.03708 |
| Opus 5 | $0.00072 | $0.01854 |
| Sonnet 5 | $0.00029 | $0.00742 |
| Haiku 4.5 | $0.00014 | $0.00371 |
Grade A, and why
openprd-requirement-intake 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 4d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenPrd Requirement Intake
作用
这份 skill 只做需求入口分流，不负责实现代码。
- 判断当前用户输入的用户可见需求类型和内部 L0/L1/L2 路由码
- 决定下一步是直接澄清、mini-plan，还是正式 PRD
- 为 L2 选择通用、面向个人消费者场景、面向企业服务场景或以 Agent 为主要使用场景的 PRD 视角；
base/consumer/b2b/agent只用于内部记录和命令 - 把用户当前需求和历史 active change 分开，避免“继续任务”吞掉新范围
- 给
$openprd-harness输出下一步行动合同
分流原则
不要按关键词判断。按影响面、未知数、决策成本和验证成本判断。
如果用户明确说“帮我梳理下”“先想清楚”“进入脑暴模式”，或需求只有一句话但明显需要先收敛业务方向、用户、商业目标、竞品和复用能力，必须先进入脑暴模式，不要直接压进 PRD，也不要先拿一版 requirement 摘要代替脑暴产物。默认使用：
openprd brainstorm . --topic <当前主题> --open- 如需让 Agent 先提炼展示文案，再补
openprd brainstorm-presentation . --template
脑暴模式是独立 lane，不等于普通 clarify：
- 目的不是只补字段，而是先判断值不值得做、给谁做、为什么现在做、有哪些方向、当前工作区能复用什么。
- 每轮至少要把这几类关键点补齐：第一批最容易触达的社区或人群、你为什么算这个社区里的自己人、现在怎么解决、当前 workaround 到底有多痛、如果先不做完整产品怎么手工交付、能否先用 spreadsheet 或 no-code 跑起来、什么真实承诺最能证明不是口头兴趣、有没有 10 个样本和更强付费信号、达到什么条件才允许产品化、先怎么低成本验证、验证阶段怎样先活下来，以及什么情况下先停。
- 资料来源默认同时包含 benchmark、knowledge、当前工作区文档/代码和开放问题。
- 如果用户能提供更大的工作区或历史项目目录，优先一起扫描可复用能力、旧流程和已有产品做法。
- 用户没有明确要求时，Agent 只能“建议进入脑暴模式”，不能静默切换。
- Agent 采用可逆默认脑暴方向并回到
capture -> classify -> synthesize -> review -> change -> tasks；用户明确选择时再覆盖默认方向。
| 用户可见需求类型 | 内部路由码 | 判断含义 | 默认处理方式 |
|---|---|---|---|
| 直接处理 | L0 | 单点、低风险、可逆、验收清楚 | 可以直接处理并事后说明 |
| 现有功能优化 | L1 | 目标明确，但影响多个文件、状态或用户可见行为 | 先给对话内 mini-plan，再执行 |
| 新功能/新流程方案 | L2 | 新产品、模块、入口、流程、权限、计费、账号、AI/第三方、云服务、数据迁移、跨系统、长期工作流，或目标/验收/影响面不清 | Agent 后台维护 PRD/review/change/tasks，同时继续用户已要求的实现 |
用户审查时优先把路由码并进“需求类型：直接处理（L0）”这类标签里，不要把内部调度码单独抬成标题。只有审查或调试真的受益时，才额外补“内部路由码：L1”这类信息，并保留上面的对照关系。
用户侧表达优先使用“面向个人消费者场景 / 面向企业服务场景 / 以 Agent 为主要使用场景”这类自然语言，不要把 consumer、b2b、agent 直接当展示词抛给用户。
审查界面意图
- 需求类型与审查界面不是一回事：L0 的音视频证据诊断也可能需要任务专属 HTML，L2 的简单概念说明也可能只需对话。
- 在入口分流时先判断下一阶段是否会出现用户需要核查、比较、选择、纠错或验收的审查边界；在证据形成、实现验证和高影响外部动作前由
$openprd-harness再判断。 - 如果已经可以预见存在人类审查节点，并命中
$openprd-harness的references/agent-authored-html-review.md中任一强制触发条件，向 Harness 传递“本轮必须由 Agent 制作并验证任务专属 HTML”的行动合同；不要因为已有 Markdown/CSV 而降级。其他多对象、多媒体、复杂测试、批量审核、方向选择或长期阅读场景继续传递“需要 Agent 自主评估审查界面”。 - OpenPrd 不生成任务专属 HTML，Agent 也不要等待用户主动索要。判断仍基于语义和证据成本，不使用 L0/L1/L2 映射或关键词命中替代任务理解；强制条件只是最低可预测边界。
What ships with it
4 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.
- 4d ago First seen · 125 lines · 144 tokens per session scan A 2d12f2bcb810
openprd-requirement-intake is a skill published in the GitHub repository mileson/openprd (50 stars, last pushed 9d ago), licensed MIT. It adds 144 tokens to every session and 3,708 once invoked, about $0.0007 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 2026-09-03.
Other skills, from other repositories
openspec-bulk-archive-change
Archive multiple completed changes at once. Use when archiving several parallel changes.
openspec-archive-change
Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.
openspec-explore
Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.
openspec-onboard
Guided onboarding for OpenSpec - walk through a complete workflow cycle with narration and real codebase work.
openspec-sync-specs
Sync delta specs from a change to main specs. Use when the user wants to update main specs with changes from a delta spec, without archiving the change.
openspec-ff-change
Fast-forward through OpenSpec artifact creation. Use when the user wants to quickly create all artifacts needed for implementation without stepping through each one individually.