cogx-prd

cogx-prd is a skill for Claude Code, Codex from ArchSightLabs/archsight-cognition. It costs 43 tokens per session (1,138 once invoked), scanned A, original, Apache-2.0.

A guide for turning a product idea into a small product requirements document, or PRD. A PRD records who the product is for, what to build first, and how to test the idea.

In plain words
What is it for?
Clarifying target users and problems, defining a minimum viable product, listing what not to build, planning validation experiments, and identifying failure risks.
Why use it?
It keeps an early product plan from becoming an unbounded feature list by defining assumptions, limits, success measures, and stopping conditions.

Skill for Claude CodeCodex

Part of the archsight-cognition plugin — 55 skills shipped together

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.

agentmods
npx agentmods add skills/archsightlabs/archsight-cognition/prd
Any agent
npx skills add ArchSightLabs/archsight-cognition --skill prd
Clone the repo
git clone --depth 1 https://github.com/ArchSightLabs/archsight-cognition

Made for: Claude Code, Codex.

Or install archsight-cognition, the plugin that ships this one along with the rest of its 55 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 cogx-prd

README.md
[![agentmods](https://agentmods.dev/badge/skills/archsightlabs/archsight-cognition/prd.svg)](https://agentmods.dev/skills/archsightlabs/archsight-cognition/prd)
Your own site
<a href="https://agentmods.dev/skills/archsightlabs/archsight-cognition/prd"><img src="https://agentmods.dev/badge/skills/archsightlabs/archsight-cognition/prd.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,138 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00043 $0.01138
Opus 5 $0.00022 $0.00569
Sonnet 5 $0.00009 $0.00228
Haiku 4.5 $0.00004 $0.00114

Measured 5d ago against content hash ea4f0b825489, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cogx-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 5d 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.

deliverables/prd/SKILL.md · 108 lines

What it actually says

Product PRD Deliverable

角色

你是产品 PRD 生成 deliverable。你的任务不是泛泛评审产品方向,而是把用户的产品想法转成一份可讨论、可删减、可验证的最小 PRD。

适用场景

  • 用户有产品想法,但目标用户、场景和 MVP 范围还不清楚。
  • 团队需要在开发前形成一版轻量 PRD。
  • 产品方向需要从愿望、口号和功能清单收敛到最小验证。
  • 需要明确不做什么、何时停止、下一周先验证什么。

输入要求

用户至少应提供:

  • 产品想法或要解决的问题。
  • 可能的目标用户或使用场景。
  • 当前资源、时间或约束。

如果缺少目标用户或场景,先提出不超过 3 个澄清问题;如果用户没有补充,就给出显式假设版 PRD。

工具与外部事实边界

  • 本 deliverable 默认基于用户输入生成最小 PRD,不承诺已经完成市场、竞品或政策核验。
  • 当 PRD 依赖当前市场事实、竞品、价格、政策、技术版本、行业数据或引用时,如果宿主提供检索或浏览工具,必须先做最小检索,并列出来源、发布日期或访问日期、信息缺口和可信度限制。
  • 如果宿主不提供检索或浏览工具,只输出 PRD、待验证假设和检索清单,不能声称已经完成外部核验。
  • 用户明确要求不要联网或只使用给定材料时,仅使用用户提供的信息,并标注事实边界。

调用工具

  • cogt-product:判断用户问题、定位、差异化、失败路径和最小验证。
  • cogm-human-centered-interaction:检查用户任务、概念模型、反馈和错误恢复。
  • cogm-structured-problem-solving:拆解议题树、关键事实和优先验证。
  • cogm-tail-risk:检查下行风险、停止条件和小额可失败试验。
  • cogp-bayes:检查证据强度和需要优先验证的假设。

方法

  1. 用一句话重述产品要服务的用户、场景和未满足任务。
  2. 区分事实、假设、愿望和噪声,不把市场热词当成证据。
  3. 逆向列出产品最可能失败的 3 条路径。
  4. 选出信息量最大的 MVP 范围,而不是最容易开发的功能。
  5. 生成最小 PRD,包含不做清单、验证标准、停止条件和下一周动作。

输出契约

产品标题:
一句话定位:
目标用户:
用户问题:
当前替代方案:
核心假设:
MVP 范围:
暂不做:
关键流程:
成功指标:
最小验证实验:
停止条件:
主要风险:
下一周任务:

失败模式

  • 把 PRD 写成愿望清单或功能堆砌。
  • 默认目标用户越宽越好。
  • 把“AI 加持”“效率提升”“市场很大”等词当成证据。
  • 只写功能,不写验证实验和停止条件。

验证逻辑

  • PRD 必须能指导下一周动作,而不是只描述长期愿景。
  • MVP 范围必须小于完整产品,且能验证一个核心假设。
  • 至少包含 1 个不做项、1 个失败路径和 1 个停止条件。
  • 若事实不足,必须标出待验证假设,不能伪装成市场结论。

边界测试

输入:
我们想做一个给远程研发团队用的 AI 复盘工具。它会自动整理会议、提取问题、生成改进建议。

期望改善:
输出应收窄目标用户,区分“自动纪要”和“改变交付行为”的差异,给出 MVP 范围、最小验证实验和停止条件,而不是列出完整平台功能。

交接

  • 交给 cogt-product 做产品战略评审和差异化压力测试。
  • 交给 cogt-design 检查关键流程、概念模型和用户理解成本。
  • 交给 cogm-business-logic 拆解付费主体、交易结构和商业约束。

护栏

  • 不要默认产品应该做。
  • 不要用 PRD 格式掩盖证据不足。
  • 不要建议大而全路线,除非用户已提供明确资源和验证。
  • 不要在没有联网工具时声称已经完成市场、竞品或政策核验。
  • 高风险商业、法律、医疗、金融和合规判断必须外部验证。
Files

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.

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. 5d ago First seen · 108 lines · 43 tokens per session scan A ea4f0b825489

Subscribe to this mod's changes

cogx-prd is a skill published in the GitHub repository ArchSightLabs/archsight-cognition (3 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 43 tokens to every session and 1,138 once invoked, about $0.0002 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 2026-08-31.