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 agentmods add skills/archsightlabs/archsight-cognition/prdnpx skills add ArchSightLabs/archsight-cognition --skill prdgit clone --depth 1 https://github.com/ArchSightLabs/archsight-cognitionWrote 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/archsightlabs/archsight-cognition/prd)<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>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 | $0.00043 | $0.01138 |
| Opus 5 | $0.00022 | $0.00569 |
| Sonnet 5 | $0.00009 | $0.00228 |
| Haiku 4.5 | $0.00004 | $0.00114 |
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.
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
- 用一句话重述产品要服务的用户、场景和未满足任务。
- 区分事实、假设、愿望和噪声,不把市场热词当成证据。
- 逆向列出产品最可能失败的 3 条路径。
- 选出信息量最大的 MVP 范围,而不是最容易开发的功能。
- 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。
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.
- 5d ago First seen · 108 lines · 43 tokens per session scan A ea4f0b825489
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.
Other skills, from other repositories
thinking-model-router
When unsure which thinking skill fits, map domain and problem type, then return NONE or one primary skill by default (at most three complementary).
thinking-systems
When behavior is emergent across components—fixes elsewhere break, loops/delays dominate—map boundary, stocks/flows, feedback, archetypes, then rank leverage.
thinking-five-whys-plus
When a fault is localized and the proximate cause is known but the systemic root is not, chain evidence-linked whys with a counterfactual stop and a countermeasure.
thinking-jobs-to-be-done
Deciding what to build or why adoption fails. Recover the progress users hire a solution for under a circumstance, then rank by outcome and competing workarounds.
thinking-map-territory
When a claim, doc, test, metric, or assumption conflicts with observed behavior, stop theorizing from the map and verify the live code or data; let territory overrule.
thinking-margin-of-safety
When provisioning, setting a limit, or committing an estimate under uncertainty, size a buffer to residual error and the cost of breach—not to the optimistic edge.