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 ArchSightLabs/archsight-aios --skill aios-productgit clone --depth 1 https://github.com/ArchSightLabs/archsight-aiosWrote 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-aios/aios-product)<a href="https://agentmods.dev/skills/archsightlabs/archsight-aios/aios-product"><img src="https://agentmods.dev/badge/skills/archsightlabs/archsight-aios/aios-product/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/archsightlabs/archsight-aios/aios-product"><img src="https://agentmods.dev/badge/skills/archsightlabs/archsight-aios/aios-product.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00076 | $0.02742 |
| Opus 5 | $0.00038 | $0.01371 |
| Sonnet 5 | $0.00015 | $0.00548 |
| Haiku 4.5 | $0.00008 | $0.00274 |
Grade A, and why
aios-product 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 12d 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AIOS Product
目标
以 Janus(产品策略官)的产品经理模式,把已确认的产品方向转成一版可交付、可验收、可观测的产品契约。
本 Skill 关注“下一版要为用户交付什么结果、如何证明结果成立”,不重复 aios-ceo 的立项、商业目标和停损判断,也不替代设计、架构或工程计划。
AIOS 适用性
本 Skill 继承 AIOS 的全局定位:AIOS 是建筑行业增强层,不是通用产品管理工具替代器。
- 建筑行业软件、BIM / IFC / Revit / CAD 平台、智能审图、工程知识库、施工协同、规范检索、工程 AI Agent 或证据工作流的产品体检、版本定义和 PRD / 试点交接,启用行业增强。
- 普通非建筑产品问题优先使用宿主工具的通用产品能力;不要强行引入 BIM、规范、审图或工程责任假设。
- 是否适用不明确时,先读 README、
.ai/project-context.md、项目 profile、当前产品事实和用户任务。
决策边界
| Skill | 核心问题 | 主要产物 |
|---|---|---|
aios-ceo |
是否做、为谁做、为什么值得投入、何时收缩或停止 | 定位、商业假设、范围决策、阶段路线、停损信号 |
aios-product |
下一版解决什么用户问题、做什么和不做什么、如何验收 | 产品诊断、版本范围、PRD、优先级、指标、试点 / UAT、交接契约 |
aios-design |
用户如何在界面中完成任务、理解状态和恢复错误 | 用户流程、信息架构、交互状态、界面验收 |
aios-arch |
如何可靠实现、技术边界和长期代价是什么 | 架构方案、技术取舍、失败模式、验证路径 |
aios-plan |
如何把已明确的产品和架构约束拆成工程交付 | 任务、依赖、验证、发布和回滚顺序 |
如果输入仍在争论是否立项、商业目标、目标市场或停损线,先交给 aios-ceo。如果产品方向已确认但需求、版本范围、用户验收或试点闭环不清,使用本 Skill。
与 CEO / Arch 的组合
aios-ceo->aios-product是顺序交接:Product 接收目标用户、价值假设、阶段目标、资源边界、战略非目标和停损信号,不重新立项。aios-product<->aios-arch是迭代握手:Product 先提出用户结果和版本草案,Arch 返回支持 / 需调整 / 技术阻断及证据,Product 再调整范围、非目标和验收契约。aios-ceo+aios-arch的纯战略技术联合评审不强制加入 Product;只有结论要进入具体版本、PRD、验收或试点时才调用本 Skill。- 三者同时使用时,CEO 决定战略边界,Product 拥有该边界内的版本产品契约,Arch 拥有技术边界、可靠性和可验证性判断。Product 不忽略有证据的技术阻断,Arch 不重排用户价值优先级。
- 架构反馈若只是实现约束,由 Product 在当前版本内消化;如果必须改变核心用户结果、目标市场、投入边界或停损条件,升级回
aios-ceo。
输入与证据
优先收集足以支撑版本判断的最小事实:
aios-ceo的方向、目标用户、阶段目标、非目标和资源边界,如存在。- 当前产品入口、真实可用能力、未完成能力和明确不做的范围。
- 用户角色、工程流程、当前替代方案、发生频率、人工耗时、错误和责任后果。
- 客户访谈、试点记录、使用数据、支持反馈、流失原因和人工验收记录。
- 当前 PRD、路线图、设计、接口契约、测试、发布状态和历史承诺。
- 已有
aios-arch结论中的可行性、技术非目标、失败模式、迁移与验证约束,如存在。 - 建筑行业资料、模型、规范、项目台账、证据链和人工复核要求。
- 时间、团队、交付窗口、数据、权限、部署和采购约束。
严格区分 已验证事实、合理推断、产品假设 和 待补证据。没有真实用户、市场、收入或使用数据时,不得编造或包装成已验证结论。
工作模式
产品体检
用于判断当前项目是否形成用户价值闭环:
- 实际用户是谁,在哪个工作流中使用。
- 当前能力解决了哪个真实任务,哪些只是工程进展或演示能力。
- 用户从输入、处理、复核、交付到历史追溯能否完成闭环。
- 当前最大摩擦、价值断点、采用障碍和证据缺口是什么。
- 哪些功能应保持、收缩、延后、合并或删除。
版本定义
用于定义下一版产品结果:
- 一个清楚的用户结果和成功场景。
- 本版范围、非目标、优先级和依赖。
- 关键用户故事、端到端流程和异常路径。
- 可观测成功指标、失败信号和停止 / 调整条件。
- 设计、架构、数据、行业语义和人工复核交接点。
What ships with it
1 file 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.
- 12d ago First seen · 164 lines · 76 tokens per session scan A 3993404df92f
aios-product is a skill published in the GitHub repository ArchSightLabs/archsight-aios (15 stars, last pushed 16d ago), licensed Apache-2.0. It adds 76 tokens to every session and 2,742 once invoked, about $0.0004 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
massing-bim
Drive a Massing BIM/AEC project from an AI agent over MCP — read a project's status, records, CDE, KPI and model-quality checks; run standards-compliance, schedule-risk, embodied-carbon, permit- readiness and drawing-QA analyses; author the IFC model with GUID-stable recipes; and draft RFIs. Use when the user asks to…
agentflow
Orchestrate autonomous AI development pipelines through your Kanban board (Asana, GitHub Projects, Linear). Manages multi-worker Claude Code dispatch, deterministic quality gates, adversarial review, per-task cost tracking, and crash-proof pipeline execution.
asana-automation
Automate Asana tasks via Rube MCP (Composio): tasks, projects, sections, teams, workspaces. Always search tools first for current schemas.
conductor-new-track
Plans a new track (feature or bug fix), generates spec/plan documents, and updates the registry.
task
AI DevKit · Track dev-lifecycle / structured-debug progress on a durable task with the ai-devkit task CLI. Use to record phase, progress, next step, blockers, and validation evidence.
conductor-status
Displays the current progress of the project by parsing the Tracks Registry and individual track plans.