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-runtimegit 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-runtime)<a href="https://agentmods.dev/skills/archsightlabs/archsight-aios/aios-runtime"><img src="https://agentmods.dev/badge/skills/archsightlabs/archsight-aios/aios-runtime.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 | $0.00064 | $0.00987 |
| Opus 5 | $0.00032 | $0.00494 |
| Sonnet 5 | $0.00013 | $0.00197 |
| Haiku 4.5 | $0.00006 | $0.00099 |
Grade A, and why
aios-runtime 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 8d 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
AIOS Runtime
目标
以 Daedalus(AI 研发工程师)的方式设计 AI Runtime、Prompt、Context、Memory、Tool Calling、MCP、RAG / GraphRAG 和多 Agent 编排。该 Skill 是高级设计入口,不负责直接改业务代码。
在 AIOS 行业增强启用时,Runtime 设计必须把规范版本、来源证据、图纸 / 构件定位、人工复核、索引版本、租户 / 项目隔离、缓存污染和多实例恢复纳入默认约束。
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 Runtime 设计替代器。
- 建筑行业项目中的 Prompt、Context、Memory、Tool、MCP、RAG、GraphRAG、多 Agent 编排、规范知识库或工程知识管线,启用 AIOS 行业增强。
- 普通非建筑 Runtime / RAG 任务优先使用宿主工具的通用能力;不要强行引入图纸、构件、规范、审图、人工复核或工程证据链假设。
- 是否适用不明确时,先读 README、
.ai/project-context.md、项目 profile、数据源和运行时目标。
输入
优先收集:
- Agent 角色资产、system prompt 或 workflow。
- 目标运行时约束,例如本地 Agent、Hermes、OpenClaw、飞书机器人或其他协作入口。
- 工具清单、权限、输入输出 schema。
- Capability 注册表、工具权限、输入输出 schema、证据契约和仲裁阻断规则。
- RAG / GraphRAG 数据源、索引、评估需求。
- 已编译的 Knowledge Pack、
knowledge.norm_lookup输入输出契约、eval gate 和 Reference Runtime 运行证据。 - 当前上下文、记忆、检索或工具调用失败案例。
工作流
- 明确 Runtime 边界:Source、Runtime、Instance 分别是什么。
- 压缩上下文:只保留任务必要信息,避免完整仓库或完整角色文件夹直接进入运行时。
- 设计 Prompt:角色、职责、边界、输入、输出、风格、升级路径。
- 设计 Memory:写入条件、读取策略、过期和清理机制。
- 设计 Tool Calling / Capability:权限最小化、schema、证据契约、审计、人工确认点。
- 设计 RAG / GraphRAG:优先把 Knowledge Pack 作为行业知识资产输入,明确 chunk、实体、关系、索引、检索、引用、评估。
- 设计本地 Reference Runtime:说明
knowledge:lookup、knowledge:eval和knowledge.norm_lookup如何返回可追溯引用、适用性、版本和仲裁状态。 - 对工具失败、权限扩大、证据缺失和 Agent 冲突输出
Claim / Evidence / Tool Result / Decision。 - 指定安全审查和验证:交给 Argus 复核注入、越权和数据污染风险。
输出格式
默认输出:
- 结论
- Runtime 设计
- Context / Memory 策略
- Tool 权限边界
- Capability Registry / 仲裁门禁
- 评估与风险
- 后续动作
涉及 Knowledge Pack 时补充:
- Knowledge Pack 路径和编译产物。
- Reference Runtime 查询入口。
- eval gate 结果。
- 未覆盖知识域和不可回答边界。
Runtime 条目建议格式:
Source:
Runtime:
Instance:
输入:
输出:
工具:
记忆:
评估:
风险:
约束
- 不擅自扩大工具权限。
- 不让 Agent 直接加载完整仓库或完整角色文件夹。
- 不把未经评估的 Prompt 投入关键流程。
- 不替代 Vitruvius 判断建筑行业语义。
- 不允许 Memory 污染任务上下文。
- 不把未通过
knowledge:eval的 Knowledge Pack 接入关键 RAG / GraphRAG 流程。
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.
- 8d ago First seen · 87 lines · 64 tokens per session scan A 10f29ed6a669
aios-runtime is a skill published in the GitHub repository ArchSightLabs/archsight-aios (14 stars, last pushed 12d ago), licensed Apache-2.0. It adds 64 tokens to every session and 987 once invoked, about $0.0003 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
ai-engineering-toolkit
6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
ai-product
Every product will be AI-powered. The question is whether you'll build it right or ship a demo that falls apart in production.
ai-product
Every product will be AI-powered. The question is whether you'll build it right or ship a demo that falls apart in production. This skill covers LLM integration patterns, RAG architecture, prompt engineering that scales, AI UX that users trust, and cost optimization that doesn't bankrupt you. Use when "keywords…
ai-llm-application
Group skill: AI/LLM application — provider selection, app patterns, RAG, agents, prompts, evaluation, safety, and monitoring.
Ai Product
Every product will be AI-powered. The question is whether you'll build it right or ship a demo that falls apart in production. This skill covers LLM integration patterns, RAG architecture, prompt ...
llm-ops
LLM Operations -- RAG, embeddings, vector databases, fine-tuning, prompt engineering avancado, custos de LLM, evals de qualidade e arquiteturas de IA para producao.