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-comparegit 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-compare)<a href="https://agentmods.dev/skills/archsightlabs/archsight-aios/aios-compare"><img src="https://agentmods.dev/badge/skills/archsightlabs/archsight-aios/aios-compare/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-compare"><img src="https://agentmods.dev/badge/skills/archsightlabs/archsight-aios/aios-compare.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 | $0.00057 | $0.01074 |
| Opus 5 | $0.00028 | $0.00537 |
| Sonnet 5 | $0.00011 | $0.00215 |
| Haiku 4.5 | $0.00006 | $0.00107 |
Grade A, and why
aios-compare 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 10d 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 Compare
目标
本 Skill 用于比较两份文档、两个版本或两个 AI 输出，帮助用户判断哪份更专业、更可复核、更适合交付，并看清差异、遗漏、风险边界和后续合并方向。
它是“文档对比”工具，不是 aios-prompt-compare。如果用户要做 weak / portable / skill-runtime 三栏提示词评测，或判断提示词是否值得沉淀为 Skill，应改用 aios-prompt-compare。
适用场景
- 比较两份 AI 输出，例如 WorkBuddy、Antigravity、Codex 对同一资料的输出。
- 比较两版文档，例如旧版 / 新版 README、方案、报告、提示词或培训材料。
- 比较同一业务资料的两个整理结果，例如合同节点表、日报问题台账、会议待办表、施工方案辅助复核清单。
- 比较客户版和内部版材料，检查外发边界、敏感信息、过度承诺和人工复核要求。
- 判断两份材料哪份更专业：看证据链、结构、行业术语、边界控制、可执行性和交付可读性，而不是只看篇幅长短。
不适用场景
- 不做提示词评测三栏报告；需要 weak / portable / skill-runtime 时使用
aios-prompt-compare。 - 不比较不同输入材料生成的输出优劣，除非用户明确要比较“资料本身差异”。
- 不输出最终法律、安全、质量、合规、结构计算、结算金额或责任归属结论。
输入
优先收集：
- 文档 A：文件名、版本、日期、用途、正文。
- 文档 B：文件名、版本、日期、用途、正文。
- 比较目标：结构差异、事实差异、遗漏项、表达边界、可执行性、外发风险、合并建议。
- 适用场景：内部复核、客户交付、培训演示、模板沉淀或版本合并。
工作流
- 建立 Compare Map：列出 A / B 的来源、版本、用途和是否同源。
- 判断是否可横向比较：同一输入、同一任务、同一目标时可比较优劣；不同输入时只比较资料差异。
- 对比结构：章节、表格、字段、输出粒度、是否便于复用。
- 对比事实和证据：是否引用来源、是否保留原文关键词、是否编造或漏掉关键事实。
- 对比边界：是否保留人工复核、资料缺口、不能下结论事项和敏感信息边界。
- 对比可执行性：是否能转成台账、清单、待办、矩阵或交底材料。
- 判断专业度：从证据链、结构完整度、行业表达、风险边界、可执行性、交付适配度给出分项判断。
- 输出合并建议：保留 A、保留 B、合并两者、补充资料或回到专项 Skill 重跑。
输出格式
默认输出：
- 结论摘要
- Compare Map
- 可比性判断
- 结构差异
- 内容差异
- 边界和风险差异
- 可执行性差异
- 专业度评分和判定
- 建议采用 / 合并方向
- 不能直接下结论的事项
差异条目格式：
维度：
文档 A：
文档 B：
差异判断：
影响：
建议：
专业度评分建议维度：
证据链：
结构完整度：
行业术语和表达：
风险边界：
可执行性：
交付可读性：
综合判断：
约束
- 不把更长当作更好；优先看证据链、结构、边界、可执行性、专业表达和用户任务匹配度。
- 不把一次 AI 输出胜负当作模型长期质量结论。
- 不把提示词评测任务误做成普通文档对比；需要三栏评测时转
aios-prompt-compare。 - 不在缺少同源输入时比较“谁更准”；只能说明输入不同或证据不足。
- 不替代业务专家、法务、造价、总工、监理、安全负责人或客户最终确认。
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.
- 10d ago First seen · 93 lines · 57 tokens per session scan A 08b34ec5e165
aios-compare is a skill published in the GitHub repository ArchSightLabs/archsight-aios (14 stars, last pushed 13d ago), licensed Apache-2.0. It adds 57 tokens to every session and 1,074 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
audio-transcriber
Transform audio recordings into professional Markdown documentation with intelligent summaries using LLM integration.
mantis-report
Generates a human-readable security review packet compiled from confirmed findings and exploit chains. Use at the end of a review cycle to produce stakeholder-facing documentation. Don't use for auditing code or verifying patches directly.
epd-parser
Extract GWP, life-cycle stages, certifications, and impact metrics from an EPD PDF. Use when given a declaration to parse; not to find or compare EPDs.
csv-to-sif
Export a project's FF&E product-library CSV as dealer-system SIF. Use to produce a .sif schedule; use sif-to-csv for the reverse direction.
product-data-cleanup
Clean a local FF&E CSV schedule by normalizing casing, dimensions, units, language, materials, and formatting. Use when asked to clean, fix, or standardize product data.
product-data-import
Generate a formatted FF&E specification schedule from notes, CSV, or pasted lists and optionally save it to the project's 33-column CSV library. Use when asked to import products or build a schedule.