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-prompt-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-prompt-compare)<a href="https://agentmods.dev/skills/archsightlabs/archsight-aios/aios-prompt-compare"><img src="https://agentmods.dev/badge/skills/archsightlabs/archsight-aios/aios-prompt-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-prompt-compare"><img src="https://agentmods.dev/badge/skills/archsightlabs/archsight-aios/aios-prompt-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 | $0.00050 | $0.01954 |
| Opus 5 | $0.00025 | $0.00977 |
| Sonnet 5 | $0.00010 | $0.00391 |
| Haiku 4.5 | $0.00005 | $0.00195 |
Grade A, and why
aios-prompt-compare scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AIOS Prompt Compare
目标
以 Daedalus（AI 研发工程师）的方式组织 Prompt / Skill 效果对比，把同一输入下的弱提示词、便携强提示词和真实 Skill 触发结果拆成三栏评估，判断哪一类输出更稳定、更可复核、更值得沉淀为 Skill。
本 Skill 是内部评估和治理入口，不替代具体业务 Skill 执行，也不直接把评测结论当作生产可用性承诺。普通用户比较两份文档、两个版本或两个 AI 输出哪份更专业时，应使用 aios-compare，不要触发本 Skill。
适用场景
- 开发者明确写出
aios-prompt-compare，并要做 Prompt / Skill 测试。 - 对比
weakPrompt、prompts/basic-prompt.md和$aios-*Skill 真实运行结果。 - 判断一段提示词是否应升级为正式 Skill。
- 复盘同一 fixture 在不同提示词、不同 Skill 或不同模型下的输出差异。
- 检查输出是否遵守证据链、禁止结论、人工复核和脱敏边界。
- 维护
prompts/evaluations/*fixtures.json、run pack、run results 和 scorecard。
不适用：
- 普通用户比较两份文档、两个版本或两个 AI 输出哪份更专业；这类任务使用
aios-compare。 - 只想直接处理工程资料时，先使用对应业务 Skill。
- 没有同一输入或可对齐输出时，不做横向优劣判断，只记录待补材料。
- 不能把一次模型输出胜负当作长期质量结论。
输入
优先收集：
- 对比目标：弱提示词、便携强提示词、真实 Skill、旧版 Skill、新版 Skill 或不同模型。
- 同一份输入材料：脱敏文本、Markdown fixture、公开样例或用户提供资料。
- 对应 fixture：例如
prompts/evaluations/engineering-business-basic-fixtures.json。 - 已生成的 run pack、run results、模型输出文件或三类原始输出。
- scorecard 或评估维度：结构完整度、证据定位、边界安全、可执行性、复用性、人工复核分流。
原始输出保全
对比报告必须保留三类输出的原始正文，不能只写摘要。
最低要求：
- 在分析前先建立
Raw Output Map，列出 weak、portable、skill-runtime 三类输出是否已提供、来源文件或运行记录、是否经过脱敏。 - 在报告末尾增加
原始输出附录，分别放入weak 原始输出、portable 原始输出、skill-runtime 原始输出。 - 每类原始输出必须用 fenced code block 包住，保持模型原始章节、表格、结论和措辞；只允许做必要脱敏，不允许改写成摘要。
- 如果某一类输出缺失，必须在对应附录写
未提供原始输出，并在结论中说明本次对比证据不足。 - 如果原始输出包含真实客户、联系人、项目名、地点、金额、日期、文件路径或源文件名，先脱敏为
[客户A]、[项目A]、[地点A]、[金额A]、[日期A]、[源文件A]，再放入附录。
摘要、scorecard 和沉淀判断只能基于这些原始输出得出；不能凭记忆、推测或二次转述补写原始输出。
三栏比较模式
默认使用三类输出，不要混在一个结论里：
weak：弱提示词结果。通常来自 fixture 中的weakPrompt，用于暴露随口问的失败模式。portable：便携强提示词结果。通常来自skills/*/prompts/basic-prompt.md，用于验证无 Skill runtime 时的最低可用版本。skill-runtime：真实 Skill 结果。必须来自宿主工具按$aios-*或自动 Skill 触发机制执行后的输出，而不是简单把SKILL.md当普通 prompt 粘贴。
如果当前只有 weak/basic 两类结果，明确标注 skill-runtime: 未提供，不要假装完成了 Skill 运行对比。
工作流
- 明确对比对象和输入是否一致；输入不一致时先停止横向比较。
- 建立 Run Map：记录 caseId、skillId、输入来源、promptSource、模型、运行时间和输出文件。
- 建立 Raw Output Map：确认 weak、portable、skill-runtime 三类原始输出是否存在、是否脱敏、是否同源。
- 分别读取 weak、portable、skill-runtime 三类原始输出；缺失时停止声称完整三栏对比。
- 按统一 scorecard 逐项评分：结构完整度、证据追溯、边界安全、可执行动作、模板复用、人工复核分流。
- 标出失败模式：编造事实、跳过资料状态判断、越权下结论、缺少 Evidence、无法落地到责任人或台账。
- 判断沉淀方向：保留普通提示词、强化 portable prompt、升级 / 修订 Skill，或补 fixture / scorecard。
- 输出原始输出附录和下一步验证命令或待补材料。
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 · 181 lines · 50 tokens per session scan A 7cd543250459
aios-prompt-compare is a skill published in the GitHub repository ArchSightLabs/archsight-aios (15 stars, last pushed 15d ago), licensed Apache-2.0. It adds 50 tokens to every session and 1,954 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
advanced-evaluation
This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise comparison, position bias, evaluation pipelines, or automated quality assessment.
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.
darwinian-evolver
Evolve prompts/regex/SQL/code with Imbue's evolution loop.
ai-wrapper-product
Expert in building products that wrap AI APIs (OpenAI, Anthropic, etc. ) into focused tools people will pay for. Not just "ChatGPT but different" - products that solve specific problems with AI.
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.
promptfoo-evaluation
Configures and runs LLM evaluation using Promptfoo framework. Use when setting up prompt testing, creating evaluation configs (promptfooconfig.yaml), writing Python custom assertions, implementing llm-rubric for LLM-as-judge, or managing few-shot examples in prompts. Triggers on keywords like "promptfoo", "eval", "LLM…