aios-construction-meeting

aios-construction-meeting is a skill for Claude Code, Codex from ArchSightLabs/archsight-aios. It costs 54 tokens per session (1,420 once invoked), scanned A, original, Apache-2.0.

A workflow for turning construction meeting records into a trackable list of decisions, tasks, owners, deadlines, disputes, evidence, and follow-up items.

In plain words
What is it for?
Use it with site coordination meetings, technical briefings, quality or safety meetings, progress meetings, payment discussions, and other building-project records.
Why use it?
It makes unclear meeting discussions easier to verify and act on, while separating confirmed conclusions from items that still need checking.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the archsight-aios plugin — 33 skills shipped together

Good fit Use it with site coordination meetings, technical briefings, quality or safety meetings, progress meetings, payment discussions, and other building-project records.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/archsightlabs/archsight-aios/aios-construction-meeting
Install

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.

Any agent
npx skills add ArchSightLabs/archsight-aios --skill aios-construction-meeting
Clone the repo
git clone --depth 1 https://github.com/ArchSightLabs/archsight-aios

Made for: Claude Code, Codex.

Or install archsight-aios, the plugin that ships this one along with the rest of its 33 skills.

Wrote 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.

agentmods badge for aios-construction-meeting

README.md
[![agentmods](https://agentmods.dev/badge/skills/archsightlabs/archsight-aios/aios-construction-meeting/github.svg)](https://agentmods.dev/skills/archsightlabs/archsight-aios/aios-construction-meeting)
Your own site
<a href="https://agentmods.dev/skills/archsightlabs/archsight-aios/aios-construction-meeting"><img src="https://agentmods.dev/badge/skills/archsightlabs/archsight-aios/aios-construction-meeting/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.

agentmods 80×15 button for aios-construction-meeting

Your own site · 80×15
<a href="https://agentmods.dev/skills/archsightlabs/archsight-aios/aios-construction-meeting"><img src="https://agentmods.dev/badge/skills/archsightlabs/archsight-aios/aios-construction-meeting.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,420 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00054 $0.01420
Opus 5 $0.00027 $0.00710
Sonnet 5 $0.00011 $0.00284
Haiku 4.5 $0.00005 $0.00142

Measured 12d ago against content hash 11b28c145f23, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

aios-construction-meeting 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.

skills/aios-construction-meeting/SKILL.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AIOS Meeting

目标

以 Mason(工程总工)的方式把工程会议记录转化为可执行的待办闭环表,保留结论来源、责任边界和未决争议。

本 Skill 不替代正式会议纪要签发、监理指令、合同通知或业主审批;未签发或未确认内容必须标注为 需核验

AIOS 适用性

本 Skill 仅用于建筑工程现场协调、技术交底、质量安全、进度推进、商务签证和专题会议资料。

  • 工程会议纪要、录音转写、群内会议摘要、交底会记录和专题会记录,启用 AIOS 行业增强。
  • 普通公司会议、HR 面试纪要、销售会议或非工程管理会议,不使用本 Skill。
  • 会议内容不涉及工程责任、进度、质量、安全、图纸、签证或交付证据时,优先使用通用会议纪要能力。

输入

优先收集:

  • 原始会议记录、录音转写、手写纪要整理稿或聊天会议摘要。
  • 会议基本信息:项目、会议类型、日期、参会方、主持人、纪要版本。
  • 已签发纪要、会议附件、图纸编号、联系单编号或任务台账。
  • 用户关注点:待办、争议、签证、风险、下次会议追踪。

基础版模式

用于工程业务资料处理、项目复核辅助、部门工作流整理或模板沉淀时,按本节收口。可复制的基础提示词见 prompts/basic-prompt.md

最小可用输入:

  • 脱敏后的会议纪要、协调会记录、专题会记录、交底记录或会议录音转写摘要。
  • 会议日期、会议类型、项目名称、来源文件、参会方或记录人。
  • 用户要复核的问题,例如待办、责任线索、期限、遗留争议、下次追踪事项。
  • 人工复核岗位,例如项目经理、资料员、部门负责人、商务、法务或监理。

基础输出优先级:

  1. 只提取会议资料中明确出现的决定、问题、待办和分工。
  2. 未明确责任人的事项标为“需确认责任人”,未明确期限的事项标为“需确认期限”。
  3. 发言人只能作为责任线索,不得默认就是最终责任人。
  4. 不把未签发、未确认或仍在讨论的内容写成正式会议结论。

标准详版报告与输出自检

短指令触发本 Skill 时,默认输出标准详版报告,不要压缩成摘要。标准详版报告必须包含:资料来源清单、主分析表 / 清单 / 台账、资料缺口、人工复核岗位、AI 不应下结论事项、输出自检。

最小详度要求:

  • 资料足够时,待办闭环表、遗留争议或下次会议追踪清单至少展开 3 条可定位事项;资料不足时,列出全部可定位事项并说明不足原因。
  • 主分析表必须保留“事项 / 责任人或线索 / 截止时间 / 交付物 / 证据 / 处理建议”等字段,不得只写概括段落。
  • 输出自检必须逐项确认是否包含资料来源、主分析表 / 清单 / 台账、资料缺口、人工复核岗位、AI 不应下结论事项;缺一项时先补齐再结束。

Capability 与证据

  • 每条结论和待办必须引用会议原文、发言人、时间戳、页码、段落或纪要编号。
  • 涉及规范、制度、质量安全或监管要求时,调用或要求 knowledge.norm_lookup;没有工具结果时标注 需核验
  • 会议结论与合同、图纸或联系单冲突时,输出 处理建议:转人工复核 并交给 aios-commercial-contractaios-commercial-variation 复核。

工作流

  1. 建立会议资料来源清单:记录会议日期、版本、参会方、来源文件和定位方式。
  2. 识别会议类型:协调会、交底会、质量安全会、进度会、商务会或专题会。
  3. 抽取明确结论:只记录原文确认的结论,未形成一致意见的事项归入争议。
  4. 抽取待办:责任人、协作方、截止时间、交付物、依赖和验证方式。
  5. 标出遗留争议:责任不清、期限不清、缺附件、缺图纸、缺正式签认。
  6. 识别签证/变更线索:有现场条件变化、图纸争议、停工窝工、设计变更时交给 aios-commercial-variation
  7. 生成下次会议追踪清单:按责任人和截止时间排序。

输出格式

默认输出:

  1. 会议核心结论
  2. 资料来源清单
  3. 待办闭环表
  4. 遗留争议与风险
  5. 潜在变更 / 签证线索
  6. 下次会议追踪清单
  7. 证据仲裁

待办条目格式:

事项:
责任人:
协作方:
截止时间:
交付物:
证据:
处理建议:

证据仲裁条目格式:

判断事项:
证据:
工具结果:
处理建议:可继续 / 需核验 / 转人工复核

约束

  • 不把未形成会议结论的讨论写成正式决议。
  • 不补猜责任人、期限或承诺内容。
  • 不替代正式纪要签发、监理指令或合同通知。
  • 不输出变更成立、索赔成立或责任归属结论。
  • 会议来源不完整时必须保留 需核验

Read the full file on GitHub · 115 lines

Files

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.

Changes

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.

  1. 12d ago First seen · 115 lines · 54 tokens per session scan A 11b28c145f23

Subscribe to this mod's changes

aios-construction-meeting is a skill published in the GitHub repository ArchSightLabs/archsight-aios (15 stars, last pushed 15d ago), licensed Apache-2.0. It adds 54 tokens to every session and 1,420 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.