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 CronusL-1141/AI-company --skill meeting-facilitategit clone --depth 1 https://github.com/CronusL-1141/AI-companyWrote 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/cronusl-1141/ai-company/meeting-facilitate)<a href="https://agentmods.dev/skills/cronusl-1141/ai-company/meeting-facilitate"><img src="https://agentmods.dev/badge/skills/cronusl-1141/ai-company/meeting-facilitate/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/cronusl-1141/ai-company/meeting-facilitate"><img src="https://agentmods.dev/badge/skills/cronusl-1141/ai-company/meeting-facilitate.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 | $0.00072 | $0.04456 |
| Opus 5 | $0.00036 | $0.02228 |
| Sonnet 5 | $0.00014 | $0.00891 |
| Haiku 4.5 | $0.00007 | $0.00446 |
Grade A, and why
meeting-facilitate 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 13d 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 — 357 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meeting Facilitate — 会议主持技能
本技能指导你(Leader 或具备主持职责的 Agent)端到端组织一场多 Agent 会议:选模板 → 创建会议 → spawn 真实参与者 → 签到 → 推进轮次 → 验证全员发言 → 结束并汇总。
前置要求
- 知道自己的
agent_id(用于以主持人身份发言)——它由 SubagentStart 注入的「你的 OS 身份」块给出; 拿不到就GET /api/agents/whoami?name=<你的名字>&session_id=<会话id>自查(服务端按 cc id / 会话+名 反查) - 已明确:会议目的、需要的角色、目标产出
- 已知会议涉及的关键文件路径(用于 materials/context_files)
核心原则(看完这三条再往下读)
- OS 不会自动 spawn 参与者 —
meeting_create只创建会议记录和 dispatch_plan,真正让参与者到场必须靠你亲自调用 Agent tool。光创建不 spawn = 没人到场 = 会议失败。 - 绝不代打他人发言 — 你以主持人身份发言时,
agent_id和caller_agent_id必须都填你自己的 ID。用别人的agent_id发言会被 OS 标记为impersonation=true并写入审计日志。 - conclude 前必须确认全员发言 —
meeting_conclude默认开启validate_attendance,未发言者会让 conclude 返回 400。不要用force=True绕过——除非有不可抗力的技术理由。
主持流程(7 步)
Step 1: 选择会议模板
根据会议目的对照下表选模板。详细模板说明见 templates/<name>.md(progressive disclosure)。
| 目的 | 推荐模板 | 轮数 | 为何 |
|---|---|---|---|
| 发散创意、产生新想法 | brainstorm |
4 | 独立发散 → 交叉启发 → 评估 → 汇总 |
| 多方案中做选择 | decision |
3 | 陈述 → 质询 → 收敛 |
| 评审代码 / PR / 交付物 | review |
3 | 陈述 → 独立评审 → 回应裁定 |
| 项目复盘、提取教训 | retrospective |
3 | 4Ls → 改进方向 → 承诺计划 |
| 每日进度同步 | standup |
1 | 三问:完成 / 计划 / 阻塞 |
| 决策有重大分歧或风险 | debate |
4 | 正方陈述 → 反方质疑 → 正方回应 → 裁决 |
| 开放议程、自由议题 | lean_coffee |
3 | 议题收集 → 投票 → 时间盒讨论 |
| 架构 / 方案多视角评审 | council |
3 | 专家视角 → 交叉质询 → 裁决 |
不确定?用 template="free",OS 会根据 topic 关键词自动推荐。
Step 2: 创建会议(拿到 dispatch_plan)
必须使用结构化 participants(dict 列表),否则 dispatch_plan 里的 launch_call 会是空的,无法 ready-to-paste。
meeting_create(
topic="评审 v0.9 Prompt Registry 架构方案",
template="council", # Step 1 选的模板
team_id="repo-insight-arch", # 可省略,自动用活跃团队
team_name="repo-insight-arch", # 仅 OS 侧归属;不会写进 launch_call
participants=[
{
"name": "arch-lead",
"agent_template": "software-architect",
"role": "评估架构整体可行性与分层合理性",
"context_files": ["docs/v0.9-prompt-registry.md"],
"expected_output": "三段式:可行性 / 风险 / 建议",
},
{
"name": "backend-arch",
"agent_template": "backend-architect",
"role": "评估存储层与 API 设计",
"context_files": ["docs/v0.9-prompt-registry.md", "src/aiteam/storage/repository.py"],
"expected_output": "存储方案 + 接口契约 + 迁移路径",
},
],
rounds=[ # 可选,省略则用模板默认 rounds
{"topic": "立场陈述", "rule": "每人 3 段:评估视角 / 风险点 / 评分 1-5"},
],
materials=["docs/v0.9-prompt-registry.md"], # 全员必读
)
What ships with it
8 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.
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.
- 13d ago First seen · 357 lines · 72 tokens per session scan A c8dc45c0599e
meeting-facilitate is a skill published in the GitHub repository CronusL-1141/AI-company (357 stars, last pushed yesterday), licensed MIT. It adds 72 tokens to every session and 4,456 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
代码调试
A debugging workflow that reproduces a problem with a failing test, collects evidence, finds the underlying cause, applies a fix, and runs regression checks. Regression checks verify that the fix does not break behavior that already worked.
创建主题
A set of rules for creating or changing frontend visual themes through configuration. It covers colors, interface components, effects, backgrounds, naming, accessibility, and how preset themes are registered.
后端编码
A backend coding guide covering web APIs, databases, error handling, logging, and endpoint tests. Backend code runs on servers and handles data and application operations.
代码实现
A coding workflow for checking requirements, understanding existing code, designing module boundaries, writing tests first, implementing changes, and reviewing risks. TDD means writing a failing test, making it pass, then improving the code.
创建Agent
A guide for creating or changing agent configuration files. An agent is a configured software worker with a role, instructions, tools, limits, and status.
游戏方案规划
A planning skill for game projects. It helps structure a game design document, which describes the game's vision, mechanics, levels, systems, numbers, target platform, audience, and business model.