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-participategit 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-participate)<a href="https://agentmods.dev/skills/cronusl-1141/ai-company/meeting-participate"><img src="https://agentmods.dev/badge/skills/cronusl-1141/ai-company/meeting-participate/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-participate"><img src="https://agentmods.dev/badge/skills/cronusl-1141/ai-company/meeting-participate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Agent Snooping · line 21 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
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 | $0.00016 | $0.00899 |
| Opus 5 | $0.00008 | $0.00449 |
| Sonnet 5 | $0.00003 | $0.00180 |
| Haiku 4.5 | $0.00002 | $0.00090 |
Grade B, and why
meeting-participate scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 13d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
curl -s "http://localhost:$(cat ~/.claude/data/ai-team-os/api_port.txt)/api/agents/whoami?name=<你的名字>&session_id=<你的会话id>" Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s "http://localhost:$(cat ~/.claude/data/ai-team-os/api_port.txt)/api/agents/whoami?name=<你的名字>&session_id=<你的会话id>" What it actually says
Meeting Participate — 会议参与技能
当你被邀请参加一个会议时,按照以下流程参与讨论。会议是多 Agent 异步协作的核心机制。
前提:先拿到自己的 agent_id
发言必须署自己的名,所以第一步是确认 agent_id 与 agent_name。不需要注册——
你被派出时 SubagentStart hook 已自动把你收编进团队(os-register 技能与
agent_register 工具均已退役)。按下面顺序取 id,命中即停:
-
读注入:启动上下文里的「## 你的 OS 身份」块,直接给出
agent_id/team_id/ 名字。绝大多数情况到此为止。 -
服务端反查(注入里写着"尚未落库"时用):收编与注入是并行的,慢一步很正常。
curl -s "http://localhost:$(cat ~/.claude/data/ai-team-os/api_port.txt)/api/agents/whoami?name=<你的名字>&session_id=<你的会话id>"服务端按
cc_agent_id→会话+名字→名字三级反查,返回{"found": true, "agent_id": ...}。 -
兜底:
agent_list(team_id)里按名字找自己那一行。
三条都拿不到(OS API 不可达)时,用你的名字作为 agent_id 发言并在内容里注明——
宁可留下可追溯的署名,也不要因为拿不到 id 就不发言。
参与流程
1. 读取会议消息
进入会议后,先了解当前讨论状态:
使用 MCP tool: meeting_read_messages
参数:
meeting_id: <会议ID>
2. 分析已有发言
仔细阅读所有已有消息:
- 理解每位参与者的核心观点
- 找出共识点和分歧点
- 识别尚未被讨论的角度
3. 发送你的观点
根据当前轮次发送消息:
使用 MCP tool: meeting_send_message
参数:
meeting_id: <会议ID>
agent_id: <你的agent_id>
agent_name: <你的名称>
content: <你的发言内容>
round_number: <当前轮次>
4. 讨论规则
严格遵循以下讨论规则:
Round 1 — 各自观点
- 独立提出你对议题的看法
- 基于你的角色和专业领域发表见解
- 不需要引用他人(还没有人发言)
Round 2+ — 引用回应
- 必须先读取前人发言(再次调用
meeting_read_messages) - 引用并回应具体观点,格式如:
@agent_name 提到"...",我认为... - 可以补充新观点,但必须至少回应一个已有观点
- 明确表达同意或不同意,并给出理由
最后一轮 — 汇总
- 总结本次讨论的共识
- 列出仍存在的分歧
- 提出下一步建议
5. 多轮参与
如果会议有多轮讨论:
- 每轮开始前重新读取消息,获取最新发言
- 递增
round_number - 持续参与直到会议被主持人结束
发言质量要求
- 具体: 不要泛泛而谈,要给出具体的技术方案或理由
- 有建设性: 提出问题的同时给出解决方案
- 尊重他人: 不同意时对事不对人,用"我认为"而非"你错了"
- 简洁: 每次发言聚焦1-3个核心观点,避免冗长
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 · 96 lines · 16 tokens per session scan B 648af0627c86
meeting-participate is a skill published in the GitHub repository CronusL-1141/AI-company (357 stars, last pushed yesterday), licensed MIT. It adds 16 tokens to every session and 899 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). 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.