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 zylMozart/ClaudeTeam --skill verify-statusgit clone --depth 1 https://github.com/zylMozart/ClaudeTeamWrote 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/zylmozart/claudeteam/verify-status)<a href="https://agentmods.dev/skills/zylmozart/claudeteam/verify-status"><img src="https://agentmods.dev/badge/skills/zylmozart/claudeteam/verify-status/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/zylmozart/claudeteam/verify-status"><img src="https://agentmods.dev/badge/skills/zylmozart/claudeteam/verify-status.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 | $0.00002 | $0.01595 |
| Opus 5 | $0.00001 | $0.00797 |
| Sonnet 5 | $0.00000 | $0.00319 |
| Haiku 4.5 | $0.00000 | $0.00160 |
Grade A, and why
verify-status 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 11d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
verify-status — 确认员工在不在线、在不在岗
何时用
这个 skill 回答一个问题:这个员工现在在不在线、在不在正确的状态(在岗、能接活)。两个场景:
- 部署后必跑(最后一道闸):团队拉起 → 每个员工的身份 init 消息注入完成 → 执行本 skill → 全员在岗才允许宣布部署成功。
claudeteam health绿不算数——health 只看进程不看"人",进程活着不等于员工在线。 - 平时单点复用:巡视中怀疑某员工掉线、不回话、不在状态时,单独对它执行第 2 步起的判读流程。
核心约束(执行时必须遵守):不要用正则/字符串匹配来判定。把每个员工 pane 的整段 tmux 文本拉出来,由你(执行本 skill 的 agent)自己通读、自己做语义判断。下文的判读维度和病征样例是帮助你理解的参照,不是匹配规则——CLI 的横幅、提示语、界面布局每个版本都会变,你要判断的是语义上它是否就位,不是某行字是否出现。
输入
- team 成员表(
claudeteam team,知道要确认谁)。 - 每个员工 pane 的完整近期文本(
claudeteam peek <agent> <N>,N 给足,覆盖从身份注入到当下的全过程,别只截尾巴几行)。
步骤
-
给足处理时间(部署场景)。身份消息注入后,员工需要时间读身份文件、查收件箱、回报到位。先等一两分钟量级(慢模型更久)再开始确认——注入完立刻看,看到的多半是还没开始的画面,会误判。(巡视复用时跳过本步,直接读现场。)
-
逐员工拉取整段现场,自己读。对每一个员工(部署场景一个都不能跳过;巡视复用时只看怀疑对象),把 pane 全文拉出来,像读一份终端实录一样从头到尾读完,回答一个问题:
这个员工现在在线吗?在岗吗?——即:它是否以正确的身份完成了该做的事(部署场景=身份消息要求的动作),并处于能接活的状态?
从这几个维度综合判断(任何单一特征都不是结论):
- 它收到身份消息了吗? 实录里应当能看到身份 init 文本到达,并且是被提交执行了,而不是还躺在输入框里没回车。
- 它按身份消息行动了吗? 正常的实录会显示它去读了身份文件、查了收件箱、更新了状态之类的动作痕迹——具体做了哪几样不重要,重要的是它在按指令行动而不是无反应。
- 它知道自己是谁吗? 实录里它的自述(比如收尾的一行 ack)应当与它的员工名一致。自称成了别的员工、或表现出"不知道自己是谁"的困惑,判不通过。
- 它现在处于什么状态? 健康的终态是:动作做完,停在一个安静的、等待下一条输入的就绪界面。还在长考属于"尚未完成"而非"失败"——回到第 1 步再等一轮。
- 有没有明显的病征? 留意这类画面(举例性质,形态会变化,靠语义理解不靠记关键词):要求登录/重新认证的提示、token 或 401 类报错、CLI 退出后裸露的 shell 提示符、反复打转的报错循环、身份文本卡在输入框未提交。看到这类画面,直接进第 4 步对应处置。
-
拿不准就问一句。读完实录仍吃不准时(比如画面安静但看不出它做没做过事),允许做一次轻量活性确认:给该员工注入一句无副作用的点名(让它用一行回答自己的名字和状态),等片刻重新拉实录看是否正确响应。每员工最多问一次,别反复戳。
-
分情况处置:
- 尚未完成(长回合未结束)→ 再等一轮回到第 2 步。总确认窗口给到合理上限(十分钟量级),超时仍未就位按"未通过"处理。
- 身份文本未提交(卡在输入框)→ 补一次提交键,回到第 2 步复查。软修复,每员工最多一次。
- 认证类病征(要求登录、token 过期、401)→ 不要试图自己绕过。记下员工名、CLI 类型、实录关键画面,进入"部署失败"出口。
- 其他未通过(自我认知错乱、CLI 崩、反复报错)→ 同上记录;崩溃类可先重拉一次(rehire/reidentify)再复查,同样每员工最多一次。
-
结论与出口(一票否决):
- 全员通过 → 逐员工写一行结论(员工名 + 通过 + 一句话依据,依据引用你在实录里看到的事实),之后才允许宣布部署成功、通知测试开跑。
- 任一员工最终未通过 → 判本次部署失败。写清:哪个员工、什么病征、实录关键片段、做过哪些软修复;明确提示用户需要人工介入登录(指出是哪个 CLI 的认证问题,让用户完成登录/换 token 后重新部署或重拉该员工)。失败时不通知测试开跑,不把"进程都活着"当成部署成功。
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.
- 11d ago First seen · 55 lines · 2 tokens per session scan A 49338fd18105
verify-status is a skill published in the GitHub repository zylMozart/ClaudeTeam (232 stars, last pushed 1mo ago), licensed MIT. It adds 2 tokens to every session and 1,595 once invoked, about $0.0000 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.