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 malue-ai/dazee-small --skill feishugit clone --depth 1 https://github.com/malue-ai/dazee-smallWrote 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/malue-ai/dazee-small/feishu)<a href="https://agentmods.dev/skills/malue-ai/dazee-small/feishu"><img src="https://agentmods.dev/badge/skills/malue-ai/dazee-small/feishu/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/malue-ai/dazee-small/feishu"><img src="https://agentmods.dev/badge/skills/malue-ai/dazee-small/feishu.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00032 | $0.01896 |
| Opus 5 | $0.00016 | $0.00948 |
| Sonnet 5 | $0.00006 | $0.00379 |
| Haiku 4.5 | $0.00003 | $0.00190 |
Grade A, and why
feishu 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 8d 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 — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
飞书 (Feishu/Lark)
通过 lark-oapi SDK 操作飞书全生态:消息、文档、日历、任务、审批、妙记。中国团队的核心协作工具。
使用场景
消息
- 用户说「在飞书上给 xxx 发个消息」「在 xxx 群里发个通知」
- 用户说「飞书上有没有新消息?」「看看飞书群里最新的讨论」
文档
- 用户说「帮我在飞书文档里创建一个周报」「搜索飞书里那个技术方案文档」
- 用户说「把这段内容追加到飞书文档末尾」「读一下飞书知识库里的 XX」
日历
- 用户说「帮我在飞书日历上建个会议」「看看我飞书日历上今天的安排」
- 用户说「把会议改到周五」「取消明天的周会」
任务
- 用户说「看看我飞书上有什么待办」「帮我加个飞书任务:周五前交报告」
- 用户说「把飞书上那个任务标记为完成」
审批
- 用户说「查看待我审批的流程」「我的请假申请审批到哪了?」
妙记(会议纪要)
- 用户说「帮我看看上次周会的会议纪要」「把昨天的会议纪要总结一下」
- 用户说「提取会议的行动项」
前置条件
- 在飞书开放平台(https://open.feishu.cn/)创建应用
- 获取 App ID 和 App Secret(如已配置飞书 Gateway 通道则可复用)
- 设置环境变量:
export FEISHU_APP_ID="cli_xxxx" export FEISHU_APP_SECRET="xxxx" - 在飞书管理后台为应用授权对应权限
执行方式
项目已安装 lark-oapi SDK,优先使用 SDK 而非原始 HTTP 调用。
初始化客户端
import lark_oapi as lark
import os
client = lark.Client.builder() \
.app_id(os.environ["FEISHU_APP_ID"]) \
.app_secret(os.environ["FEISHU_APP_SECRET"]) \
.build()
发送消息
from lark_oapi.api.im.v1 import *
import json
request = CreateMessageRequest.builder() \
.receive_id_type("chat_id") \
.request_body(CreateMessageRequestBody.builder()
.receive_id("目标群聊或用户ID")
.msg_type("text")
.content(json.dumps({"text": "消息内容"}))
.build()) \
.build()
response = client.im.v1.message.create(request)
富文本消息:
content = {
"zh_cn": {
"title": "周报通知",
"content": [
[{"tag": "text", "text": "请各位提交本周周报"}],
[{"tag": "a", "text": "点击填写", "href": "https://..."}],
]
}
}
# msg_type = "post"
获取群聊列表:
request = ListChatRequest.builder().build()
response = client.im.v1.chat.list(request)
文档操作
from lark_oapi.api.docx.v1 import *
# 读取文档内容
request = RawContentDocumentRequest.builder() \
.document_id("文档ID") \
.build()
response = client.docx.v1.document.raw_content(request)
# 创建文档
request = CreateDocumentRequest.builder() \
.request_body(CreateDocumentRequestBody.builder()
.title("文档标题")
.folder_token("目标文件夹token")
.build()) \
.build()
response = client.docx.v1.document.create(request)
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.
- 8d ago First seen · 253 lines · 32 tokens per session scan A c31990b76174
feishu is a skill published in the GitHub repository malue-ai/dazee-small (36 stars, last pushed 5mo ago), licensed MIT. It adds 32 tokens to every session and 1,896 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
recipe-create-doc-from-template
Copy a Google Docs template, fill in content, and share with collaborators.
reversa-sync
Convergência pós-coding do Reversa: destila a feature entregue num adendo em reversasdd/addenda/, mantendo a extração representativa entre re-extrações, sem tocar nos artefatos originais. Passo opcional do ciclo forward após /reversa-coding.
slack-report-delivery
Deliver formatted network reports, audit results, topology diagrams, and compliance documentation to Slack channels with rich Block Kit formatting. Use when posting a health check report, sharing a security audit, delivering topology diagrams, or sending scheduled network reports to Slack.
notion
Notion CLI/API for pages, Markdown content, data sources, files, comments, search, Workers, and raw API calls.
sred-project-organizer
Take a list of projects and their related documentation, and organize them into the SRED format for submission.
notion
Search, read, create, and update Notion pages and databases. Supports knowledge capture, meeting prep, research documentation, and spec-to-task workflows.