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 zhanglunet/openworker-zh-localized --skill corp-knowledgegit clone --depth 1 https://github.com/zhanglunet/openworker-zh-localizedWrote 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/zhanglunet/openworker-zh-localized/corp-knowledge)<a href="https://agentmods.dev/skills/zhanglunet/openworker-zh-localized/corp-knowledge"><img src="https://agentmods.dev/badge/skills/zhanglunet/openworker-zh-localized/corp-knowledge/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/zhanglunet/openworker-zh-localized/corp-knowledge"><img src="https://agentmods.dev/badge/skills/zhanglunet/openworker-zh-localized/corp-knowledge.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 | $0.00127 | $0.00952 |
| Opus 5 | $0.00063 | $0.00476 |
| Sonnet 5 | $0.00025 | $0.00190 |
| Haiku 4.5 | $0.00013 | $0.00095 |
Grade A, and why
corp-knowledge 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 9d 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.
What it actually says
企业知识库检索
一条纪律
没找到出处就说没找到。 企业知识库里的问题——报销标准、审批链、故障处置——答错的代价 不是"回答质量差"，是有人照着做了。凭模型记忆编一个看起来合理的制度条款，比直说"我在 知识库里没查到"糟糕得多。
每个结论都要给出处：文件路径 + 章节/行号。给不出出处的话，就不是结论，是猜测。
知识库在哪
管理员在全局配置里挂了只读的知识目录（knowledge_roots），它们对每个会话都可见：
# 先看清楚有哪些目录、大致什么结构
list_files
这些目录是只读的：你可以随便读、随便搜，但写不进去。要产出的东西写到工作目录。
怎么查（顺序很重要）
- 先 grep，再读文件。知识库通常有几百上千个文件，一个个读会烧光上下文。
grep "报销标准" # 先定位命中哪些文件 grep "差旅.*标准|标准.*差旅" # 术语不确定时用正则放宽 - 命中后只读相关段落，用
read_file_lines取命中行附近，不要整篇读进来。 - 顺着交叉引用走。制度文件常互相引用（"详见《差旅管理办法》第 4 条"）， 引用链的末端才是真正的规定。
- 注意时效。同一主题常有多个版本（
2024版、旧版、废止）。文件名和文档头部 的生效日期是判断依据；拿不准就把两个版本都列出来，让用户确认哪个现行有效。
术语对不上时
企业内部叫法和用户问法经常不一致（用户说"打车报销"，制度里写"市内交通费"）。 一次没搜到不等于没有：
- 换同义词再搜（报销/费用/结算、请假/休假/考勤、采购/招标/寻源）
- 用更短的词根搜（搜"差旅"而不是"差旅费报销标准是多少"）
- 用
list_files看目录结构，从分类往下找
试过这些还是没有，就明确说"知识库里没有这部分内容"，并建议去问谁。
回答的形状
结论：市内交通费单次上限 100 元，超出需部门经理审批。
出处：
- 制度/费用管理办法.md 第 3.2 节（2025-06 生效）
- 制度/审批权限表.md 第 12 行
补充：夜间 22:00 后打车不受此限（同文件 3.2.1）。
先给结论，再给出处，最后才是补充说明——用户多数时候只需要第一行。
不要做的事
- 不要把整个知识库读进上下文再回答。grep 定位 → 精读片段，永远是这个顺序。
- 不要把知识库内容原样大段复制进回答。摘要 + 出处，需要原文时用户会问。
- 不要试图修改知识库。它是只读挂载的，改动请走知识库自己的流程。
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.
- 9d ago First seen · 71 lines · 127 tokens per session scan A 57b208e07c0a
corp-knowledge is a skill published in the GitHub repository zhanglunet/openworker-zh-localized (2 stars, last pushed 2d ago), licensed MIT. It adds 127 tokens to every session and 952 once invoked, about $0.0006 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
frame-macos-notification
A template for realistic macOS Big Sur-style notification banners, with an app icon, title, message, and optional action button.
notifications
Send notifications through the unified notification router.
telegram-setup
Connect a Telegram bot to the Vellum Assistant gateway with automated webhook registration and credential storage.
chat-complex-documents
Chat with and search your complex documents — ask questions, extract tables and fields, and get answers grounded in the source. Connects the hosted Unstructured Transform MCP server to parse, structure, and enrich PDFs, Word/Excel/PowerPoint, images, scanned files, emails, and 60+ other formats into clean, AI-ready…
test-warp-ui
Guides testing Warp UI features and changes using the computer use tool. Use this skill only when computer-use testing was requested (explicit request or accepted offer) and the computeruse tool is available to the agent. Covers launching Warp and verifying UI behavior.
start-the-day
An on-demand personal daily briefing — weather, headlines, the shape of your day, and one thing worth your attention — in a sharp executive-assistant voice. The general-purpose morning brief; richer work or admin digests compose it as their general layer.