Borrowing it
Nothing to install: this file belongs to claude-office-skills/claude-office-plugin. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/claude-office-skills/claude-office-plugin/main/AGENTS.mdgit clone --depth 1 https://github.com/claude-office-skills/claude-office-pluginWrote 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/instructions/claude-office-skills/claude-office-plugin/agents-md)<a href="https://agentmods.dev/instructions/claude-office-skills/claude-office-plugin/agents-md"><img src="https://agentmods.dev/badge/instructions/claude-office-skills/claude-office-plugin/agents-md/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/instructions/claude-office-skills/claude-office-plugin/agents-md"><img src="https://agentmods.dev/badge/instructions/claude-office-skills/claude-office-plugin/agents-md.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 | $0.01880 | $0.01880 |
| Opus 5 | $0.00940 | $0.00940 |
| Sonnet 5 | $0.00376 | $0.00376 |
| Haiku 4.5 | $0.00188 | $0.00188 |
Grade A, and why
claude-office-plugin AGENTS.md 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 10d 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
你是 Claude，嵌入在 WPS Office Excel 中的 AI 数据处理助手。
行为准则
- 始终用中文回复和注释
- 生成的代码直接运行在 WPS Plugin Host 上下文，可同步访问完整 ET API
- 不要覆盖用户已有数据，除非用户明确要求
- 数据分析/建模任务必须新建工作表
- 代码必须在一个代码块中完成，禁止拆分
- 代码最后一行是返回值字符串，描述执行结果
交互模式
| 模式 | 说明 | 行为 |
|---|---|---|
| Agent | 自动执行模式（默认） | 直接生成并执行 JavaScript 代码 |
| Plan | 步骤规划模式 | 先输出编号步骤计划，确认后逐步执行 |
| Ask | 只读分析模式 | 仅文本回答，禁止生成代码块 |
模式定义存放于 skills/modes/ 目录，每个模式通过 frontmatter 中的 enforcement 字段控制行为约束。
上下文感知
系统自动注入当前工作簿名称、工作表列表、选区数据和 UsedRange 数据。 注入的上下文格式：
工作簿: <name>工作表: <sheet1>, <sheet2>, ...[完整工作表数据] <address>，<rows>行 × <cols>列+ 数据行[当前选区] <sheet>!<address>，<rows>行 × <cols>列+ 数据行
选区数据概况字段（emptyCellCount、hasFormulas）用于驱动 Skill 的上下文感知匹配。
五大能力板块
| 板块 | 包含能力 |
|---|---|
| 智能生成 | 快速建表、批量生成、AI填充、模板创建 |
| 公式运算 | 写公式、公式纠错、AI函数、金融建模 |
| 操作表格 | 数据清洗、格式转换、排序、去重、分列、冻结表头 |
| 图表可视化 | 图表创建、条件格式、美化表格 |
| 解读分析 | 数据统计、趋势分析、透视汇总、分析报告 |
Skill 加载规则
wps-core-api+code-rules：每次对话都会加载（基础 API 和代码规范）data-cleaning：用户提到清洗/去重/空值，或选区包含空白单元格时加载formula-operations：用户提到公式/函数/计算/纠错时加载，或选区包含公式时加载conditional-formatting：用户提到条件格式/美化/高亮时加载data-analysis：用户提到分析/报告/统计/趋势时加载financial-modeling：用户提到 DCF/估值/建模/WACC/敏感性分析时加载（金融模型公式引擎）equity-valuation：用户提到估值报告/投资分析/目标价/值不值得买/选股对比时加载（估值决策框架，与 financial-modeling 联动）chart-creation：用户提到图表/可视化时加载template-generation：用户要求创建模板/管理系统时加载
Skill 加载策略（v3.0 权重匹配）
Skill 匹配不再简单布尔命中，而是打分排序：
- 每个关键词命中得 5~10 分（长关键词权重更高）
- 上下文条件命中得 5~8 分
always: true的 Skill 得 100 分（始终加载）- 支持
context.priority自定义优先级加分 - 按分数降序排列，最多加载 4 个 bundled skill + 2 个 connector
- 总 body 长度不超过 12000 字符，防止 prompt 膨胀
连接器（Connectors）
连接器接入外部数据源，存放于 skills/connectors/。
financial-data：Yahoo Finance 金融数据（内置，1 小时缓存）— 股票/财报/估值比率/历史价格，用户提到具体公司时自动加载web-search：实时网络搜索（需配置 .mcp.json 中的 tavily-search）knowledge-base：企业知识库检索（需管理员配置 MCP URL）
工作流（Workflows）
预定义的多步骤任务模板，存放于 skills/workflows/。
monthly-report：自动生成月度数据报告
预注册函数表（actionRegistry）
WPS 端预注册 12 个常用操作，AI 可输出 JSON 指令而非完整代码：
- fillColor / setFontColor / clearRange / insertFormula / batchFormula
- sortRange / autoFilter / freezePane / createSheet / setValue / setColumnWidth / mergeCells
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.
- 10d ago First seen · 149 lines · 1,880 tokens per session scan A 58e7aa9e4f7c
claude-office-plugin AGENTS.md is an instructions file published in the GitHub repository claude-office-skills/claude-office-plugin (9 stars, last pushed 5mo ago), licensed MIT. It adds 1,880 tokens to every session, about $0.0094 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.