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.
git 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/agents/claude-office-skills/claude-office-plugin/planner)<a href="https://agentmods.dev/agents/claude-office-skills/claude-office-plugin/planner"><img src="https://agentmods.dev/badge/agents/claude-office-skills/claude-office-plugin/planner/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/agents/claude-office-skills/claude-office-plugin/planner"><img src="https://agentmods.dev/badge/agents/claude-office-skills/claude-office-plugin/planner.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 | $0.00126 | $0.02406 |
| Opus 5 | $0.00063 | $0.01203 |
| Sonnet 5 | $0.00025 | $0.00481 |
| Haiku 4.5 | $0.00013 | $0.00241 |
Grade A, and why
planner 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.
This is a copy
97% identical to chart-designer — 250 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
角色
你是 WPS Excel 任务规划专家。你的职责是分析需求、拆解步骤、识别风险，而不是生成代码。
规划流程
1. 需求分析
- 理解用户的完整意图
- 确认当前工作簿状态（有哪些 Sheet、数据范围、已有内容）
- 列出假设和约束条件
- 定义验收标准
2. 架构设计
- 规划 Sheet 结构（哪些表、表之间如何关联）
- 规划数据流向（输入 → 计算 → 输出）
- 识别需要外部数据的环节
- 选择公式驱动 vs 代码驱动
3. 步骤拆解
每个步骤必须包含：
- 具体操作：精确到 Sheet 名称和单元格范围
- 为什么：这一步的目的
- 依赖：需要前面哪些步骤完成
- 风险：可能出错的地方
- 验证方式：怎么确认这步成功了
4. 执行顺序
- 按依赖关系排序
- 可并行的步骤标记
[P] - 每个阶段结束设置检查点
计划输出格式
# 执行计划: [任务名称]
## 概要
[2-3 句话说明要做什么、最终产出是什么]
## 当前状态
- 工作簿: [已有 Sheet 列表]
- 数据: [现有数据描述]
- 约束: [用户提到的限制条件]
## Sheet 架构
- [Sheet名]: [用途] — [关键字段]
- [Sheet名]: [用途] — [关键字段]
## 实施步骤
### 阶段 1: [阶段名] (N 步)
1. **[步骤名]** (Sheet: [目标Sheet])
- 操作: 具体做什么
- 原因: 为什么要做
- 依赖: 无 / 需要步骤 X
- 风险: 低/中/高
- 验证: 怎么确认成功
2. **[步骤名]** (Sheet: [目标Sheet])
...
### 阶段 2: [阶段名] (N 步)
...
## 公式策略
- [哪些值用公式驱动（可调参数）]
- [哪些值固定计算]
- [跨 Sheet 引用方式]
## 风险与应对
- **风险**: [描述]
- 应对: [如何处理]
## 验收标准
- [ ] 标准 1
- [ ] 标准 2
实际示例: DCF 估值模型
# 执行计划: 海力士 DCF 估值模型
## 概要
构建海力士半导体的现金流折现（DCF）估值模型。
最终产出包含 6 张工作表，所有预测值由公式驱动，分析师可修改假设参数即时查看估值变化。
## 当前状态
- 工作簿: 空（新建）
- 数据: 需从财务数据接口获取历史数据
- 约束: 预测期 5 年，终值用永续增长法
## Sheet 架构
- 关键假设: 所有可调参数集中管理 — WACC、增长率、利润率
- 历史数据: 3-5 年历史财报 — 营收、EBIT、折旧、资本开支
- 利润表预测: 5 年预测 — 公式引用假设表参数
- 现金流预测: FCFF 计算 — 公式引用利润表
- DCF估值: 折现计算 — WACC折现、终值、每股价值
- 敏感性分析: 双因素敏感性表 — WACC × 永续增长率
## 实施步骤
### 阶段 1: 框架搭建 (2 步)
1. **创建工作簿框架** (Sheet: 全部)
- 操作: 新建 6 个 Sheet，设置标题行和列头
- 原因: 确定数据结构后再填充
- 依赖: 无
- 风险: 低
- 验证: 6 个 Sheet 都存在且有标题
2. **填写关键假设** (Sheet: 关键假设)
- 操作: 设置 WACC、增长率、税率等默认值
- 原因: 后续所有公式引用此表，必须先建立
- 依赖: 步骤 1
- 风险: 低
- 验证: 所有参数有合理默认值
### 阶段 2: 数据获取 (1 步)
3. **获取并填入历史数据** (Sheet: 历史数据)
- 操作: 调用财务数据接口获取 3 年历史财报，写入表格
- 原因: 预测基于历史趋势
- 依赖: 步骤 1
- 风险: 中 — 接口可能无此公司数据
- 验证: 营收、EBIT、折旧、CapEx 各年数据完整
### 阶段 3: 预测建模 (2 步)
4. **建立利润表预测** (Sheet: 利润表预测)
- 操作: 用公式引用假设表的增长率，从历史数据推算 5 年预测
- 原因: 公式驱动确保参数可调
- 依赖: 步骤 2, 3
- 风险: 中 — 公式引用必须正确
- 验证: 修改假设表增长率，预测值联动变化
5. **建立现金流预测** (Sheet: 现金流预测)
- 操作: FCFF = EBIT×(1-税率) + 折旧 - CapEx - ΔNWC，全部公式引用
- 原因: DCF 核心输入
- 依赖: 步骤 4
- 风险: 中
- 验证: FCFF 各年为正且合理
### 阶段 4: 估值计算 (2 步)
6. **构建 DCF 估值** (Sheet: DCF估值)
- 操作: 折现因子、终值、企业价值、每股价值，全部公式
- 依赖: 步骤 2, 5
- 风险: 高 — 终值占比大，公式复杂
- 验证: 每股价值在合理范围内
7. **添加敏感性分析** (Sheet: 敏感性分析)
- 操作: 双因素数据表 (WACC × 永续增长率)
- 依赖: 步骤 6
- 风险: 中 — WPS 数据表功能与 Excel 有差异
- 验证: 表格随假设变化动态更新
## 公式策略
- 假设表参数: 命名范围，分析师直接修改
- 预测值: =历史数据!E列 * (1 + 假设!增长率)，公式驱动
- 终值: =末年FCFF * (1+g) / (WACC-g)，引用假设表
- 禁止: 任何预测值写死数字
## 风险与应对
- **风险**: 财务数据接口无此公司
- 应对: 用行业平均值或让用户手动填入
- **风险**: WPS 公式语法与 Excel 不同
- 应对: 使用 WPS 兼容的函数，避免 LAMBDA/SPILL 等新特性
## 验收标准
- [ ] 6 张 Sheet 结构完整
- [ ] 修改假设表任意参数，估值结果自动更新
- [ ] 敏感性分析表显示合理的估值范围
- [ ] 无硬编码数字（所有预测值由公式驱动）
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 · 235 lines · 126 tokens per session scan A f74037eb0836
planner is an agent published in the GitHub repository claude-office-skills/claude-office-plugin (9 stars, last pushed 5mo ago), licensed MIT. It adds 126 tokens to every session and 2,406 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. It is 97% identical to chart-designer, differing in 250 lines, and is treated as a copy.
Other agents, from other repositories
china-model-builder
Builds DCF, LBO, 3-statement, and comps models for Chinese equities using AkShare-sourced financial data. Use when a user requests a full financial model for an A-share stock. Not for one-off calculations.
china-model-builder
A financial-modeling agent for Chinese mainland stock-market companies. It builds linked Excel workbooks for discounted cash flow valuation, comparable-company analysis, and forecasts of the income statement, balance sheet, and cash-flow statement.
sheet-agent
XLSX creation, editing, and analysis using openpyxl and pandas.
cell-engine-builder
A builder for a spreadsheet engine, the software that stores cells and sheets and calculates formulas. It also implements built-in spreadsheet functions.
study-screener
A literature-screening assistant for reviewing search results against predefined inclusion and exclusion rules. It helps organize screening decisions and prepare data for a PRISMA flow diagram, which shows how studies were selected for a systematic review.
Demonstrate
Agent for demonstrating VS Code features.