Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/TangentDomain/excel-mcp-servernpx agentmods add skills/tangentdomain/excel-mcp-server/excel-skillWrote 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/tangentdomain/excel-mcp-server/excel-skill)<a href="https://agentmods.dev/skills/tangentdomain/excel-mcp-server/excel-skill"><img src="https://agentmods.dev/badge/skills/tangentdomain/excel-mcp-server/excel-skill.svg" alt="Measured on agentmods" 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 | $0.00038 | $0.02137 |
| Opus 5 | $0.00019 | $0.01069 |
| Sonnet 5 | $0.00008 | $0.00427 |
| Haiku 4.5 | $0.00004 | $0.00214 |
Grade A, and why
excel 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Excel 配置表 Skill
游戏开发专用 Excel 配置表管理。SQL-over-Excel 引擎,26 个工具,支持高级 SQL 查询、批量操作、跨文件 JOIN。
调用方式
所有操作通过 CLI 可执行文件调用,输出 JSON。
优先使用打包二进制(无需 Python 环境):
# 打包后的独立可执行文件(ZIP 包内 bin/excel-cli.exe 或 bin/excel-cli)
excel-cli <command> [options]
回退到 Python 源码(开发环境):
python scripts/excel-cli.py <command> [options]
输出格式:{success: bool, data: Any, message: str, meta: dict},退出码 0=成功 1=失败。
核心原则:SQL 优先
优先使用 query — 所有数据查询/分析任务
- 复杂条件筛选 → WHERE, LIKE, IN, BETWEEN, 子查询
- 聚合统计 → COUNT, SUM, AVG, MAX, MIN, GROUP BY, HAVING
- 多表关联 → 5 种 JOIN,支持跨文件
- 窗口函数 → ROW_NUMBER, RANK, DENSE_RANK
- 字符串函数 → UPPER, LOWER, TRIM, LENGTH, CONCAT, REPLACE, SUBSTRING
工具选择决策树
═══ 读数据 ═══
首选:所有数据查询/分析 → query(SQL 引擎,批量分析首选)
│
├─ 已知精确坐标(如 A1:C10)────────────→ get-range
├─ 快速了解表结构(列名+类型+样本值)───→ describe-table
├─ 只需表头信息(中文+英文)───────────→ get-headers(更轻量)
├─ 定位文本位置───────────────────────→ search(返回 row/column)
├─ 跨文件搜索─────────────────────────→ search-directory
└─ 查找末行(追加数据前必用)──────────→ find-last-row
═══ 写数据(选对工具!) ═══
┌─ 批量修改多行?(改 10 行以上/按条件)──→ update-query(SQL UPDATE)
│ 需要计算表达式 → SET 血量=血量*2
│ 需要预览 → --dry-run
│
├─ 精确坐标写入(知道具体 A1:C10)───────→ update-range
│ 默认覆盖!--insert-mode 才是追加
│ 安全追加?→ 先 find-last-row → 再 update-range --insert-mode
│
├─ 按 ID 改单行────────────────────────→ upsert-row
│ 存在则更新,不存在则插入,幂等安全
│
├─ 批量插入新行────────────────────────→ insert-query(SQL INSERT)
└─ 删行?
按条件删?→ delete-query(SQL DELETE,必须 WHERE)
按行号删?→ structure delete_rows
═══ 高级脚本 ═══
循环/复杂逻辑/重复操作?→ run-python(直接执行 Python 代码)
═══ 结构操作 ═══
文件? → create-file
工作表? → list-sheets / create-sheet / delete-sheet / rename-sheet / copy-sheet
行/列? → structure(insert/delete rows+columns)
改列名? → rename-column
行高/列宽?→ set-layout
═══ 格式化 ═══
样式/合并/边框? → format-cells(字体+合并+边框+预设样式)
═══ 对比 & 备份 ═══
按 ID 对比两表? → compare-sheets
备份恢复? → backup(create/list/restore)
防错自查清单
| # | 自查问题 | 常见错误 | 正确做法 |
|---|---|---|---|
| 1 | 追加还是覆盖? | update-range 追加忘了 --insert-mode | 追加→--insert-mode+先 find-last-row;覆盖→默认 |
| 2 | 一行还是批量? | 改单行用 update-query | 单行→upsert-row;批量/条件→update-query |
| 3 | 范围含工作表名? | 多表文件 cell_range="A1:C10" 报错 | 用 "Sheet名!A1:C10" |
| 4 | SQL 类型对吗? | SELECT 传给 update-query | 查→query / 改→update-query / 增→insert-query / 删→delete-query |
| 5 | 写入后验证了? | 写完不验证 | 写入→query 验证→有备份可恢复 |
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 · 179 lines · 38 tokens per session scan A 4c2558419f22
excel is a skill published in the GitHub repository TangentDomain/excel-mcp-server (10 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 2,137 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
xlsx-engineer
You are the XLSX Engineering Specialist. You create, edit, analyze, and validate Excel spreadsheet files with professional formatting, working formulas, and zero errors.
office-router
Route Office requests into the correct xlsx, docx, or pptx workflow, while preferring Slidev for new presentation drafts unless .pptx is explicitly required.
xlsx-edit
Edit or generate xlsx workbooks using either deterministic V1 office tools or a Python workbook script when higher fidelity is needed.
calc-spreadsheets
Use when creating, opening, or editing LibreOffice Calc ODS spreadsheets, or XLSX workbooks only when Excel compatibility is explicitly required.
xlsx
Read, create, and convert Microsoft Excel (.xlsx) and CSV spreadsheets — extract sheets and tables to JSON, build workbooks from JSON/CSV, and export to PDF.
bilig-xlsx-formula-recalc
Recalculate XLSX formula outputs in Node.js after cell edits without opening Excel, LibreOffice, or browser automation.