Borrowing it
Nothing to install: this file belongs to TangentDomain/excel-mcp-server. 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/TangentDomain/excel-mcp-server/main/CLAUDE.mdgit clone --depth 1 https://github.com/TangentDomain/excel-mcp-serverWrote 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/tangentdomain/excel-mcp-server/claude-md)<a href="https://agentmods.dev/instructions/tangentdomain/excel-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/tangentdomain/excel-mcp-server/claude-md.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 | $0.01013 | $0.01013 |
| Opus 5 | $0.00507 | $0.00507 |
| Sonnet 5 | $0.00203 | $0.00203 |
| Haiku 4.5 | $0.00101 | $0.00101 |
Grade A, and why
excel-mcp-server CLAUDE.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 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Excel MCP Server
游戏开发专用 Excel 配置表 MCP 服务器。SQL-over-Excel 引擎,35 个工具,支持高级 SQL 查询、批量操作、跨文件 JOIN。
技术栈
- Python 3.10+ / FastMCP / openpyxl / sqlglot
- 测试: pytest + pytest-timeout + pytest-xdist
- Lint: ruff (format + check)
- 版本: 1.16.0
目录结构
src/excel_mcp_server_fastmcp/ # 主包
api/ # SQL 执行引擎(query/update/insert/delete)
core/ # Excel 操作核心(read/write/backup)
models/ # 数据模型
utils/ # 工具函数
calibrator/ # SQLite 交叉校验工具
verification/ # baseline 驱动验证
tests/
invariants/ # 不变量测试(INV-1~32)
test_data/ # 测试数据
scripts/
pre_commit_check.sh # 提交前检查
docs/
SQL_PRINCIPLES.md # SQL 标准遵循原则
MCP 工具 → Python API 映射
| MCP 工具 | Python API |
|---|---|
| excel_query | execute_advanced_sql_query |
| excel_update_query | execute_advanced_update_query |
| excel_insert_query | execute_advanced_insert_query |
| excel_delete_query | execute_advanced_delete_query |
SQL 核心原则
只支持 SQL 标准支持的功能。 SQLite 3.x 为真值来源,calibrator 交叉校验。
- 支持: 窗口函数、JOIN、聚合、CTE、子查询
- 不支持: WHERE 引用窗口函数别名、SELECT 别名在 WHERE 中
- SQL 执行顺序: FROM → JOIN → WHERE → GROUP BY → HAVING → 窗口函数 → SELECT → ORDER BY → LIMIT
API 契约
所有工具返回 {success: bool, data: list, message: str}。
success=False时data为空列表,message非空且不含堆栈affected_rows必须精确等于实际变更行数
不变量体系
32 条不变量,三层分层。详见 .claude/skills/INVARIANT-DRIVEN-DEV.md。
L1 外部真值(4条): INV-1 结果结构 / INV-2 SQL对齐 / INV-3 文件完整 / INV-4 行数守恒
L2 架构原则(5条): INV-5~9 失败安全/错误分类/幂等读取/LIMIT/聚合语义
L3 具体不变量(23条): INV-10~32 窗口函数/空表/写操作/SQL边界
判据执行
python -m pytest tests/invariants/ -q # 全量(<60s)
python -m pytest tests/invariants/ -k "smoke" # 烟雾(<10s)
当前状态: 154 passed, 3 skipped, 收敛评级 C。
代码规范
- 向量化优先:
pd.Series而非逐行 - 分发表用
tuple不用frozenset - 异常回退: 类型转换失败时逐行 fallback
- 版本更新:
__init__.py+pyproject.toml同步
部署检查
ruff check src/ tests/ && ruff format --check src/ tests/
python -m pytest tests/invariants/ -q --tb=short --timeout=30
Enforcement
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 · 96 lines · 1,013 tokens per session scan A e06ee1cf9a2b
excel-mcp-server CLAUDE.md is an instructions file published in the GitHub repository TangentDomain/excel-mcp-server (10 stars, last pushed 1mo ago), licensed MIT. It adds 1,013 tokens to every session, about $0.0051 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).
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.
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.