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 agentmods add skills/zm1990s/kb-agent/excel-live-controlnpx skills add zm1990s/kb-agent --skill excel-live-controlgit clone --depth 1 https://github.com/zm1990s/kb-agentWrote 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/zm1990s/kb-agent/excel-live-control)<a href="https://agentmods.dev/skills/zm1990s/kb-agent/excel-live-control"><img src="https://agentmods.dev/badge/skills/zm1990s/kb-agent/excel-live-control.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 | $0.00055 | $0.04763 |
| Opus 5 | $0.00028 | $0.02381 |
| Sonnet 5 | $0.00011 | $0.00953 |
| Haiku 4.5 | $0.00006 | $0.00476 |
Grade A, and why
excel-live-control 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 6d 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
100% identical to excel-live-control — 460 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 — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Excel Live Control
Inspect, edit, analyze, format, and verify the workbook in the selected live Microsoft Excel session. Use connected-document tools for workbook reads and writes; use Computer Use only for application setup, target confirmation, and focus management.
On initial entry, complete the setup gates in order before session discovery. On follow-ups, reuse only the verified target and rediscover after workbook or add-in lifecycle changes.
Resolve every referenced file relative to this skill folder. Do not load the sibling artifact skill or its artifact-tool instructions while this live route is active.
Hard Routing Rules
Use this skill only when explicitly tagged or when the request clearly targets the Microsoft Excel desktop application, an open, active, or connected workbook in Excel Desktop, a selected range in Excel Desktop, the ChatGPT add-in for Excel, or a follow-up edit on the live-control path. For generic requests such as "create a spreadsheet," "create a workbook," or "create an Excel file" without explicit targeting of the Microsoft Excel desktop application or ChatGPT add-in, use the local workbook-authoring Spreadsheets skill instead. Stay on the live-control path unless the user explicitly switches targets; keep follow-up edits on the same path.
Routing selects the execution and delivery surface only; it does not override requested workbook content or a supplied reference/template.
Setup is part of the task. Use Computer Use only for setup checks and focus management, then use connected-document tools for workbook reads and writes. If a setup gate or required live capability is unavailable, stop and use the applicable exact guidance below. Do not silently switch to artifact authoring, open an unrelated workbook, or edit workbook cells through Computer Use.
Keep user-facing language to "Microsoft Excel", "ChatGPT add-in for Excel", "open workbook", "connected Excel session", or "live Excel control"; avoid internal connector/backend names.
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 403 B
- domain_guidance/corporate_finance_fpa.md 8.8 KB
- domain_guidance/financial_models.md 16 KB
- domain_guidance/healthcare.md 4.2 KB
- domain_guidance/marketing_advertising.md 3.9 KB
- domain_guidance/scientific_research.md 2.8 KB
- features/charts.md 5.6 KB
- officejs.md 8.5 KB
- style_guidelines.md 5.3 KB
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.
- 6d ago First seen · 231 lines · 55 tokens per session scan A 994e33cf1d33
excel-live-control is a skill published in the GitHub repository zm1990s/kb-agent (5 stars, last pushed 16d ago), licensed MIT. It adds 55 tokens to every session and 4,763 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to excel-live-control, differing in 460 lines, and is treated as a copy.
Other skills, from other repositories
dcf-model
Build discounted cash flow valuation workbooks in Excel.
audit-xls
Audit a spreadsheet for formula accuracy, errors, and common mistakes. Scopes to a selected range, a single sheet, or the entire model (including financial-model integrity checks like BS balance, cash tie-out, and logic sanity). Triggers on "audit this sheet", "check my formulas", "find formula errors", "QA this…
google-drive-sheets
Find, read, export, edit, and manage the user's Google Drive, Docs, Sheets, and Slides through per-user OAuth.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
large-file-parquet-analysis-and-highlight
当Excel文件总行数超过1万行时，通过转换为Parquet格式提升读取性能，提取目标指标并计算最大值，最后将结果输出为Excel并对特定行进行高亮标注。.
excel-basic-statistics-and-routing
Skill "excel-basic-statistics-and-routing" from OpenSenseNova/SenseNova-Skills, covering skill steps, 保存区间提取与汇总结果 and 保存筛选与统计结果.