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 instructions/passerbyflutter/libreoffice-mcp-tools/copilot-instructionsgit clone --depth 1 https://github.com/passerbyflutter/libreoffice-mcp-toolsWrote 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/passerbyflutter/libreoffice-mcp-tools/copilot-instructions)<a href="https://agentmods.dev/instructions/passerbyflutter/libreoffice-mcp-tools/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/passerbyflutter/libreoffice-mcp-tools/copilot-instructions.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 | $0.02788 | $0.02788 |
| Opus 5 | $0.01394 | $0.01394 |
| Sonnet 5 | $0.00558 | $0.00558 |
| Haiku 4.5 | $0.00279 | $0.00279 |
Grade A, and why
libreoffice-mcp-tools copilot-instructions.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 5d 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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LibreOffice MCP Tools — Copilot Instructions
Project Overview
A TypeScript MCP (Model Context Protocol) server that lets AI/LLM agents read, write, and edit Office documents (DOCX, DOC, XLSX, XLS, PPTX, PPT, ODF, PDF, CSV, TXT) via LibreOffice. Designed to minimize token usage through structured, range-based, outline-first document access.
Reference architecture: chrome-devtools-mcp
Architecture Principles
Token Efficiency (Core Design Goal)
- Outline-first —
document_get_outlinereturns headings/sheet names/slide titles BEFORE content - Range-based access —
document_read_rangewith paragraph/row/slide offsets, never dump whole doc - Pagination — ALL list tools support
limit+offsetparams - Structured JSON — spreadsheet data as
{headers: string[], rows: any[][]}not raw CSV - Markdown output — text documents rendered as compact markdown (headings → #, bold → **, etc.)
- Metadata-first — word count, page count, sheet names BEFORE reading content
Technology Stack
- Language: TypeScript, ESM modules (
"type": "module"in package.json) - MCP SDK:
@modelcontextprotocol/sdk - Schema validation:
zod - Build:
tsc(TypeScript compiler) - Native document parsers (fast, no LibreOffice needed for reads):
- DOCX/DOTX:
mammothfor text extraction,docxfor writing - XLSX/XLS/ODS/CSV:
xlsx(SheetJS) - PPTX:
jszip+ custom XML parser
- DOCX/DOTX:
- LibreOffice CLI (
soffice --headless) for:- Converting legacy binary formats (DOC→DOCX, XLS→XLSX, PPT→PPTX) before parsing
- Exporting to PDF, HTML, etc.
- Writing to ODF formats
- Complex write operations on any format
File Format Support
| Format | Extensions | Read | Write | Method |
|---|---|---|---|---|
| Word 2007+ | .docx, .dotx |
✅ | ✅ | Native (mammoth/docx) |
| Word 97-2003 | .doc, .dot |
✅ | ✅ | LibreOffice → DOCX bridge |
| Excel 2007+ | .xlsx, .xlsm |
✅ | ✅ | Native (SheetJS) |
| Excel 97-2003 | .xls |
✅ | ✅ | LibreOffice → XLSX bridge |
| PowerPoint 2007+ | .pptx |
✅ | ✅ | Native (JSZip XML) |
| PowerPoint 97-2003 | .ppt |
✅ | ✅ | LibreOffice → PPTX bridge |
| OpenDocument Text | .odt |
✅ | ✅ | LibreOffice bridge |
| OpenDocument Spreadsheet | .ods |
✅ | ✅ | LibreOffice bridge |
| OpenDocument Presentation | .odp |
✅ | ✅ | LibreOffice bridge |
| Rich Text Format | .rtf |
✅ | ✅ | LibreOffice bridge |
| CSV | .csv |
✅ | ✅ | Native (SheetJS/built-in) |
.pdf |
✅ (text) | ❌ | LibreOffice CLI | |
| Plain text | .txt |
✅ | ✅ | Native |
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.
- 5d ago First seen · 214 lines · 2,788 tokens per session scan A 4b26f8dfd659
libreoffice-mcp-tools copilot-instructions.md is an instructions file published in the GitHub repository passerbyflutter/libreoffice-mcp-tools (0 stars, last pushed 4mo ago), licensed MIT. It adds 2,788 tokens to every session, about $0.0139 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
gpt-rag-ingestion azure-boundaries.instructions.md
Instructions for Azure/gpt-rag-ingestion, a project described as: The GPT-RAG Data Ingestion service automates processing of diverse documents—PDFs, images, spreadsheets, transcripts, and SharePoint—readying them for Azure AI Search. It applies smart chunking, generates text and image embeddings, and enables rich…
document-SKILLs AGENTS.md
AGENTS.md instructions for appautomaton/document-SKILLs, covering document skills, python, python packages, node.js and system tools (brew or apt-get).
tablepack AGENTS.md
Instructions for kujiangmudao/tablepack, covering two user paths, multimodal requirement, environment, hard requirements (never skip) and qc checklist (every pdf).
cdxml-toolkit-community CLAUDE.md
Claude Code instructions for ZiChenWang114514/cdxml-toolkit-community, covering cdxml-toolkit — agent reference, what this is, key rules, mcp server and tool reference.
mcp-server-anydoc AGENTS.md
AGENTS.md instructions for ofershap/mcp-server-anydoc, covering mcp-server-anydoc, when to use, install (agent instructions), tools and limits.
bookkeeper-starter CLAUDE.md
Instructions for audrey-560/bookkeeper-starter, covering bookkeeper — ai bookkeeping os (multi-client), layout, key invariants (do not break), skills (user-invoked) and per-client facts.