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/kujiangmudao/tablepack/agents-mdgit clone --depth 1 https://github.com/kujiangmudao/tablepackWhat 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 | $0.01026 | $0.01026 |
| Opus 5 | $0.00513 | $0.00513 |
| Sonnet 5 | $0.00205 | $0.00205 |
| Haiku 4.5 | $0.00103 | $0.00103 |
Grade A, and why
tablepack AGENTS.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 2d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TablePack (pdf-excel) — Agent / operator rules (must follow)
Product name: TablePack. Turns PDF tables → Excel packages using MinerU.
When the user asks to convert PDFs, always follow this file + skills/pdf-table-to-excel/SKILL.md.
Two user paths
| User | What to do |
|---|---|
| Already has MinerU | Use this repo + skill; ensure mineru on PATH or config.yaml → mineru_bin |
| No MinerU yet | Run scripts/install_mineru.ps1 (Windows) or scripts/install_mineru.sh (Unix), activate .venv-mineru, then same skill/CLI. See docs/INSTALL.md |
Multimodal requirement
- Auto pipeline (
python -m pdf_excel): text/CLI is enough. - Quality control / sheet repair: requires a vision-capable model that can open
原始表格/screenshots (or PDF pages). - Text-only models: may run packaging, but must not claim visual QC was done.
Environment
Resolve paths via (in order): CLI flags → env vars → config.yaml → defaults.
| Item | Default / note |
|---|---|
| Source PDFs | pdf/ |
| Output packages | output/ |
| MinerU cache | work/mineru_raw/ |
| MinerU CLI | MINERU_BIN or config.yaml → mineru_bin (auto-discover if on PATH) |
| Backend | pipeline by default; tables on (-t true); language ch unless configured |
| Code entry | python -m pdf_excel or convert_pipeline.py |
Local machine tip: Path B writes config.yaml; or copy config.example.yaml (gitignored).
Hard requirements (never skip)
- MinerU is the primary parser (helpers OK for repair only).
- One PDF → one Excel, same basename.
- All tables of one PDF in one workbook as different sheets.
- Package structure:
output/<PDF_STEM>/
├── <PDF_STEM>.xlsx
├── 原始表格/ # table screenshots (required)
├── 图片/ # non-table figures
└── 转换说明.md # success
or 问题说明.md # fail / partial fail
- Strict visual QC after auto convert: compare each sheet vs
原始表格/(or PDF). Fix misaligned columns, bad headers, merges, suspicious numbers immediately. - Unrecoverable tables: write markdown explaining why — never fabricate data.
- PDFs with no tables: still emit folder + placeholder xlsx +
问题说明.md+ keep figures when possible.
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.
- 2d ago First seen · 84 lines · 1,026 tokens per session scan A 30fd9a1311a3
tablepack AGENTS.md is an instructions file published in the GitHub repository kujiangmudao/tablepack (5 stars, last pushed 19d ago), licensed MIT. It adds 1,026 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
mcp-server-excel readme-management.instructions.md
Instructions for sbroenne/mcp-server-excel, covering readme management - quick reference, core entry documents, feature documentation, critical rules and tool & action counts must match.
mcp-server-excel extension-development.instructions.md
Instructions for sbroenne/mcp-server-excel, covering vs code extension development instructions, extension overview, changelog and changesets (critical), version management and automatic version management (unified release workflow).
mcp-server-excel copilot-instructions.md
Instructions for sbroenne/mcp-server-excel, covering github copilot instructions - excelmcp, repository map, environment, working rules and build and validation.
mcp-server-excel excel-connection-types-guide.instructions.md
Instructions for sbroenne/mcp-server-excel, covering excel connection types - llm quick reference, critical: loadto operation limitations, connection action compatibility, decision tree: connection vs power query and recommended workflows.
mcp-server-excel excel-com-interop.instructions.md
Instructions for sbroenne/mcp-server-excel, covering excel com interop, api selection, batch execution and exceptions, com lifetime and excel application state.
mcp-server-excel mcp-server-guide.instructions.md
Instructions for sbroenne/mcp-server-excel, covering mcp server development, tool pattern, errors and json, schema and descriptions and cross-surface verification.