A Python library that extracts the structure and meaning of Excel workbooks. Excel workbooks are spreadsheet files that can contain cells, tables, charts, drawings, formatting, and print settings.

Use it to extract cells, links, tables, shapes, arrows, SmartArt, charts, colors, print areas, and page breaks. It can process individual files or directories and output JSON, YAML, or TOON when supported.

It turns complex spreadsheet contents into structured data that other software, including language models, can process more easily. It also makes extraction fallbacks visible through logging.

overview — Agent by harumiWeb

Install

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.

agentmods

npx agentmods add agents/harumiweb/exstruct/overview

Clone the repo

git clone --depth 1 https://github.com/harumiWeb/exstruct

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 384 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00000	$0.00384
Opus 5	$0.00000	$0.00192
Sonnet 5	$0.00000	$0.00077
Haiku 4.5	$0.00000	$0.00038

Measured yesterday against content hash 2ce278c81458, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

overview 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 yesterday.

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.

dev-docs/agents/overview.md · 45 lines

What it actually says

ExStruct - Excel structure extraction engine overview

ExStruct is a Python library that extracts semantic structure from Excel workbooks. It combines openpyxl, Excel COM (xlwings), and a LibreOffice backend to generate structured data that LLMs can work with easily.

Features

Unifies the extraction flow with a pipeline-oriented design
Switches extraction granularity by mode (light / libreoffice / standard / verbose)
Abstracts openpyxl / COM / LibreOffice backends
Supports JSON / YAML / TOON output when dependencies are installed
Supports print_areas and auto_page_breaks export
Makes fallback reasons visible through unified logging

Extraction targets

Cells (values / links / coordinates)
Tables (candidate ranges)
Shapes / Arrows / SmartArt (position / text / arrows / layout)
Charts (series / axes / type / title)
Print Areas / Auto Page Breaks
Colors Map (including conditional formatting)

Usage examples at a glance

Use extract(path, mode="standard") to obtain WorkbookData
Use process_excel for file output or directory output
Use the CLI as exstruct file.xlsx --format json

Directory layout at a glance

docs/                 public documentation
dev-docs/             internal documentation
src/exstruct/
  core/               extraction pipeline and backends
  models/             Pydantic models
  io/                 JSON/YAML/TOON output
  render/             PDF/PNG output
  cli/                CLI
tests/                tests

AI agents should read docs/ as the public contract and use dev-docs/specs/ and dev-docs/adr/ to fill in internal behavior.

Changes

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.

yesterday First seen · 45 lines · 0 tokens per session scan A 2ce278c81458

Subscribe to this mod's changes

overview is an agent published in the GitHub repository harumiWeb/exstruct (195 stars, last pushed 2mo ago), licensed BSD-3-Clause. It costs nothing until one of its globs matches a file; then it loads 384 tokens. 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 2026-08-30.

Backend and APIs Data and AI Documents LLM RAG data-ex document-ai excel structured-data

overview

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

ExStruct - Excel structure extraction engine overview

Features

Extraction targets

Usage examples at a glance

Directory layout at a glance

What this file has done since we first saw it

Other agents, from other repositories

ai-chat

ai-doc-bridge

licensing-billing

version-control

office-addin

sidebar-shell