reducto-document-parsing

reducto-document-parsing is a skill for Claude Code from reductoai/claude-plugins. It costs 76 tokens per session (1,457 once invoked), scanned A, original, MIT.

Instructions for using the Reducto command-line tool to read and edit documents. It can turn PDFs, images, office files, and spreadsheets into Markdown, extract structured data using a JSON schema, and apply natural-language edits.

In plain words
What is it for?
Use it to parse document files, extract fields from invoices or forms, convert documents to Markdown, and edit document content through commands.
Why use it?
It removes the need to manually copy information from documents or build separate parsing steps for each supported file type. Login is required before using its commands.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is uvx --from reducto-cli reducto parse ./documents/.

Part of the reducto-cli plugin — 1 skill shipped together

Good fit Use it to parse document files, extract fields from invoices or forms, convert documents to Markdown, and edit document content through commands.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/reductoai/claude-plugins
agentmods
npx agentmods add skills/reductoai/claude-plugins/reducto-document-parsing

Made for: Claude Code.

Or install reducto-cli, the plugin that ships this one along with the rest of its 1 skill.

Wrote 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.

agentmods badge for reducto-document-parsing

README.md
[![agentmods](https://agentmods.dev/badge/skills/reductoai/claude-plugins/reducto-document-parsing/github.svg)](https://agentmods.dev/skills/reductoai/claude-plugins/reducto-document-parsing)
Your own site
<a href="https://agentmods.dev/skills/reductoai/claude-plugins/reducto-document-parsing"><img src="https://agentmods.dev/badge/skills/reductoai/claude-plugins/reducto-document-parsing/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for reducto-document-parsing

Your own site · 80×15
<a href="https://agentmods.dev/skills/reductoai/claude-plugins/reducto-document-parsing"><img src="https://agentmods.dev/badge/skills/reductoai/claude-plugins/reducto-document-parsing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,457 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00076 $0.01457
Opus 5 $0.00038 $0.00728
Sonnet 5 $0.00015 $0.00291
Haiku 4.5 $0.00008 $0.00146

Measured 9d ago against content hash 51ca8332ca72, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

reducto-document-parsing 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 9d 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.

plugins/reducto-cli/skills/reducto-document-parsing/SKILL.md · 205 lines

How it starts

The opening of the file, as written. The whole thing — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reducto CLI - Document Processing

This skill provides guidance for using the Reducto CLI to parse, extract, and edit documents.

Overview

Reducto CLI is a powerful document processing tool that uses AI to:

  • Parse documents into clean Markdown with metadata
  • Extract structured data according to JSON schemas
  • Edit documents using natural language instructions

Prerequisites

Before using reducto commands, ensure the user is authenticated:

uvx --from reducto-cli reducto login

This opens a browser for device code authentication.

Supported File Types

  • PDF: .pdf
  • Images: .png, .jpg, .jpeg
  • Office documents: .doc, .docx, .ppt, .pptx
  • Spreadsheets: .xls, .xlsx

Commands

1. Parse Documents

Convert documents to Markdown with YAML front matter containing metadata.

Basic usage:

uvx --from reducto-cli reducto parse path/to/document.pdf

Parse entire directory:

uvx --from reducto-cli reducto parse ./documents/

Output: Creates <filename>.parse.md files with parsed content.

Parse Options
Flag Description
--agentic Enables all agentic options for tables, text, and figures. Increases accuracy but also increases latency. Use for complex layouts or when maximum accuracy is needed.
--change-tracking Returns <s> tags around strikethrough text, <u> tags around underlined text, and <change> tags around colored adjacent strikethrough and underlined text. Useful for documents with revision history.
--highlights Include highlighted text in output
--hyperlinks Include embedded hyperlinks
--comments Include document comments

Examples:

# Maximum accuracy (slower)
uvx --from reducto-cli reducto parse document.pdf --agentic

# Contract with change tracking
uvx --from reducto-cli reducto parse contract.pdf --change-tracking

# All metadata
uvx --from reducto-cli reducto parse document.pdf --hyperlinks --comments --highlights

# Combined flags
uvx --from reducto-cli reducto parse legal_doc.pdf --agentic --change-tracking --comments

Read the full file on GitHub · 205 lines

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.

  1. 9d ago First seen · 205 lines · 76 tokens per session scan A 51ca8332ca72

Subscribe to this mod's changes

reducto-document-parsing is a skill published in the GitHub repository reductoai/claude-plugins (2 stars, last pushed 3mo ago), licensed MIT. It adds 76 tokens to every session and 1,457 once invoked, about $0.0004 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.