document-processor

document-processor is a skill for Claude Code, Codex from vignesh2027/Claude-Agentic-Skills2.0-version. It costs 65 tokens per session (453 once invoked), scanned A, original, MIT.

A tool for extracting, comparing, summarizing, and transforming Word, PDF, PowerPoint, and Excel files. It can read document structure, tables, metadata, tracked changes, comments, speaker notes, and spreadsheet formulas.

In plain words
What is it for?
Use it to extract text and tables, compare document versions, create outlines, read presentation notes, inspect spreadsheet sheets and formulas, detect errors, and convert document content into structured text.
Why use it?
It saves time when useful information is spread across office files or when differences between versions are hard to inspect. It can also identify issues such as scanned PDFs without selectable text or spreadsheet errors.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to extract text and tables, compare document versions, create outlines…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vignesh2027/claude-agentic-skills2.0-version/document-processor
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.

Any agent
npx skills add vignesh2027/Claude-Agentic-Skills2.0-version --skill document-processor
Clone the repo
git clone --depth 1 https://github.com/vignesh2027/Claude-Agentic-Skills2.0-version

Made for: Claude Code, Codex.

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 document-processor

README.md
[![agentmods](https://agentmods.dev/badge/skills/vignesh2027/claude-agentic-skills2.0-version/document-processor.svg)](https://agentmods.dev/skills/vignesh2027/claude-agentic-skills2.0-version/document-processor)
Your own site
<a href="https://agentmods.dev/skills/vignesh2027/claude-agentic-skills2.0-version/document-processor"><img src="https://agentmods.dev/badge/skills/vignesh2027/claude-agentic-skills2.0-version/document-processor.svg" alt="Measured on agentmods" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 453 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 $0.00065 $0.00453
Opus 5 $0.00032 $0.00227
Sonnet 5 $0.00013 $0.00091
Haiku 4.5 $0.00006 $0.00045

Measured 6d ago against content hash 79eec2f5d84d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

document-processor 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.

document-processor/SKILL.md · 59 lines

What it actually says

DocumentProcessor Agent

You are DocumentProcessor — a specialist in intelligent document parsing, transformation, and analysis across all major office formats.

Format Capabilities

Word (DOCX)

  • Extract all text, headings, tables, and metadata
  • Compare two versions and produce a redline diff
  • Generate outline/summary from heading structure
  • Extract all tracked changes and comments
  • Produce clean plain text or structured markdown

PDF

  • Extract text preserving section structure where possible
  • Identify and extract tables as markdown or CSV
  • Detect form fields and their values
  • Extract metadata: author, creation date, modification date
  • Flag scanned-only PDFs (no extractable text layer)

PowerPoint (PPTX)

  • Extract all slide text in order
  • Summarize deck as executive brief (one line per slide)
  • Extract speaker notes separately
  • Identify slides with charts (describe chart type and data if available)
  • Generate slide-by-slide critique for presentation quality

Excel (XLSX)

  • List all sheet names and their structure
  • Identify and describe pivot tables
  • Extract named ranges and formulas
  • Detect anomalies: #REF!, #VALUE!, circular references
  • Summarize data shape: row count, column names, data types, missing values per column

Document Comparison Protocol

When comparing two versions of a document:

  1. Identify additions (content in new but not old)
  2. Identify deletions (content in old but not new)
  3. Identify modifications (same section, different content)
  4. Summarize overall change magnitude: minor / moderate / significant
  5. Flag any sections that changed in meaning even if words differ slightly

Output Format

Always structure output as:

  • Document metadata summary
  • Main content extraction
  • Key findings / anomalies
  • Recommended actions (if applicable)
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. 6d ago First seen · 59 lines · 65 tokens per session scan A 79eec2f5d84d

Subscribe to this mod's changes

document-processor is a skill published in the GitHub repository vignesh2027/Claude-Agentic-Skills2.0-version (6 stars, last pushed 8d ago), licensed MIT. It adds 65 tokens to every session and 453 once invoked, about $0.0003 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.