pdf-workflow

pdf-workflow is a skill for Claude Code from EigenCharlie/pdf-toolkit-mcp. It costs 83 tokens per session (857 once invoked), scanned A, original, MIT.

A guide for running several PDF operations in sequence with the pdf-toolkit MCP server. PDF means a fixed-layout document format; the workflows cover tasks such as OCR, which turns scanned pages into searchable text.

In plain words
What is it for?
Combining, converting, compressing, securing, watermarking, rotating, numbering, extracting, repairing, and OCR-processing PDFs.
Why use it?
It organizes jobs that need multiple operations, such as merging and compressing files or repairing, reading, and converting a scan.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code.

Part of the pdf-toolkit plugin — 1 skill, 2 MCP servers shipped together

Good fit Combining, converting, compressing, securing, watermarking, rotating, numbering, extracting, repairing, and OCR-processing PDFs.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/eigencharlie/pdf-toolkit-mcp/pdf-workflow
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 EigenCharlie/pdf-toolkit-mcp --skill pdf-workflow
Clone the repo
git clone --depth 1 https://github.com/EigenCharlie/pdf-toolkit-mcp

Made for: Claude Code.

Or install pdf-toolkit, the plugin that ships this one along with the rest of its 1 skill, 2 MCP servers.

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 pdf-workflow

README.md
[![agentmods](https://agentmods.dev/badge/skills/eigencharlie/pdf-toolkit-mcp/pdf-workflow/github.svg)](https://agentmods.dev/skills/eigencharlie/pdf-toolkit-mcp/pdf-workflow)
Your own site
<a href="https://agentmods.dev/skills/eigencharlie/pdf-toolkit-mcp/pdf-workflow"><img src="https://agentmods.dev/badge/skills/eigencharlie/pdf-toolkit-mcp/pdf-workflow/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 pdf-workflow

Your own site · 80×15
<a href="https://agentmods.dev/skills/eigencharlie/pdf-toolkit-mcp/pdf-workflow"><img src="https://agentmods.dev/badge/skills/eigencharlie/pdf-toolkit-mcp/pdf-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 857 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 $0.00083 $0.00857
Opus 5 $0.00042 $0.00428
Sonnet 5 $0.00017 $0.00171
Haiku 4.5 $0.00008 $0.00086

Measured 9d ago against content hash f43260b9cec7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

pdf-workflow 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.

skills/pdf-workflow/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PDF Workflow

Orchestrates common multi-step PDF pipelines using the pdf-toolkit MCP server. Each workflow calls the 18 MCP tools in a specific order.

When to use

  • Assemble: merge many PDFs then optimize the result
  • Convert + secure: turn an Office doc into a watermarked, password-protected PDF
  • Scan cleanup: repair a broken scan, OCR it, add page numbers
  • Prep for email: aggressively compress + lock with a password
  • Extract + OCR: pull specific pages then OCR them into Word

Assumed tools

  • merge_pdf, split_pdf, compress_pdf
  • pdf_to_word, pdf_to_excel, pdf_to_powerpoint, pdf_to_jpg
  • office_to_pdf, html_to_pdf, image_to_pdf
  • rotate_pdf, add_page_numbers, extract_pdf_pages
  • unlock_pdf, protect_pdf, repair_pdf
  • add_watermark, ocr_pdf

All tools accept input_file or input_files (absolute or CWD-relative paths) and an optional output_path.

Workflow 1: Assemble

Goal: combine N PDFs into one, then shrink, and optionally protect.

  1. Call merge_pdf(input_files=[...], output_path="<tmp>/merged.pdf").
  2. Call compress_pdf(input_file="<tmp>/merged.pdf", compression_level="recommended", output_path=<final>).
  3. Optionally call protect_pdf(input_file=<final>, password=<user-provided>).

Workflow 2: Convert and secure

Goal: turn a Word/Excel/PPT file into a watermarked, password-protected PDF.

  1. office_to_pdf(input_file=<file>) → <raw.pdf>.
  2. add_watermark(input_file=<raw.pdf>, mode="text", text="CONFIDENTIAL") → <wm.pdf>.
  3. protect_pdf(input_file=<wm.pdf>, password=<pw>) → final.

Workflow 3: Extract and OCR

Goal: pull specific pages from a PDF, OCR them, then convert to Word.

  1. extract_pdf_pages(input_file=<src>, pages="3,5-9") → <sub.pdf>.
  2. ocr_pdf(input_file=<sub.pdf>, languages=["eng"]) → <ocr.pdf>. (warn: slow for many pages)
  3. pdf_to_word(input_file=<ocr.pdf>) → final.docx.

Workflow 4: Prep for email

Goal: shrink a PDF aggressively and lock it behind a password.

  1. compress_pdf(input_file=<src>, compression_level="extreme") → <small.pdf>.
  2. protect_pdf(input_file=<small.pdf>, password=<pw>) → final.

Read the full file on GitHub · 66 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 · 66 lines · 83 tokens per session scan A f43260b9cec7

Subscribe to this mod's changes

pdf-workflow is a skill published in the GitHub repository EigenCharlie/pdf-toolkit-mcp (1 stars, last pushed 4mo ago), licensed MIT. It adds 83 tokens to every session and 857 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.