process-pdf

A command that reads a PDF from a web address or local file and turns its contents into a structured knowledge-graph note. A knowledge graph links related facts and questions.

In plain words
What is it for?
Use it to process research papers, guides, reports, or technical documents and create notes containing metadata, key questions, and synthesized answers.
Why use it?
It combines PDF extraction with organized synthesis, so important information is easier to search and connect later.

Command

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 commands/witt3rd/claude-plugins/process-pdf
Clone the repo
git clone --depth 1 https://github.com/witt3rd/claude-plugins
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 923 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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00923
Opus 5 $0.00000 $0.00462
Sonnet 5 $0.00000 $0.00185
Haiku 4.5 $0.00000 $0.00092

Measured yesterday against content hash 6bbdb4de484a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

process-pdf 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.

plugins/azkg/commands/process-pdf.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Process PDF and Create Note

Extract content from a PDF (URL or local file) and create a comprehensive knowledge graph note using question-oriented content synthesis.

Usage

/process-pdf <pdf_url_or_path> [note_filename]

Process

Step 1: Content Acquisition (PDF-Specific)

Access PDF content:

  • If URL: Use mcp__firecrawl__firecrawl_scrape with PDF parser
  • If local file: Use Read tool (supports PDF)
  • Extract text, structure, and key information

Analyze document metadata:

  • Extract title, authors, publication date if available
  • Identify document type (academic paper, guide, report, technical spec, etc.)
  • Note any special structure (abstract, sections, references)

Read the extracted content:

  • This is the raw content to be synthesized

Step 2: Universal Content Processing

Follow the shared content synthesis pipeline documented in _shared_content_synthesis.md:

  1. Apply Question-Oriented Content Synthesis

    • Phase 1: Central Question Discovery
    • Phase 2: Domain Question Extraction
    • Phase 3: Specific and Atomic Question Decomposition
    • Phase 4: Progressive Answer Development
  2. Generate note structure and metadata

    • Determine filename based on central question
    • Assign 3-6 tags mixing dimensions
    • Create PDF-specific YAML frontmatter
  3. MOC Integration

    • Read TOPICS.md to understand MOC structure
    • Identify appropriate MOC(s) for this note
    • Update MOC file(s) with wikilink and description
  4. Relationship Discovery

    • Search for related notes in knowledge graph
    • Establish bidirectional relationships
    • Update related notes

PDF-Specific Note Structure

---
tags: [domain, topic, content-type]
source: <pdf_url_or_path>
document_title: "<title>"
authors: "<authors if applicable>"
date_added: <ISO_date>
---

# Note Title (Based on Central Question)

## Central Question

**Question**: [The single overarching question the document addresses]

**Executive Summary**: 2-3 paragraphs previewing key insights and how the document resolves the central question.

## Part I: [Domain Question 1]

### [Specific Question 1.1]

**Question**: [Clear, specific question from this section]

**Answer**: [Comprehensive response including:
- Direct answer to the question
- Supporting evidence from document (specific quotes, examples, data with page numbers)
- Technical details and concrete information
- Implications and connections to broader themes]

### [Specific Question 1.2]

**Question**: [Next specific question]

**Answer**: [Evidence-based response...]

## Part II: [Domain Question 2]

### [Specific Question 2.1]

**Question**: [Clear question]

**Answer**: [Comprehensive response with document evidence...]

[Continue with additional parts and sections as needed]

## Resolution: [Answer to Central Question]

Synthesize domain insights to definitively resolve the central question posed at the beginning.

## Related Concepts

### Prerequisites
- [[prerequisite]] - Why needed first

### Related Topics
- [[related]] - Connection explanation

### Extends
- [[base_concept]] - What this builds upon

## References

- [Document Title](<source>) - Brief description
- Authors: <authors>
- Accessed: <date>

Read the full file on GitHub · 136 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. yesterday First seen · 136 lines · 0 tokens per session scan A 6bbdb4de484a

Subscribe to this mod's changes

process-pdf is a command published in the GitHub repository witt3rd/claude-plugins (2 stars, last pushed 10mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 923 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 2026-08-31.