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.
npx agentmods add skills/vladkesler/initrunner/document-comparisonnpx skills add vladkesler/initrunner --skill document-comparisongit clone --depth 1 https://github.com/vladkesler/initrunnerWrote 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.
[](https://agentmods.dev/skills/vladkesler/initrunner/document-comparison)<a href="https://agentmods.dev/skills/vladkesler/initrunner/document-comparison"><img src="https://agentmods.dev/badge/skills/vladkesler/initrunner/document-comparison.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00028 | $0.00688 |
| Opus 5 | $0.00014 | $0.00344 |
| Sonnet 5 | $0.00006 | $0.00138 |
| Haiku 4.5 | $0.00003 | $0.00069 |
Grade A, and why
document-comparison 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Document comparison skill.
When to activate
Use this skill when the user asks you to:
- Compare two or more PDF documents
- Find differences between document versions
- Compare terms, clauses, or sections across documents
- Build a side-by-side comparison of document contents
Methodology
1. Identify the documents
List available files and confirm which documents to compare. If the user is vague ("compare the two contracts"), list the PDFs and ask which ones they mean.
2. Extract metadata for both documents
Call extract_pdf_metadata on each document to get:
- Page count
- Title and author
- Creation and modification dates
This helps you understand the scope and identify if one is a revision of the other (same title, different dates).
3. Determine comparison dimensions
Use the think tool to decide what to compare. Common dimensions:
- Structure: sections, headings, page count
- Content: specific clauses, terms, definitions
- Numbers: financial figures, dates, quantities
- Coverage: topics present in one but missing in the other
Ask the user what matters most if it is not clear from context.
4. Targeted extraction
Extract the relevant sections from each document. Use page ranges to keep extractions focused:
- For structural comparison: extract the first 2-3 pages (table of contents, introduction) from each
- For clause comparison: extract the specific pages containing the target clauses
- For full comparison of short docs (< 20 pages): extract all
5. Build the comparison matrix
Use the think tool to construct a comparison. Structure it as:
| Dimension | Document A (page) | Document B (page) | Difference |
|----------------|--------------------|--------------------|------------|
| Term length | 12 months (p.3) | 24 months (p.4) | B is 2x |
| Payment terms | Net 30 (p.5) | Net 60 (p.5) | B is longer |
For numerical differences, use the calculator to compute deltas and percentages.
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.
- 3d ago First seen · 94 lines · 28 tokens per session scan A 6105127fb137
document-comparison is a skill published in the GitHub repository vladkesler/initrunner (41 stars, last pushed 5d ago), licensed Apache-2.0. It adds 28 tokens to every session and 688 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
hive.pdf
Read, write, merge, split, rotate, watermark, encrypt, and OCR PDF files using Python (pypdf, pdfplumber, reportlab, pypdfium2) and command-line tools (poppler-utils, qpdf). Use when the user asks to extract text/tables/images from a PDF, create or modify a PDF, combine or split PDFs, OCR a scanned PDF…
document-processor
Activates DocumentProcessor for intelligent processing of Word, PDF, PowerPoint, and Excel files. Use when you need to extract, summarize, redline, or transform documents in any Office format — compare versions, extract tables, generate document outlines, convert formats, or produce structured data from unstructured…
files
Работа с файлами: поиск, чтение, запись, копирование, PDF, отправка.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
filex
Parse workspace files, HTTP(S) file URLs, or supported source URLs such as YouTube into Markdown, inspect source routing, and inspect resumable PDF batch status with the FileX CLI inside an AWorld sandbox. Use for reading, extracting, transcribing, inspecting, summarizing, or answering questions about PDF, Word…
citra
Skill "citra" from SylphxAI/pdf-reader-mcp, covering citra — pdf evidence for agents, install, or, tools and sdk.