pdf

A guide for working with PDF files, which are documents designed to keep their layout across devices. It covers reading, summarising, splitting, merging, compressing, and converting them.

In plain words
What is it for?
Use it to extract information from PDFs, summarise pages, combine documents, reduce file size, or convert documents to and from PDF.
Why use it?
It provides a clear process for handling PDF tasks with the available document tools and for checking before an operation that could overwrite content.

Skill for Claude CodeCodex

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 skills/lftpadilla/agent-dev-kit/pdf
Any agent
npx skills add LFTPadilla/agent-dev-kit --skill pdf
Clone the repo
git clone --depth 1 https://github.com/LFTPadilla/agent-dev-kit

Made for: Claude Code, Codex.

Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 216 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 $0.00037 $0.00216
Opus 5 $0.00018 $0.00108
Sonnet 5 $0.00007 $0.00043
Haiku 4.5 $0.00004 $0.00022

Measured yesterday against content hash 839fd59229a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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/dev-skills/skills/pdf/SKILL.md · 31 lines

What it actually says

PDF

Use this skill when a user asks to work with a PDF or another document format that needs PDF conversion.

Preferred path

Use the environment's built-in document and PDF tooling first. Prefer:

  • reading and summarizing PDFs,
  • extracting specific pages,
  • merging PDFs,
  • compressing PDFs,
  • converting common document formats to or from PDF.

Guidance

  • If the user wants information from a PDF, inspect the file and answer directly.
  • If the user wants a document operation, use the available PDF/document toolchain instead of inventing shell pipelines.
  • Keep page references explicit when summarizing or extracting.
  • Confirm before destructive operations like overwriting or replacing a file.

Notes

  • If the environment already exposes richer built-in PDF tools, treat this skill as routing guidance, not as a custom implementation.
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 · 31 lines · 37 tokens per session scan A 839fd59229a6

Subscribe to this mod's changes

pdf is a skill published in the GitHub repository LFTPadilla/agent-dev-kit (2 stars, last pushed 4d ago), licensed MIT. It adds 37 tokens to every session and 216 once invoked, about $0.0002 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.

Related

Other skills, from other repositories