A tool for reading, creating, filling, and reformatting PDF files, which are fixed-layout documents.

Use it to read PDFs, extract information, create documents, fill form fields, or produce a reformatted PDF.

It supports common PDF work without treating the document as ordinary text or code.

pdf — Skill for Claude Code and Codex by IceWhaleTech

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 IceWhaleTech/ZimaOS-Blue --skill pdf

Clone the repo

git clone --depth 1 https://github.com/IceWhaleTech/ZimaOS-Blue

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/icewhaletech/zimaos-blue/pdf/github.svg)](https://agentmods.dev/skills/icewhaletech/zimaos-blue/pdf)

Your own site

<a href="https://agentmods.dev/skills/icewhaletech/zimaos-blue/pdf"><img src="https://agentmods.dev/badge/skills/icewhaletech/zimaos-blue/pdf/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/icewhaletech/zimaos-blue/pdf"><img src="https://agentmods.dev/badge/skills/icewhaletech/zimaos-blue/pdf.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,528 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.

Model	Per session	Once invoked
Fable 5.1	$0.00037	$0.01528
Opus 5	$0.00018	$0.00764
Sonnet 5	$0.00007	$0.00306
Haiku 4.5	$0.00004	$0.00153

Measured 10d ago against content hash 1accd100390d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, 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 10d 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.

assets/skills/pdf/SKILL.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PDF

Use this skill when the .pdf file is the source of truth and the task needs PDF-native reading, form filling, or final-document output.

Common Actions

blue pdf action=read path=reports/brief.pdf
blue pdf action=read path=reports/brief.pdf read_mode=fast
blue pdf action=info path=reports/brief.pdf
blue pdf action=create path=reports/brief.pdf title="Launch Brief" content="# Summary"
blue pdf action=fill path=forms/intake.pdf output_path=forms/intake_filled.pdf fields='{"name":"Orca"}'
blue pdf action=reformat input_path=reports/source.pdf output_path=reports/source_clean.pdf

Parameters (Practical Reference)

Common read parameters (action=read):

path / pdf: Path or URL to a single PDF (workspace path preferred).
pdfs / paths: Multiple PDFs (deduped, capped).
read_mode: Preset for speed vs coverage (full / auto / fast).
purpose (Default: summarize): High-level intent hint that selects sensible defaults when you did not explicitly set read_mode / max_pages / max_chars / include flags. Values: summarize / facts / skim.
pages: Page selection like "1,3-5" or [1,3,4,5]. Use this when you know where the answer is.
max_pages: Hard cap on number of pages returned.
max_chars: Hard cap on characters returned.
include_markdown: Include a layout-aware Markdown view when possible.
include_outline: Include bookmarks/outline when available (useful for navigation).
include_pages: Include per-page outputs (helps citations and page-specific extraction).
include_layout: Include semantic blocks/tables when available (more expensive).
fallback_mode: How to handle scanned pages:
- auto (default): try text extraction; fall back to OCR/vision when needed
- text_only: disable OCR + vision (fastest; fails on scans)
- ocr_only: force OCR (better for scans; slower)
- vision_only: force vision OCR (slowest; last resort)

Create/reformat/fill parameters:

action=create: path (output), plus title/subtitle/content (Markdown-like).
action=reformat: input_path (source PDF), output_path (destination PDF).
action=fill: path (source PDF), fields (map), and output_path (destination PDF).

Read the full file on GitHub · 121 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.

10d ago First seen · 121 lines · 37 tokens per session scan A 1accd100390d

Subscribe to this mod's changes

pdf is a skill published in the GitHub repository IceWhaleTech/ZimaOS-Blue (25 stars, last pushed 4mo ago), licensed MIT. It adds 37 tokens to every session and 1,528 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 2026-08-30.

Documents PDF ai-agent clawdbot edge-computing ollama self-hosted single-binary

ocr-and-documents

Extract text from PDFs and scanned documents. Use webextract for remote URLs, pymupdf for local text-based PDFs, marker-pdf for OCR/scanned docs. For DOCX use python-docx, for PPTX see the powerpoint skill.

moltis-org/moltis · 54 tokens

nano-pdf

Edit PDFs with natural-language instructions using the nano-pdf CLI. Modify text, fix typos, update titles, and make content changes to specific pages without manual editing.

moltis-org/moltis · 38 tokens

pandic-office

Convert Markdown to PDF (or DOCX/EPUB/HTML) using the pandoc CLI. Use when asked to produce a PDF report, brief, summary, or any document where the input is Markdown and the output should be a polished, paginated file.

Team-Commonly/commonly · 59 tokens

markdown-converter

Convert binary documents (PDF, DOCX, XLSX, PPTX, HTML, EPUB, images) to clean LLM-friendly Markdown using Microsoft's markitdown Python tool. Use when a user attaches a binary file and you need to read its contents.

Team-Commonly/commonly · 57 tokens

pdf

Manipulate PDF files — extract text, count pages, render thumbnails, merge or split documents. Use for PDF-specific operations that don't fit markdown-converter (general read) or pandic-office (write from markdown).

Team-Commonly/commonly · 49 tokens

nutrient-openclaw

Use the pinned Nutrient OpenClaw plugin to convert, OCR, extract, redact, watermark, sign, or inspect the last-known local credit record for documents. Route only OpenClaw document-processing requests to its declared tools. Treat processing as an external, credit-consuming DWS transfer that requires a bounded estimate…

jdrhyne/agent-skills · 77 tokens