LocalAI is an inference server that runs language, vision, voice, image, and video models through compatible APIs on local hardware. It is used to operate models privately across different hardware, including CPU-only systems, and supports applications, agents, and multi-user services. The catalogue contains instructions for using LocalAI.
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 skills add mudler/LocalAI --skill pdfgit clone --depth 1 https://github.com/mudler/LocalAIWrote 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/mudler/localai/pdf)<a href="https://agentmods.dev/skills/mudler/localai/pdf"><img src="https://agentmods.dev/badge/skills/mudler/localai/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.
<a href="https://agentmods.dev/skills/mudler/localai/pdf"><img src="https://agentmods.dev/badge/skills/mudler/localai/pdf.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00035 | $0.00483 |
| Opus 5.5 | $0.00014 | $0.00193 |
| Sonnet 5.5 | $0.00007 | $0.00097 |
| Haiku 4.5 | $0.00003 | $0.00048 |
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 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.
What it actually says
PDF files with the Simple Office tools
Use the tools of the Simple Office add-on: addon__office__read-pdf and
addon__office__create-pdf. A file is a path in the user's files, such as
/reports/plan.pdf.
Read a PDF
- Call
read-pdfwith the path. You get the text page by page, up to 50 pages in one call. - For a longer file, call
read-pdfagain withfirstPage(andlastPageif you need a range) to continue. - A scanned page has no text. Say that the page has no text and stop. Do not guess what it says.
- Answer from what you read, and give the page numbers.
Create a PDF
- Use
create-pdfwithpathand amarkdownstring. Headings, paragraphs, bullet and numbered lists, bold/italic emphasis and simple rectangular tables are supported. Code is literal text; links show labels without fetching targets. HTML, images and unsupported constructs are refused. Optionaltitleis metadata, not an extra visible heading. All arguments are strings. The formerblocksargument is no longer accepted. Example:{"path":"/reports/plan.pdf","markdown":"# Plan\n\nA short summary."}. - The text must use Latin-1 characters only. Replace other characters, or tell the user which ones cannot be written.
- If the path is taken, the old file stays and the new one is saved next to it.
Change a PDF
There is no edit tool. To change a PDF, read it, then create a new PDF with the changed content, and tell the user that the layout of the original is not kept.
When the tools cannot do it
The tools do not fill forms, sign, merge, split or keep the layout of an existing PDF. Say so before you start, and offer what the tools can do.
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 Changed · +4 lines · +1 tokens per session 58dde03ee4ad
- 4d ago First seen · 41 lines · 34 tokens per session scan A 41f24bbc5c0c
pdf is a skill published in the GitHub repository mudler/LocalAI (50,218 stars, last pushed yesterday), licensed MIT. It adds 35 tokens to every session and 483 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-11-02.
pdf compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| pdfmudler/LocalAI | Skill | 50k | yesterday | MIT | A | 35 | Claude Code, Codex |
| csv-to-executive-reportskrun-dev/skrun | Skill | 209 | 1mo ago | MIT | A | 81 | Claude Code, Codex |
| receipts-to-expensesskrun-dev/skrun | Skill | 209 | 1mo ago | MIT | A | 54 | Claude Code, Codex |
| pdf-processingskrun-dev/skrun | Skill | 209 | 1mo ago | MIT | A | 29 | Claude Code, Codex |
| extracting-lab-tablesmaziyarpanahi/openmed | Skill | 5.8k | yesterday | Apache-2.0 | A | 210 | Claude Code |
| pdf-toolkitopensquilla/opensquilla | Skill | 7.1k | 6d ago | Apache-2.0 | A | 127 | Claude Code, Codex |
| figuressynthetic-sciences/openscience | Skill | 4.3k | 2d ago | Apache-2.0 | A | 99 | Claude Code |