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 docxgit 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/docx)<a href="https://agentmods.dev/skills/mudler/localai/docx"><img src="https://agentmods.dev/badge/skills/mudler/localai/docx/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/docx"><img src="https://agentmods.dev/badge/skills/mudler/localai/docx.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 | $0.00039 | $0.00565 |
| Opus 5.5 | $0.00016 | $0.00226 |
| Sonnet 5.5 | $0.00008 | $0.00113 |
| Haiku 4.5 | $0.00004 | $0.00056 |
Grade A, and why
docx 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Word documents with the Simple Office tools
Use the tools of the Simple Office add-on: addon__office__read-docx,
addon__office__edit-docx and addon__office__create-docx. A file is a
path in the user's files, such as /reports/plan.docx.
Read first
- Call
read-docxwith the path. You get the paragraphs with their index, and the tables. - Answer from what you read. Do not guess text you did not read.
Change a document
- Read the document first to get the paragraph indexes.
- Call
edit-docxwithpathandedits. Each edit has anop:set: replace the text of the paragraphindex.insert: add a paragraph withtextafter the paragraphafter(-1for the start).styleis optional and must be a style of the document.delete: remove the paragraphindex.replace: replacefindwithtexteverywhere.
- The edits run in order, and all or none are saved. An insert or a delete moves the indexes after it: plan the order, or read the document again.
- Change the smallest range of paragraphs. Do not create the document again to fix a typo.
- If someone changed the file meanwhile, your version is saved as a second file. Tell the user its path.
Create a document
Use create-docx with path and a markdown string. Markdown supports
headings, paragraphs, bullet and numbered lists, bold/italic emphasis and
simple rectangular tables. Code is literal text; links show their labels
without fetching targets. HTML, images and unsupported constructs are refused.
Optional title is metadata, not an extra visible heading. All arguments
are strings. The former blocks argument is no longer accepted.
Example: {"path":"/reports/plan.docx","markdown":"# Plan\n\nA **short** summary."}.
If the path is taken, the old file stays and the new one is saved next to it.
When the tools cannot do it
The tools do not edit tables, tracked changes, comments, images, headers, footers or fields. Say so before you start, and offer what the tools can do. Do not describe a manual method instead.
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 · +6 lines · +1 tokens per session 740ee92396de
- 4d ago First seen · 45 lines · 38 tokens per session scan A 66570fab822e
docx is a skill published in the GitHub repository mudler/LocalAI (50,218 stars, last pushed yesterday), licensed MIT. It adds 39 tokens to every session and 565 once invoked, about $0.0002 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.
docx compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| docxmudler/LocalAI | Skill | 50k | yesterday | MIT | A | 39 | Claude Code, Codex |
| knowledge-base-from-vaultskrun-dev/skrun | Skill | 209 | 1mo ago | MIT | A | 91 | 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 |
| slide-deck-generatorskrun-dev/skrun | Skill | 209 | 1mo ago | MIT | A | 69 | Claude Code, Codex |
| pdf-processingskrun-dev/skrun | Skill | 209 | 1mo ago | MIT | A | 29 | Claude Code, Codex |
| dcf-modelNousResearch/hermes-agent | Skill | 261k | today | MIT | A | 14 | Claude Code, Codex |