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 xlsxgit 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/xlsx)<a href="https://agentmods.dev/skills/mudler/localai/xlsx"><img src="https://agentmods.dev/badge/skills/mudler/localai/xlsx/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/xlsx"><img src="https://agentmods.dev/badge/skills/mudler/localai/xlsx.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 | $0.00037 | $0.00672 |
| Opus 5.5 | $0.00015 | $0.00269 |
| Sonnet 5.5 | $0.00007 | $0.00134 |
| Haiku 4.5 | $0.00004 | $0.00067 |
Grade A, and why
xlsx 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Excel workbooks with the Simple Office tools
Use the tools of the Simple Office add-on: addon__office__read-xlsx,
addon__office__edit-xlsx and addon__office__create-xlsx. A file is a
path in the user's files, such as /reports/plan.xlsx.
Read first
- Call
read-xlsxwith the path only. You get the sheet names and the cell values of each sheet, row by row. - For a large workbook, call
read-xlsxagain withsheetto read one sheet. - Answer from what you read. Do not guess a value you did not read.
Change cells
- Read the sheet first, so that you know the cell addresses.
- Call
edit-xlsxwithpath,sheetandcells. Each cell has arefsuch asB3and exactly one oftext,number,formulaorclear. - Change only the cells that must change. Do not create the workbook again to change a cell.
- A formula is a string that starts with
=, such as=SUM(B2:B9). The file is not recalculated: say that the value shows when the file is opened in a spreadsheet program. - To add a sheet, give
addSheetwith its name in the same call. - Tell the user the sheet and the range you changed.
Create a workbook
Use create-xlsx with path and a comma-separated csv string, only when
no file exists. It creates exactly one sheet; optional sheet defaults to
Sheet1, and optional title is metadata. All arguments are strings. The
former sheets/rows creation structure is no longer accepted.
Example: {"path":"/reports/status.xlsx","csv":"Name,Status\nWorker,Ready\n","sheet":"Status"}.
Standard CSV quoting, escaped quotes, multiline cells and LF/CRLF are supported.
Every nonempty field stays text, including leading zeros and values beginning
with =, +, - or @; no formulas or numbers are inferred. Empty cells
stay blank in place. The first row is ordinary data, not a styled header.
Use edit-xlsx afterwards for explicit numbers or formulas. Ragged rows,
malformed quoting, empty content and invalid sheet names are refused.
Limits: 5000 rows, 200 columns and 100000 grid cells, including empty fields.
If the path is taken, the old file stays and the new one is saved next to it:
give the user the new path.
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 · +11 lines · +1 tokens per session 7ff793e6ad12
- 4d ago First seen · 44 lines · 36 tokens per session scan A 81cf5ae7f8a8
xlsx is a skill published in the GitHub repository mudler/LocalAI (50,218 stars, last pushed yesterday), licensed MIT. It adds 37 tokens to every session and 672 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.
xlsx compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| xlsxmudler/LocalAI | Skill | 50k | yesterday | MIT | A | 37 | Claude Code, Codex |
| receipts-to-expensesskrun-dev/skrun | Skill | 209 | 1mo ago | MIT | A | 54 | Claude Code, Codex |
| dcf-modelNousResearch/hermes-agent | Skill | 261k | today | MIT | A | 14 | Claude Code, Codex |
| comps-analysisNousResearch/hermes-agent | Skill | 261k | today | MIT | A | 13 | Claude Code, Codex |
| lbo-modelNousResearch/hermes-agent | Skill | 261k | today | MIT | A | 19 | Claude Code, Codex |
| google-workspaceNousResearch/hermes-agent | Skill | 261k | today | MIT | A | 21 | Claude Code, Codex |
| 3-statement-modelNousResearch/hermes-agent | Skill | 261k | today | MIT | A | 18 | Claude Code, Codex |