Octos is a self-hosted AI assistant that runs on a user's computer and can connect to different AI providers, execute code, browse the web, remember information, schedule jobs, and create documents through browser, terminal, and messaging interfaces. The catalogue entries extend or configure this assistant's workflows.
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 octos-org/octos --skill officegit clone --depth 1 https://github.com/octos-org/octosWrote 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/octos-org/octos/office)<a href="https://agentmods.dev/skills/octos-org/octos/office"><img src="https://agentmods.dev/badge/skills/octos-org/octos/office/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/octos-org/octos/office"><img src="https://agentmods.dev/badge/skills/octos-org/octos/office.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 | $0.00051 | $0.00710 |
| Opus 5.5 | $0.00020 | $0.00284 |
| Sonnet 5.5 | $0.00010 | $0.00142 |
| Haiku 4.5 | $0.00005 | $0.00071 |
Grade A, and why
office 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 4d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Office document generation
Call office_generate once per output file. Paths are relative to the session workspace. Images must be PNG or JPEG already inside that workspace. The tool never overwrites an existing file; choose a new name.
DOCX
{
"kind": "docx",
"output": "reports/q3-summary.docx",
"title": "Q3 summary",
"paragraphs": ["Revenue increased.", "Details are below."],
"tables": [{"rows": [["Region", "Sales"], ["East", "120"], ["West", "140"]]}],
"images": [{"path": "charts/q3.png", "width_inches": 5.5}]
}
The document contains the title, paragraphs, every table row/cell, and embedded images in that order.
XLSX
{
"kind": "xlsx",
"output": "reports/q3.xlsx",
"sheets": [
{
"name": "Summary",
"rows": [
[{"value": "Region", "bold": true, "fill": "DDEBF7"}, {"value": "Sales", "bold": true, "fill": "DDEBF7"}],
["East", 120],
["West", 140],
[{"value": "Total", "bold": true}, {"formula": "SUM(B2:B3)", "number_format": "#,##0.00"}]
]
},
{"name": "Notes", "rows": [["Values are in USD."]]}
]
}
A cell can be a JSON string, number, or boolean, or an object with:
value: string, number, or boolean;formula: formula text, with or without the leading=(use instead ofvalue);bold:truefor bold text;fill: six-digit RGB fill such asDDEBF7;number_format: Excel number format such as0.00,0%, or#,##0.00.
Formulas are marked for recalculation when the workbook opens. No LibreOffice or other external program is required.
PPTX
{
"kind": "pptx",
"output": "reports/q3-deck.pptx",
"slides": [
{"title": "Q3 summary", "bullets": ["Revenue increased", "East and West grew"]},
{"title": "Regional sales", "bullets": ["East: 120", "West: 140"], "image": {"path": "charts/q3.png", "width_inches": 5.5}}
]
}
Each slide has an editable title and bullet paragraphs. The optional image is placed to the right of the text, preserving its aspect ratio. Presentations are limited to 100 slides and 64 MiB of image bytes in total; each image is limited to 32 MiB and a width of 5.5 inches.
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago Changed · +15 lines · +8 tokens per session c1932ddddb82
- 6d ago First seen · 58 lines · 43 tokens per session scan A c3c5ca3b07b5
office is a skill published in the GitHub repository octos-org/octos (766 stars, last pushed today), licensed Apache-2.0. It adds 51 tokens to every session and 710 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 2026-10-31.
office compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| officeoctos-org/octos | Skill | 766 | today | Apache-2.0 | A | 51 | Claude Code, Codex |
| dcf-modelNousResearch/hermes-agent | Skill | 261k | yesterday | MIT | A | 14 | Claude Code, Codex |
| gogopenclaw/openclaw | Skill | 394k | yesterday | MIT | A | 20 | Claude Code, Codex |
| xlsxasgeirtj/system_prompts_leaks | Skill | 71k | 2d ago | CC0-1.0 | A | 206 | Claude Code, Codex |
| audit-xlsanthropics/financial-services | Skill | 41k | 9d ago | Apache-2.0 | A | 104 | Claude Code |
| google-drive-sheetsyc-software/qm | Skill | 16k | today | MIT | A | 32 | Claude Code, Codex |
| feishuHmbown/CodeWhale | Skill | 41k | 5d ago | MIT | A | 33 | Claude Code, Codex |