DeepSeek Harness is an open-source framework for building and running AI agents, organized so that its functionality is provided through plugins. Developers use it to launch agent workflows through a local web interface or from source, while the catalogue add-ons extend the harness as plugins.
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 deepseek-ai/deepseek-harness --skill officegit clone --depth 1 https://github.com/deepseek-ai/deepseek-harnessWrote 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/deepseek-ai/deepseek-harness/office)<a href="https://agentmods.dev/skills/deepseek-ai/deepseek-harness/office"><img src="https://agentmods.dev/badge/skills/deepseek-ai/deepseek-harness/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/deepseek-ai/deepseek-harness/office"><img src="https://agentmods.dev/badge/skills/deepseek-ai/deepseek-harness/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 | $0.00027 | $0.00204 |
| Opus 5.5 | $0.00011 | $0.00082 |
| Sonnet 5.5 | $0.00005 | $0.00041 |
| Haiku 4.5 | $0.00003 | $0.00020 |
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 yesterday.
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
Office task routing
Call the skill tool with the format skill name before creating, reading, or editing Office files. Standalone rendering, PDF export, and recalculation need only their operation skill.
- Create, read, or edit:
office-docx(Word),office-pptx(PowerPoint), oroffice-xlsx(Excel). - Images, visual inspection, or tasks primarily about layout, spacing, sizing, or alignment:
office-render, even without an explicit visual-check request. - Refresh spreadsheet formula results:
office-recalculate. - Export an Office file to PDF:
office-export-pdf.
Honor requests to skip rendering. New files, content edits, formulas, and incidental formatting such as bold headers or number formats need no render unless visual inspection is requested. Do not reload skills.
What ships with it
1 file 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.
- yesterday First seen · 16 lines · 27 tokens per session scan A d5b9c95af707
office is a skill published in the GitHub repository deepseek-ai/deepseek-harness (250,433 stars, last pushed today), licensed MIT. It adds 27 tokens to every session and 204 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 2026-10-15.
Other skills, from other repositories
manage-taskboard
Manage work in the native DeepSeek Harness Taskboard with exact task ids and optimistic versions. Use when an Agent must inspect project work, claim an eligible todo, record progress or blockers, verify an implementation, submit it for human review, or release its own claim; also use when a human asks how to accept…
industry-research-method
A Chinese-language method for researching an industry by mapping its supply chain, tracking policies and news, and writing sourced reports. It separates the chain into upstream inputs, midstream production, and downstream distribution or use.
company-research-method
A documented process for researching a company using supplied files and selected public sources. It produces a company overview with business details, sourced financial figures, and stated risks.
write-docs-cn
A guide to writing project documentation, especially README files. It explains how tutorials differ from reference material and where each kind of information belongs.
write-tech-cn
A writing guide for Chinese technical documents such as READMEs, tutorials, blogs, and technical explanations. It focuses on direct conclusions, clear actions, natural Chinese, and consistent technical terms.
pptwise
Generate a native, editable PPTX deck from an outline, notes, or source material with the pptwise CLI. Use when the user asks to create a PPT, deck, presentation, or slides and wants a deterministic, editable, theme-consistent result.