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 office-recalculategit 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-recalculate)<a href="https://agentmods.dev/skills/deepseek-ai/deepseek-harness/office-recalculate"><img src="https://agentmods.dev/badge/skills/deepseek-ai/deepseek-harness/office-recalculate/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-recalculate"><img src="https://agentmods.dev/badge/skills/deepseek-ai/deepseek-harness/office-recalculate.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 | $0.00017 | $0.00347 |
| Opus 5.5 | $0.00007 | $0.00139 |
| Sonnet 5.5 | $0.00003 | $0.00069 |
| Haiku 4.5 | $0.00002 | $0.00035 |
Grade A, and why
office-recalculate 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
Recalculate spreadsheet formulas
Use the installed LibreOffice Kit CLI through the shell with the absolute Node and CLI paths supplied below. In Bash, invoke "<node>" "<cli>"; in PowerShell, invoke & "<node>" "<cli>". Prefer bundled LibreOffice unless the user requests another installation. If the Office sidecar is missing, follow sidecar setup: ask whether the user wants to download it and install only after they agree. Do not invoke system soffice, use npx, or install a replacement to work around a failed recalculation with an installed sidecar.
Keep the original workbook and write a new file in the task workspace. Quote each input and output path.
"<node>" "<cli>" recalculate --input <workbook.xlsx> --output <recalculated.xlsx>
Verify the saved result with openpyxl, using load_workspace_dependencies for the Python path unless a project environment is required. Open it with both data_only=False and data_only=True. Check that formulas survive and cached results match the requested logic, expected totals, and cell types. Check required unchanged sheets, styles, and data. Recalculation does not validate business logic or guarantee Excel-specific feature compatibility.
If no supported recalculation engine is available or the command fails, preserve the workbook and explain that calculated values could not be refreshed. Do not replace requested formulas with constants or present stale/absent caches as fresh results. Deliver the verified output through present when available, keeping the file in place.
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 · 19 lines · 17 tokens per session scan A acc3729600af
office-recalculate is a skill published in the GitHub repository deepseek-ai/deepseek-harness (250,433 stars, last pushed today), licensed MIT. It adds 17 tokens to every session and 347 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
youtube-digest
A transcript extractor for YouTube videos. It reads available subtitles or automatically generated captions, can translate non-Chinese captions into Chinese, and can export the text to Excel, a spreadsheet application.
google-workspace-ops
Operate across Google Drive, Docs, Sheets, and Slides as one workflow surface for plans, trackers, decks, and shared documents. Use when the user needs to find, summarize, edit, migrate, or clean up Google Workspace assets without dropping to raw tool calls.
investor-materials
Create and update pitch decks, one-pagers, investor memos, accelerator applications, financial models, and fundraising materials. Use when the user needs investor-facing documents, projections, use-of-funds tables, milestone plans, or materials that must stay internally consistent across multiple fundraising assets.
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.