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 Jesse-njx/dsh-cowork --skill cligit clone --depth 1 https://github.com/Jesse-njx/dsh-coworkWrote 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/jesse-njx/dsh-cowork/cli)<a href="https://agentmods.dev/skills/jesse-njx/dsh-cowork/cli"><img src="https://agentmods.dev/badge/skills/jesse-njx/dsh-cowork/cli.svg" alt="Measured on agentmods" 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 | $0.00040 | $0.00622 |
| Opus 5 | $0.00020 | $0.00311 |
| Sonnet 5 | $0.00008 | $0.00124 |
| Haiku 4.5 | $0.00004 | $0.00062 |
Grade A, and why
dsh-cowork 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 6d 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.
What it actually says
DSH Cowork (doc-read / doc-write)
Use the doc-read / doc-write CLI to work with binary documents instead of
trying to read them as text.
When to use
- The user asks to read, summarize, extract from, or edit an
.xlsx,.pdf,.docx,.pptx, or.ipynbfile. - A file does not open with your normal text reader.
doc-read
doc-read <file> [--page N] [--pages N] [--sheets a,b] [--row-offset N] [--rows N] \
[--slide N] [--slides N] [--cell N] [--cells N] [--max-bytes N] [--json]
- xlsx results are markdown tables with cell refs (
A1,C12) — use them as addresses for edits. - pdf/pptx/ipynb support page/slide/cell windows. Always window large files: start with the default window, then pass offsets to continue.
- A
> Truncated:line means the window was cut short — continue with a higher offset rather than guessing at the rest. --jsonprints the structured window (addresses, formulas, notices) instead of markdown.
doc-write
doc-write create <file> <xlsx|ipynb> --spec spec.json [--force]
doc-write edit <file> --spec spec.json [--force]
Spec shapes:
- xlsx create:
{"sheets":[{"name":"S1","cells":[{"ref":"A1","value":42}]}]}— values may be string/number/boolean/null or{"formula":"SUM(A1:A2)"}. - xlsx edit:
{"format":"xlsx","edits":[{"sheet":"S1","ref":"A1","value":"x"}]} - ipynb create:
{"cells":[{"type":"markdown","source":"# Hi"},{"type":"code","source":"print(1)"}]} - ipynb edit:
{"format":"ipynb","edits":[{"op":"replace","cell":0,"source":"..."}]}(op∈ replace | insert | delete; insert takesat+cells)
Rules:
- Writes are atomic (temp file + rename). Never write a macro-enabled format (xlsm/docm/pptm) — they are rejected.
--forceis required to overwrite an existing file.- After an edit, re-read the file with
doc-readto verify before telling the user it succeeded.
What ships with it
5 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.
- 6d ago First seen · 56 lines · 40 tokens per session scan A 1bde6610fd03
dsh-cowork is a skill published in the GitHub repository Jesse-njx/dsh-cowork (5 stars, last pushed 24d ago), licensed MIT. It adds 40 tokens to every session and 622 once invoked, about $0.0002 per session on Opus 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 2026-08-31.
Other skills, from other repositories
yao-ocr
OCR text recognition expert. ALWAYS invoke this skill when you need to extract text from images or PDFs — including invoices, receipts, ID cards, bank cards, business licenses, tables, handwritten documents, or any visual text content.
officecli
Use when the task involves Office document or standalone image handling such as creating, modifying, or converting PPTX, DOCX, XLSX, Report, or IMG files, and the agent should first check whether officecli supports that workflow before choosing the execution path.
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.
pdf-image-text-extractor
A tool for reading text from images and PDF files, including scanned documents. OCR means recognizing printed or handwritten characters in an image and turning them into editable text.
dsh-paddleocr-skills-setup
Install and configure the native PaddleOCR plugin for DeepSeek Harness (DSH) from the Settings → PaddleOCR GUI. Use for OCR and image-to-text from screenshots, scans, and PDFs; Chinese/CJK text; PDF-to-Markdown; structured document parsing with tables, formulas, layout, and reading order; or DSH endpoint, credential…
office-tools
A collection of tools for working with Excel, Word, PowerPoint, PDF, CSV, and Markdown files. It includes spreadsheet analysis, file conversion, and image extraction from documents.