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 chuancyzhang/deepseek-cowork --skill document-readergit clone --depth 1 https://github.com/chuancyzhang/deepseek-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/chuancyzhang/deepseek-cowork/document-reader)<a href="https://agentmods.dev/skills/chuancyzhang/deepseek-cowork/document-reader"><img src="https://agentmods.dev/badge/skills/chuancyzhang/deepseek-cowork/document-reader/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/chuancyzhang/deepseek-cowork/document-reader"><img src="https://agentmods.dev/badge/skills/chuancyzhang/deepseek-cowork/document-reader.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 | $0.00015 | $0.00474 |
| Opus 5.5 | $0.00006 | $0.00190 |
| Sonnet 5.5 | $0.00003 | $0.00095 |
| Haiku 4.5 | $0.00002 | $0.00047 |
Grade A, and why
document-reader 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 18d 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
Document Reader
This bundled capability is enabled by default and reads structured document formats that plain text file tools intentionally refuse.
Tool
document_read
Reads DOCX, PPTX, XLSX, XLS, or PDF files from the current workspace and returns a unified structured payload with extracted text.
- The first call returns a bounded batch.
max_charslimits the entire JSON result (includingsectionsand metadata), defaults to 12000, and accepts 2000–60000. - Check
has_moreandrange. Continue only as needed by passingnext_cursorascursorwith the samepath; omit selectors or keep them identical. A changed file requires a fresh read. - For Excel, prefer
sheet_nameandcell_range(for exampleA1:D100); without a sheet selector, batches traverse sheets in workbook order.metadata.sheet_countis the workbook total, whilesheet_nameslists only sheets included in the current batch. - PDF supports
pages, for example2-4. Long pages, paragraphs and cells may span batches; concatenatecontentwithout adding separators to reconstruct the selected text. - Do not automatically load every batch. Read the ranges needed for the user's task, and keep findings concise before continuing.
Boundaries
- Use
text_file_readonly for plain text files. - Use
document_readfor Office/PDF reads. If the user explicitly disabled this capability, ask them to enable it in the capability store. - There is no Office/PDF write tool. When the user asks to create or modify Office/PDF files, use
run_python_codewith an appropriate library and normal workspace write safety rules. - This plugin does not use Pandoc.
What ships with it
2 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.
- 18d ago Changed · +6 lines ce9fbcb428ab
- 1mo ago First seen · 32 lines · 15 tokens per session scan A be73380fd90e
document-reader is a skill published in the GitHub repository chuancyzhang/deepseek-cowork (18 stars, last pushed today), licensed Apache-2.0. It adds 15 tokens to every session and 474 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 2026-08-30.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
apify-youtube-transcript-scraper
Get YouTube captions, timestamped quotations, SRT/VTT and translated transcripts for videos, channels and playlists through the harshmaur/youtube-transcript-scraper Apify Actor.
legal-hold
Issue, refresh, release, or report on legal holds — drafts the hold notice as .docx, updates legalhold fields in log.yaml, and calendars the next refresh. Use when the user says "issue a hold", "refresh hold", "release hold", or asks for a portfolio-wide hold status report.
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.