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 showdoc-mcpgit 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/showdoc-mcp)<a href="https://agentmods.dev/skills/chuancyzhang/deepseek-cowork/showdoc-mcp"><img src="https://agentmods.dev/badge/skills/chuancyzhang/deepseek-cowork/showdoc-mcp/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/showdoc-mcp"><img src="https://agentmods.dev/badge/skills/chuancyzhang/deepseek-cowork/showdoc-mcp.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 | $0.00026 | $0.00281 |
| Opus 5.5 | $0.00010 | $0.00112 |
| Sonnet 5.5 | $0.00005 | $0.00056 |
| Haiku 4.5 | $0.00003 | $0.00028 |
Grade A, and why
showdoc-mcp 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 1mo 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
ShowDoc MCP
Use this skill when the user asks to search, list, or read ShowDoc API documentation.
Setup
Configure the skill in the Skill Center:
SHOWDOC_HOST: ShowDoc server URL, including protocol.SHOWDOC_LOGIN_SECRET_KEY: login secret key from ShowDoc user settings.SHOWDOC_PROJECT_NAME: the project name to lock this MCP server to.SHOWDOC_USERNAME: optional username.
Saving the Skill configuration automatically creates, updates, and enables the managed showdoc stdio MCP server. Use the separate connection test when you need to verify tools or diagnose startup.
MCP Server
The generated preset uses:
{
"command": "npx",
"args": ["-y", "mcp-showdoc", "--host", "...", "--login_secret_key", "...", "--project_name", "..."]
}
Safety Rules
- Keep the project name scoped to the exact project the user wants to expose.
- Do not ask ShowDoc for unrelated projects unless the user changes the configuration.
- Treat
SHOWDOC_LOGIN_SECRET_KEYas a secret.
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.
- 1mo ago First seen · 40 lines · 26 tokens per session scan A 9e194c863527
showdoc-mcp is a skill published in the GitHub repository chuancyzhang/deepseek-cowork (18 stars, last pushed today), licensed Apache-2.0. It adds 26 tokens to every session and 281 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
ocr-pipeline-and-quality
Xberg OCR backends, preprocessing, caching, page acceptance, hOCR, tables, cross-backend quality. Use for OCR behavior or A/B quality work.
pdf-backends
Xberg PDF extraction: native/Pdfium backend selection, rendering, encryption, OCR fallback, capability gaps. Use for PDF engine work.
add-sharepoint
Adds SharePoint Online connector to a Power Apps code app. Use when reading lists, managing documents, or integrating with SharePoint sites. Can also create new SharePoint lists.
excel2json
An Excel conversion tool that turns worksheet data into JSON, a structured text format commonly used by programs and web APIs. It supports row-based, column-based, and two-dimensional output, and converts dates to a standard text form.
rag-web-fallback
Only reach for external web search when the local corpus comes back empty or clearly insufficient. Forces the agent to try knowledge-rag first, then explicitly document why it needed to escalate. Prevents wasted API cost, latency, and (in air-gapped deployments) accidental network calls.
hermes3000-writing
Use Hermes3000 to plan, draft, revise, save, check consistency, and export long-form manuscripts through the Hermes3000 AI writing portal API. Use for novels, fiction series, nonfiction books, whitepapers, long reads, chapter outlines, character/world-building, style guides, consistency memory, and DOCX/PDF/EPUB/HTML…