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 patsnap/mcp --skill patsnap-deep-patent-mininggit clone --depth 1 https://github.com/patsnap/mcpWrote 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/patsnap/mcp/patsnap-deep-patent-mining)<a href="https://agentmods.dev/skills/patsnap/mcp/patsnap-deep-patent-mining"><img src="https://agentmods.dev/badge/skills/patsnap/mcp/patsnap-deep-patent-mining/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/patsnap/mcp/patsnap-deep-patent-mining"><img src="https://agentmods.dev/badge/skills/patsnap/mcp/patsnap-deep-patent-mining.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00091 | $0.00632 |
| Opus 5 | $0.00046 | $0.00316 |
| Sonnet 5 | $0.00018 | $0.00126 |
| Haiku 4.5 | $0.00009 | $0.00063 |
Grade A, and why
patsnap-deep-patent-mining 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 11d 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
Setup
Get your API Key at https://open.patsnap.com
Deep Patent Mining
This skill connects your AI agent to Patsnap's Deep Patent Mining MCP server.
With this skill, your agent can use Patsnap data and workflow capabilities for IP Intelligence tasks.
Prerequisites
This skill requires the Patsnap Deep Patent Mining MCP server to be configured in your environment:
{
"mcpServers": {
"deep_patent_mining": {
"url": "https://connect.patsnap.com/7cc6ae/mcp?apikey=YOUR_API_KEY",
"type": "streamableHttp"
}
}
}
Get your API key at open.patsnap.com.
For the full list of available tools and input parameters, refer to the official MCP server documentation: https://open.patsnap.com/marketplace/mcp-servers/patent-mining
Instructions for AI Agents
Step 1: Understand the user's search intent
Identify the target entities, date ranges, owners, patent numbers, technologies, or document types in the user's request.
Step 2: Choose the right workflow
Use semantic, fielded, identifier-based, analytics, or retrieval workflows according to the task and available MCP tools.
Step 3: Synthesize and cite
Present results in a structured format and cite returned patent numbers, record IDs, titles, organizations, or source names when available.
Example Workflows
- Use Deep Patent Mining to analyze recent patent activity for a target technology.
- Find relevant patents and summarize the key applicants, dates, and technical themes.
- Compare the most important records returned by Deep Patent Mining.
Resources
- MCP Server: https://open.patsnap.com/marketplace/mcp-servers/patent-mining
- Patsnap Open Platform: open.patsnap.com
- Patsnap: https://www.patsnap.com
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.
- 11d ago First seen · 68 lines · 91 tokens per session scan A 810abe99d186
patsnap-deep-patent-mining is a skill published in the GitHub repository patsnap/mcp (111 stars, last pushed 22d ago), licensed Apache-2.0. It adds 91 tokens to every session and 632 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
uspto-database
Access USPTO patent data via PatentsView REST API and Google Patents Public Data (BigQuery). Search by inventor, assignee, CPC, or keywords; download metadata and claims; analyze portfolios; track tech trends. For IP landscape analysis, competitor monitoring, prior art search, and tech forecasting in life sciences and…
analytical-method-validation
Plan, execute, and document validation, verification, and transfer of analytical procedures under the governing framework - ICH Q2(R2) and Q14, USP / / , ICH M10 bioanalytical, CLSI EP, or ISO/IEC 17025. Use for HPLC, LC-MS/MS, GC, CE, ICP-MS, dissolution, qNMR, qPCR, NIR, and ligand binding or cell-based assays…
treatment-plans
Format and structurally validate local treatment-plan documentation after clinical decisions have already been supplied and verified by authorized licensed professionals. Use for source traceability, clinician-authored intervention records, goals and checkpoints, shared-decision records, reconciliation handoffs, and…
adverse-event-narrative
Generates CIOMS I-compliant ICSR narratives from adverse event case data for FDA and EMA regulatory submission. Includes temporal analysis, MedDRA coding, causality assessment using WHO-UMC or Naranjo criteria, and multi-format output.
irb-application-assistant
Assists researchers with Institutional Review Board (IRB) application tasks, including drafting informed consent documents, reviewing research protocols for compliance, generating application forms, and preparing submission checklists. Use when the user mentions IRB, Instituti...
alterlab-uspto
Access USPTO APIs for patent and trademark searches, examination history (PEDS), assignments, citations, office actions, and trademark status (TSDR). Use when searching patents or trademarks, conducting prior art searches, retrieving patent examination or assignment records, or doing intellectual property (IP)…