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 illusionaireal/oh-my-patent --skill prior-art-searchgit clone --depth 1 https://github.com/illusionaireal/oh-my-patentWrote 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/illusionaireal/oh-my-patent/prior-art-search)<a href="https://agentmods.dev/skills/illusionaireal/oh-my-patent/prior-art-search"><img src="https://agentmods.dev/badge/skills/illusionaireal/oh-my-patent/prior-art-search/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/illusionaireal/oh-my-patent/prior-art-search"><img src="https://agentmods.dev/badge/skills/illusionaireal/oh-my-patent/prior-art-search.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 | $0.00022 | $0.01773 |
| Opus 5.5 | $0.00009 | $0.00709 |
| Sonnet 5.5 | $0.00004 | $0.00355 |
| Haiku 4.5 | $0.00002 | $0.00177 |
Grade A, and why
prior-art-search 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 22d 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.
How it starts
The opening of the file, as written. The whole thing — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prior Art Search Skill
Search existing patents and technical literature to identify prior art for novelty and patentability assessment.
Overview
This skill integrates with multiple MCP servers (Google Scholar, USPTO, Semantic Scholar) to conduct comprehensive prior art searches across patents, academic papers, and technical documentation.
Usage
The skill is typically invoked by the patent-landscape-analyst agent during the RESEARCH stage of the patent workflow.
Basic Usage Pattern
// The skill is invoked through agent orchestration
// Agent: patent-landscape-analyst
// Input: topic keywords, technical domain
// Output: aggregated landscape report
Input Parameters
Required
- query: Search keywords and technical terms
- Example:
"homomorphic encryption privacy-preserving computation"
- Example:
Optional
-
searchScope: Time range for results
- Default: Last 5 years
- Options:
1year,3years,5years,10years,all
-
maxResultsPerSource: Maximum results from each source
- Default: 5
- Range: 1-20
-
sources: Which databases to query
- Default: All enabled MCP servers
- Options:
google_scholar,uspto_patent,semantic_scholar,cnipa_patent,patsnap_search
-
jurisdiction: Filter by patent jurisdiction
- Default: All jurisdictions
- Options:
CN,US,PCT EP/JPare not supported (REQ-017): if the user asks for them, say so explicitly, then proceed without a jurisdiction filter (or suggestPCTfor international filings). Never pass an unsupported code downstream.
Output Format
Primary Output
File: references/landscape_{topic_slug}.md
Contains aggregated search results organized by:
- Patent references (with classification codes)
- Academic literature
- Technical standards
- Industry implementations
Secondary Output
Files: references/{source}_{id}.md
Individual evidence cards for each finding:
- Full citation
- Abstract/summary
- Relevance score
- Key technical features
- Novelty comparison notes
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.
- 22d ago Changed 8532304b6d3b
- 1mo ago Changed · +222 lines 8c0dae4de4a4
- 1mo ago First seen · 30 lines · 22 tokens per session scan A b146c69385a2
prior-art-search is a skill published in the GitHub repository illusionaireal/oh-my-patent (110 stars, last pushed 15d ago), licensed MIT. It adds 22 tokens to every session and 1,773 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
motherduck-security-governance
Assess or configure MotherDuck access control: roles (RBAC), share grants, table-, row-, and column-level security, masking, tenant isolation, residency, and Terraform governance.
check-yonsei-space-rules
Read the current official Yonsei space rules first and check a booking proposal against public lead-time, duration, booking-count, ten-minute interval, applicant eligibility, and restricted-period rules; use a screenshot, pasted form, export, or JSON only when the live rule page is unavailable or intentionally…
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
plagiarism-checker
Scans lyrics for phrases that may match existing songs using web search and LLM knowledge. Use before release to check for unintentional borrowing.
gerrit-workflow
This skill should be used when the user asks to "submit a change to Gerrit", "push for review", "upload a patch", "update a change in Gerrit", "add a patch set", "work with Gerrit", "push to refs/for", "fix a missing Change-Id", "amend a Gerrit change", or any task involving git operations in a repository hosted on…