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 ThomasMoreAI/legal-skills-open --skill patent-search-sylvanus4git clone --depth 1 https://github.com/ThomasMoreAI/legal-skills-openWrote 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/thomasmoreai/legal-skills-open/patent-search-sylvanus4)<a href="https://agentmods.dev/skills/thomasmoreai/legal-skills-open/patent-search-sylvanus4"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/patent-search-sylvanus4/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/thomasmoreai/legal-skills-open/patent-search-sylvanus4"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/patent-search-sylvanus4.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 | $0.00222 | $0.02590 |
| Opus 5 | $0.00111 | $0.01295 |
| Sonnet 5 | $0.00044 | $0.00518 |
| Haiku 4.5 | $0.00022 | $0.00259 |
Grade A, and why
patent-search-sylvanus4 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 9d 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 — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Patent Search — Multi-Jurisdiction Prior Art Search
Role
Expert patent search analyst who identifies relevant prior art across multiple patent offices and academic databases, producing structured search reports with bilingual keyword coverage and jurisdiction-specific metadata.
Prerequisites
- WebSearch tool available for patent database queries
- WebFetch tool for retrieving patent document details
- Write tool for persisting results to
outputs/patent-search/{date}/
Workflow
Step 0: Input Validation
Before Step 1, confirm and normalize inputs. Required:
- Technical field description — domain and problem context (e.g., AI orchestration, distributed systems).
- At least three key technical features — distinct mechanisms or structural elements (not marketing phrases).
- Target jurisdictions — at least one of US, KR, EP, WO, or explicit “global”; default if unspecified: US + KR.
Graceful degradation:
- If the user provides fewer than three features, extract additional features from any attached documents, prior messages, or patent-scanner output before proceeding. If still fewer than three, ask the user to name missing differentiators.
- If no technical details are available (vague one-liner with no field, no features, no docs), stop and ask for field + three features + jurisdictions before running searches.
- If jurisdiction is vague (“worldwide”), treat as multi-source global search and include US + KR + WO minimum in coverage.
Step 1: Understand the Invention
Collect from the user:
- Technical field and problem being solved
- Key technical features of the invention
- Target jurisdictions (US, KR, or both — default: both)
- Any known prior art references
If the user provides an existing draft or patent-scanner output, extract the technical features from those files.
Step 2: Generate Bilingual Keyword Sets
Produce a keyword matrix:
| Category | English Keywords | Korean Keywords | IPC/CPC Codes |
|---|---|---|---|
| Core concept | ... | ... | ... |
| Variant terminology | ... | ... | ... |
| Component terms | ... | ... | ... |
| Effect/result terms | ... | ... | ... |
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.
- 9d ago First seen · 216 lines · 222 tokens per session scan A f5d12284201f
patent-search-sylvanus4 is a skill published in the GitHub repository ThomasMoreAI/legal-skills-open (72 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 222 tokens to every session and 2,590 once invoked, about $0.0011 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 2026-09-03.
Other skills, from other repositories
pia-generator
Generate structured privacy impact assessments so Claude can organize project privacy risks, controls, and decision points into a review-ready report.
audit-scope-checklist
Generate a scoped IT audit program with controls mapped to roles and compliance frameworks. Use this skill for audit planning, control checklist generation, and auditprogram.json creation.
compliance-checker
Compare system configuration evidence against common control frameworks and produce a concise compliance assessment with gaps and remediation priorities.
compliance-controls-playbook
Guide Claude through a structured compliance audit workflow covering framework selection, evidence planning, control testing, exception handling, and reporting.
evidence-tracker
Manage audit evidence requests, collection progress, and status reporting so Claude can keep audits organized and identify overdue or blocked evidence items.
consent-checker
Review privacy policy or notice text against common privacy frameworks so Claude can explain coverage gaps, strengths, and compliance priorities.