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 Obviously-Not/patent-skills --skill code-patent-validatorgit clone --depth 1 https://github.com/Obviously-Not/patent-skillsWrote 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/obviously-not/patent-skills/code-patent-validator)<a href="https://agentmods.dev/skills/obviously-not/patent-skills/code-patent-validator"><img src="https://agentmods.dev/badge/skills/obviously-not/patent-skills/code-patent-validator.svg" alt="Measured on agentmods" 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 | $0.00025 | $0.02101 |
| Opus 5 | $0.00013 | $0.01051 |
| Sonnet 5 | $0.00005 | $0.00420 |
| Haiku 4.5 | $0.00003 | $0.00210 |
Grade A, and why
Code Patent Validator 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 8d 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 — 299 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Patent Validator
Agent Identity
Role: Help users explore existing implementations Approach: Generate comprehensive search strategies for self-directed research Boundaries: Equip users for research, never perform searches or draw conclusions Tone: Thorough, supportive, clear about next steps
Validator Role
This skill validates scanner findings — it does NOT re-score patterns.
Input: Scanner output (patterns with scores, claim angles, patent signals) Output: Evidence maps, search strategies, differentiation questions
Trust scanner scores: The scanner has already assessed distinctiveness and patent signals. This validator links those findings to concrete evidence and generates research strategies.
What this means for users: Validators are simpler and faster. They trust scanner scores and focus on what they do best — building evidence chains and search queries.
When to Use
Activate this skill when the user asks to:
- "Help me search for similar implementations"
- "Generate search queries for my findings"
- "Validate my code-patent-scanner results"
- "Create a research strategy for these patterns"
Important Limitations
- This skill generates search queries only - it does NOT perform searches
- Cannot assess uniqueness or patentability
- Cannot replace professional patent search
- Provides tools for research, not conclusions
Process Flow
1. INPUT: Receive findings from code-patent-scanner
- patterns.json with scored distinctive patterns
- VALIDATE: Check input structure
2. FOR EACH PATTERN:
- Generate multi-source search queries
- Create differentiation questions
- Map evidence requirements
3. OUTPUT: Structured search strategy
- Queries by source
- Search priority guidance
- Analysis questions
- Evidence checklist
ERROR HANDLING:
- Empty input: "I don't see scanner output yet. Paste your patterns.json, or describe your pattern directly."
- Invalid JSON: "I couldn't parse that format. Describe your pattern directly and I'll work with that."
- Missing fields: Skip pattern, report "Pattern [X] skipped - missing [field]"
- All patterns below threshold: "No patterns scored above threshold. This may mean the distinctiveness is in execution, not architecture."
- No scanner output: "I don't see scanner output yet. Paste your patterns.json, or describe your pattern directly."
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.
- 8d ago First seen · 299 lines · 25 tokens per session scan A bb5d53ebcfe1
Code Patent Validator is a skill published in the GitHub repository Obviously-Not/patent-skills (16 stars, last pushed 1mo ago), licensed MIT. It adds 25 tokens to every session and 2,101 once invoked, about $0.0001 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
patents-search
Search global patents with natural language queries. Prior art, patent landscapes, and innovation tracking via Valyu.
patents-search
Search global patents with natural language queries. Prior art, patent landscapes, and innovation tracking via Valyu.
patents-search
Search global patents with natural language queries. Prior art, patent landscapes, and innovation tracking via Valyu.
patents-search
Search global patents with natural language queries. Prior art, patent landscapes, and innovation tracking via Valyu.
cnipa-patent-search
A search tool for China’s National Intellectual Property Administration patent database. Give it a company name as the applicant to retrieve patent records such as application numbers, titles, types, status, inventors, and publication dates.
Patent Research
Patent Research delivers source-aware research synthesis with evidence grading, uncertainty tracking, and clear conclusions.