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 agentmods add skills/learningmatter-mit/atomisticskills/general-patent-searchnpx skills add learningmatter-mit/AtomisticSkills --skill general-patent-searchgit clone --depth 1 https://github.com/learningmatter-mit/AtomisticSkillsWrote 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/learningmatter-mit/atomisticskills/general-patent-search)<a href="https://agentmods.dev/skills/learningmatter-mit/atomisticskills/general-patent-search"><img src="https://agentmods.dev/badge/skills/learningmatter-mit/atomisticskills/general-patent-search.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 | $0.00027 | $0.00502 |
| Opus 5 | $0.00014 | $0.00251 |
| Sonnet 5 | $0.00005 | $0.00100 |
| Haiku 4.5 | $0.00003 | $0.00050 |
Grade A, and why
general-patent-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 6d 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
general-patent-search
Goal
To retrieve patent information (titles, assignees, dates, and snippets) for specific materials, chemicals, or technologies to assess novelty, freedom-to-operate, and existing intellectual property landscapes. This skill uses Google Patents for free, global, no-key-required patent querying.
Instructions
1. Identify Target and Scope
Determine exactly what you are searching for.
- Are you looking for a specific chemical? (e.g., "tetrafluoropropene")
- Are you looking for a specific company's IP? (e.g., assignee "SK Innovation")
2. Search Strategy (Google Patents)
Use the python script to query Google Patents. It will return global patents matching your query string.
# Env: base-agent
python .agents/skills/general-patent-search/scripts/query_google_patents.py "query string" --limit 10
Examples
Searching for recent global patents on a novel refrigerant by chemical name:
# Env: base-agent
python .agents/skills/general-patent-search/scripts/query_google_patents.py "tetrafluoropropene OR HFO-1234yf" --limit 5
Searching for global patents assigned to SK Innovation regarding electrolytes:
# Env: base-agent
python .agents/skills/general-patent-search/scripts/query_google_patents.py "assignee:(SK Innovation) AND electrolyte" --limit 5
Constraints
- Environments: The script requires the
base-agentConda environment. - Google Patents Limits: The scraping script is sensitive to IP rate-limiting. Do not set
--limitexcessively high (keep under 50). - Chemical Structures: This tool performs text-based searches. It does not perform exact Substructure or Tanimoto similarity searches natively. You must provide textual synonyms (e.g., IUPAC names, trade names) for accurate chemical retrieval.
References
- Google Patents: https://patents.google.com/
Author: Sathya Edamadaka Contact: GitHub @snme
What ships with it
3 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.
- 6d ago First seen · 53 lines · 27 tokens per session scan A cb5d2fd5c2a0
general-patent-search is a skill published in the GitHub repository learningmatter-mit/AtomisticSkills (161 stars, last pushed 3d ago), licensed MIT. It adds 27 tokens to every session and 502 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
domain-setup
Configure your industry domain, country, and regulatory context — agents automatically adapt to your business.
specification-writing
Write the full patent specification from claims and invention disclosure. Use when user says "撰写说明书", "write specification", "写说明书", "patent description", or wants to draft the complete patent specification.
regulatory-research-fallback
Fallback workflow for regulatory research when web extraction tools fail on government PDFs.
package-installer
Install third-party open-source projects (a GitHub URL or a local git directory the user provides) as external packages. The project is cloned verbatim into the per-user packages directory — never edit, normalize, or reorganize its files.
x-scorecard
OpenSSF Scorecard for assessing open source project security. Check security best practices and compliance. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.