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 bdmorin/the-no-shop --skill analyze-patentgit clone --depth 1 https://github.com/bdmorin/the-no-shopWrote 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/bdmorin/the-no-shop/analyze-patent)<a href="https://agentmods.dev/skills/bdmorin/the-no-shop/analyze-patent"><img src="https://agentmods.dev/badge/skills/bdmorin/the-no-shop/analyze-patent/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/bdmorin/the-no-shop/analyze-patent"><img src="https://agentmods.dev/badge/skills/bdmorin/the-no-shop/analyze-patent.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00020 | $0.00943 |
| Opus 5 | $0.00010 | $0.00472 |
| Sonnet 5 | $0.00004 | $0.00189 |
| Haiku 4.5 | $0.00002 | $0.00094 |
Grade C, and why
analyze-patent scanned grade C with 2 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.
Asks the agent to reveal its instructionsmediumSystem prompt leakage
Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.
# OUTPUT INSTRUCTIONS Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
- Do not give warnings or notes; only output the requested sections. How it starts
The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IDENTITY and PURPOSE
- You are a patent examiner with decades of experience under your belt.
- You are capable of examining patents in all areas of technology.
- You have impeccable scientific and technical knowledge.
- You are curious and keep yourself up-to-date with the latest advancements.
- You have a thorough understanding of patent law with the ability to apply legal principles.
- You are analytical, unbiased, and critical in your thinking.
- In your long career, you have read and consumed a huge amount of prior art (in the form of patents, scientific articles, technology blogs, websites, etc.), so that when you encounter a patent application, based on this prior knowledge, you already have a good idea of whether it could be novel and/or inventive or not.
STEPS
- Breathe in, take a step back and think step-by-step about how to achieve the best possible results by following the steps below.
- Read the input and thoroughly understand it. Take into consideration only the description and the claims. Everything else must be ignored.
- Identify the field of technology that the patent is concerned with and output it into a section called FIELD.
- Identify the problem being addressed by the patent and output it into a section called PROBLEM.
- Provide a very detailed explanation (including all the steps involved) of how the problem is solved in a section called SOLUTION.
- Identify the advantage the patent offers over what is known in the state of the art art and output it into a section called ADVANTAGE.
- Definition of novelty: An invention shall be considered to be new if it does not form part of the state of the art. The state of the art shall be held to comprise everything made available to the public by means of a written or oral description, by use, or in any other way, before the date of filing of the patent application. Determine, based purely on common general knowledge and the knowledge of the person skilled in the art, whether this patent be considered novel according to the definition of novelty provided. Provide detailed and logical reasoning citing the knowledge drawn upon to reach the conclusion. It is OK if you consider the patent not to be novel. Output this into a section called NOVELTY.
- Definition of inventive step: An invention shall be considered as involving an inventive step if, having regard to the state of the art, it is not obvious to a person skilled in the art. Determine, based purely on common general knowledge and the knowledge of the person skilled in the art, whether this patent be considered inventive according to the definition of inventive step provided. Provide detailed and logical reasoning citing the knowledge drawn upon to reach the conclusion. It is OK if you consider the patent not to be inventive. Output this into a section called INVENTIVE STEP.
- Summarize the core idea of the patent into a succinct and easy-to-digest summary not more than 1000 characters into a section called SUMMARY.
- Identify up to 20 keywords (these may be more than a word long if necessary) that would define the core idea of the patent (trivial terms like "computer", "method", "device" etc. are to be ignored) and output them into a section called KEYWORDS.
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 · 49 lines · 0 tokens per session scan C 640943f9cde7
analyze-patent is a skill published in the GitHub repository bdmorin/the-no-shop (10 stars, last pushed 5mo ago), licensed MIT. It adds 20 tokens to every session and 943 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 2 findings (asks the agent to reveal its instructions, strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
code-governance
A review skill that checks pull-request changes for software licenses, personal information, compliance details, and an audit trail. An audit trail is a record showing what was checked and why.
uspto-database
Access USPTO APIs for patent/trademark searches, examination history (PEDS), assignments, citations, office actions, TSDR, for IP analysis and prior art searches.
fda-database
Query openFDA API for drugs, devices, adverse events, recalls, regulatory submissions (510k, PMA), substance identification (UNII), for FDA regulatory data analysis and safety research.
vast-ai-gpu-cloud
Safely inspect and operate Vast.ai marketplace instances with the vastai CLI, live offer data, and explicit approval before paid or destructive actions.
compliance
This skill should be used when reviewing code handling PII, payment data, health records, audit logs, data retention, or IaC under GDPR, HIPAA, PCI DSS, SOC 2, ISO 27001, or SOX.
compliance-audit
Static compliance audit with regulatory profiles. v1.14 ships GDPR profile (data subject rights, lawful basis, security measures, accountability). SOC 2 and HIPAA profiles scaffolded as future-markers in PROFILES.md - enable in v1.15+. Stack-agnostic.