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.
git clone --depth 1 https://github.com/Raw1mage/patentmcpWrote 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/commands/raw1mage/patentmcp/review-epo-claims)<a href="https://agentmods.dev/commands/raw1mage/patentmcp/review-epo-claims"><img src="https://agentmods.dev/badge/commands/raw1mage/patentmcp/review-epo-claims/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/commands/raw1mage/patentmcp/review-epo-claims"><img src="https://agentmods.dev/badge/commands/raw1mage/patentmcp/review-epo-claims.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 | $0.00022 | $0.02304 |
| Opus 5.5 | $0.00009 | $0.00922 |
| Sonnet 5.5 | $0.00004 | $0.00461 |
| Haiku 4.5 | $0.00002 | $0.00230 |
Grade A, and why
review-epo-claims 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 1mo 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.
This is a copy
100% identical to review-epo-claims — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.
EPO Claims Review
Automated analysis of patent claims for European Patent Office compliance with Art. 84 EPC / Rule 43 EPC / EPO Guidelines Part F.
Focus Area: $ARGUMENTS
What This Command Does
Performs comprehensive EPO claims analysis:
-
Clarity Analysis (Art. 84 EPC):
- Identifies unclear or ambiguous terms
- Detects relative terms without reference points
- Checks for consistent terminology throughout claims
- Validates technical feature definitions
-
Conciseness Check (Art. 84 EPC):
- Detects redundant claims
- Identifies unnecessarily complex claim structures
- Checks for duplicate scope between claims
- Validates claim set economy
-
Support by Description (Art. 84 EPC):
- Verifies all claimed features are disclosed in the description
- Checks claim scope does not exceed disclosure
- Validates generalizations from specific examples
- Identifies unsupported claim breadth
-
Claim Structure (Rule 43 EPC):
- Validates two-part form (preamble + characterizing portion) where appropriate
- Checks independent claim structure
- Validates dependent claim references
- Verifies claim categories (product, process, apparatus, use)
-
Issue Categorization:
- Critical: Will cause objection under Art. 84 EPC
- Important: May cause objection or limit claim scope
- Minor: Best practice improvements per EPO Guidelines
Who This Is For
- Patent attorneys preparing EP applications
- Applicants responding to EPO Art. 84 objections
- Practitioners converting US claims to EPO format
- Quality assurance before EP filing or Euro-PCT entry
Process
Step 1: Provide Claims
You can provide claims in three ways:
Option 1: Paste claims directly
/review-epo-claims
> Paste your claims text, then type 'END' on a new line:
1. A system for authenticating users, characterised in that
the system comprises a distributed ledger configured to
store and verify credentials.
2. The system according to claim 1, wherein the distributed
ledger is a blockchain.
END
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.
- 1mo ago First seen · 327 lines · 22 tokens per session scan A dccdb6b9aa4e
review-epo-claims is a command published in the GitHub repository Raw1mage/patentmcp (2 stars, last pushed 2mo ago), licensed MIT. It adds 22 tokens to every session and 2,304 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to review-epo-claims, differing in 0 lines, and is treated as a copy.
Other commands, from other repositories
art-3d-pass
Review 3D art assets for export conventions, rigs, animation clips, materials, lighting, and LOD compliance.
cert-check
Review the current state against certification and platform compliance expectations.
comply
Check a plan's or diff's compliance with this repo's rule files — deterministic selection, one starved brief per rule, verdicts re-checked against the plan.
alex
Invoke Alex, your Senior UK Legal Counsel for legal advice, contracts, compliance, and risk assessment.
legal
Invoke Legal Counsel for contracts, GDPR, compliance, and legal risk assessment.
snr-privacy
Build the privacy pack — data inventory from the code, an accurate privacy policy, working cookie consent, and an automated self-service deletion pipeline.