Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Raw1mage/patentmcpnpx agentmods add skills/raw1mage/patentmcp/testing-assistantWrote 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/raw1mage/patentmcp/testing-assistant)<a href="https://agentmods.dev/skills/raw1mage/patentmcp/testing-assistant"><img src="https://agentmods.dev/badge/skills/raw1mage/patentmcp/testing-assistant/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/raw1mage/patentmcp/testing-assistant"><img src="https://agentmods.dev/badge/skills/raw1mage/patentmcp/testing-assistant.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 | $0.00021 | $0.01127 |
| Opus 5.5 | $0.00008 | $0.00451 |
| Sonnet 5.5 | $0.00004 | $0.00225 |
| Haiku 4.5 | $0.00002 | $0.00113 |
Grade A, and why
testing-assistant 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 testing-assistant — 1 line 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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Testing Assistant Skill
Expert system for testing and validating the Claude Patent Creator.
FOR CLAUDE: Test scripts in scripts/ directory.
- Go directly to running appropriate test
- Run from project root
- Tests require active venv
- Only run diagnostics if tests fail
When to Use
Running test suites, validating new features, testing after changes, debugging failures, creating tests, setting up CI/CD, performance testing, E2E validation, regression testing.
Testing Pyramid
/\
/ \ E2E (Manual + Automated)
/----\
/ API \ Integration Tests
/--------\
/ Unit \ Unit Tests
/----------\
Strategy: More unit tests (fast, isolated), fewer integration (moderate), minimal E2E (slow).
Test Suite Overview
scripts/
+-- test_install.py # Complete installation validation
+-- test_gpu.py # GPU detection and CUDA
+-- test_bigquery.py # BigQuery connection
+-- test_analyzers.py # Claims, spec, formalities
+-- test_embedding_speed.py # Performance benchmarks
+-- test_checkpoint.py # Index checkpoint system
Quick Test:
python scripts/test_install.py
Manual Testing via Claude
Test MCP tools through Claude Code interface.
Quick Test Examples
1. MPEP Search: "Search MPEP for claim definiteness requirements"
2. Patent Search: "Search for patents about neural networks filed in 2024"
3. Claims Review: "Review these claims: [paste test claims]"
4. Full Review: "/full-review" (with test application)
5. Diagrams: "Create a flowchart for this process: [describe]"
Validation Checklist
[OK] MPEP search returns relevant results
[OK] BigQuery search finds patents
[OK] Claims analyzer identifies issues
[OK] Specification analyzer checks support
[OK] Formalities checker validates format
[OK] Diagrams generate successfully
[OK] Full review workflow completes
[OK] All MCP tools accessible
[OK] Error messages clear and helpful
[OK] Performance acceptable (<2s most ops)
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 · 185 lines · 21 tokens per session scan A 5c76ad50fd0b
testing-assistant is a skill published in the GitHub repository Raw1mage/patentmcp (2 stars, last pushed 2mo ago), licensed MIT. It adds 21 tokens to every session and 1,127 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 testing-assistant, differing in 1 line, and is treated as a copy.
Other skills, from other repositories
test-master
Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation…
axiom-testing
Use when writing ANY test, debugging flaky tests, making tests faster, or choosing Swift Testing vs XCTest. Covers unit tests, UI tests, async testing, test architecture.
designing-tests
Designs and implements testing strategies for any codebase. Use when adding tests, improving coverage, setting up testing infrastructure, debugging test failures, or when asked about unit tests, integration tests, or E2E testing.
testing-blocks
Use this when you have made AEM Edge Delivery Services code changes to blocks, scripts, or styles and need to validate them before opening a pull request. Covers unit testing for utilities and logic, browser testing with Playwright, linting, and guidance on what to test and how.
JMeter Load Testing
Load and performance testing skill using Apache JMeter, covering test plans, thread groups, assertions, listeners, timers, and distributed testing.
06-test
Write and iterate developer-side tests until they pass, or validate a user journey end to end in the browser during implementation. Use when the user wants to add coverage, find what's untested, or walk a flow while building it. Do NOT use for independent acceptance QA or reviewer evidence, auditing test health, or…