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/VerificateAI/verificate-mcp-quickstartWrote 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/rules/verificateai/verificate-mcp-quickstart/verificate-gate)<a href="https://agentmods.dev/rules/verificateai/verificate-mcp-quickstart/verificate-gate"><img src="https://agentmods.dev/badge/rules/verificateai/verificate-mcp-quickstart/verificate-gate/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/rules/verificateai/verificate-mcp-quickstart/verificate-gate"><img src="https://agentmods.dev/badge/rules/verificateai/verificate-mcp-quickstart/verificate-gate.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 | $0.00240 | $0.00240 |
| Opus 5.5 | $0.00096 | $0.00096 |
| Sonnet 5.5 | $0.00048 | $0.00048 |
| Haiku 4.5 | $0.00024 | $0.00024 |
Grade A, and why
verificate-gate 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.
What it actually says
Verificate gate (hard rules)
- Every substantive code change MUST be passed through the
validate_ai_outputtool (the complete change, not a fragment) before it is presented as done. - A REJECTED verdict is a stop: fix every finding, re-validate, and repeat until approved. Never present rejected code as complete, never summarise away findings, and never soften or reinterpret the verdict.
- Before implementing any new feature or refactor, the implementation plan MUST
pass
validate_planfirst, with real context (system, scale, constraints). - Claims like "tests pass", "integrated", or "deployed" require proof (command output), not assertion.
- These rules override speed. If the Verificate MCP server is unreachable, say so and stop — do not skip validation silently.
Setup: set the VERIFICATE_TOKEN environment variable with the token from your dashboard (30-day free trial, no card: https://verificate.ai/auth/signup).
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 · 22 lines · 240 tokens per session scan A 1add04639d14
verificate-gate is a cursor rule published in the GitHub repository VerificateAI/verificate-mcp-quickstart (1 stars, last pushed 1mo ago), licensed MIT. It adds 240 tokens to every session, about $0.0010 per session on Opus 5.5. 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 2026-08-31.
Other cursor rules, from other repositories
jest
Jest: describe/it, matchers, mocking, async testing.
testing
Testing: test design, mocking strategy, coverage philosophy.
playwright
Playwright: e2e testing, page objects, fixtures, assertions.
pytest
You are an expert in pytest testing. Follow these rules.
vitest
Vitest: unit testing, mocking, coverage, snapshot testing.
cypress
Cypress: cy commands, selectors, fixtures, intercepts.