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/Jott2121/agent-gateWrote 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/jott2121/agent-gate/20-tests)<a href="https://agentmods.dev/rules/jott2121/agent-gate/20-tests"><img src="https://agentmods.dev/badge/rules/jott2121/agent-gate/20-tests/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/jott2121/agent-gate/20-tests"><img src="https://agentmods.dev/badge/rules/jott2121/agent-gate/20-tests.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 | $0.00000 | $0.00194 |
| Opus 5.5 | $0.00000 | $0.00078 |
| Sonnet 5.5 | $0.00000 | $0.00039 |
| Haiku 4.5 | $0.00000 | $0.00019 |
Grade A, and why
20-tests 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 4d 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
Tests
- Write the failing test first, show it failing, then make it pass. Paste both runs in the PR.
- Test behavior, not implementation. Exercise real entry points (e.g. call the MCP tool, not just import it).
- Every guard/gate gets a deny-path test: error, timeout, malformed input, empty input.
- Never add
skip,xfail, or loosen assertions to get green. Never lower--cov-fail-underor mutation thresholds. - Tests must run offline with no API keys; live-model tests are marked and deselected by default.
- No network, no wall-clock sleeps, no order dependence. Use fixtures with fixed seeds.
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.
- 4d ago First seen · 14 lines · 0 tokens per session scan A b23177424aad
20-tests is a cursor rule published in the GitHub repository Jott2121/agent-gate (3 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 194 tokens. 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 2026-10-12.
Other cursor rules, from other repositories
workflow
BDD-style workflow, UI screenshots in the PR, HTTP OpenAPI, config schema and CLI packaging sync before lint, final checks, the comment on an issue a merge closes and the cleanup after the merge.
mcpnuke-tests
Test conventions for mcpnuke — enforces TDD workflow.
python-code-validator
Validate generated Python at every step, not once at the end.
python-testing
This rule provides comprehensive guidance for testing Python applications before production deployment. It covers test-driven development (TDD), different types of tests, using both mock and real data, and implementing testing loops to ensure code quality.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.