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/kensaurus/cursor-kenjiWrote 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/kensaurus/cursor-kenji/test)<a href="https://agentmods.dev/commands/kensaurus/cursor-kenji/test"><img src="https://agentmods.dev/badge/commands/kensaurus/cursor-kenji/test/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/kensaurus/cursor-kenji/test"><img src="https://agentmods.dev/badge/commands/kensaurus/cursor-kenji/test.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 | $0.00025 | $0.00520 |
| Opus 5.5 | $0.00010 | $0.00208 |
| Sonnet 5.5 | $0.00005 | $0.00104 |
| Haiku 4.5 | $0.00003 | $0.00052 |
Grade A, and why
test 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 27d 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
/test
Pick the test skill that matches the target. Do not run one generic suite and call it done.
This command is a thin entry point. Pick the right skill for the target:
test-unit— write and improve unit tests (Jest, Vitest, pytest, Go test).test-playwright— PDCA the changes you just made: drive the live app for the touched flows + blast radius and fix pain points as you go.test-qa— full-app webapp QA, dynamic user stories, CRUD verification.test-exploratory— unscripted monkey wander as GUEST then LOGGED-IN, then a guest-vs-authed diff. Discovery only — do not fix in-pass.test-visual-regression— Playwright screenshot baselines and CI pixel diffs.test-load— k6/Artillery throughput, latency percentiles, breaking point. Never hit prod unsigned.mobile-emulator-test— native mobile builds (RN/Expo/Capacitor/Flutter) on Android emulator.
All browser QA is manual and headed. Drive a visible browser through playwright-cli (
npx --yes @playwright/cli@latest -s=<session> …, with--headedonopen) one real user action at a time — never*.spec.ts,npx playwright test, or driving the UI througheval/run-code. First read theprotocol-browser-anti-stallskill (Rule 0).
Use /test to explicitly trigger testing. Otherwise, say "test this", "test my changes with playwright", "write tests", "QA the app", "monkey test the app", "guest vs logged in", "add visual regression tests", "load test this", or "smoke-test on emulator" and the appropriate skill auto-fires.
Highest-impact combo: test-exploratory → workflow-feedback-to-closure → test-playwright (wander twice → ticket real bugs → lock the worst ones). Pre-release: wander first, then workflow-quality-gate.
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.
- 27d ago Changed · +1 lines e0ccefb5b1f6
- 28d ago Changed 301ccd4cb2be
- 1mo ago First seen · 29 lines · 25 tokens per session scan A 76a15e913571
test is a command published in the GitHub repository kensaurus/cursor-kenji (9 stars, last pushed 22d ago), licensed MIT. It adds 25 tokens to every session and 520 once invoked, about $0.0001 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 commands, from other repositories
gauntlet-loop
Beat a real-world quality bar via builder/critic loops; critics alone decide when each part passes.
prompt-eval-debug
Debug any prompt with a tiny eval suite (control, edge, boundary), failure diagnosis, and smallest next change, no blind rewrite.
tdd
Canon TDD (specify, encode, fulfill) with one test at a time, approval gates, and kitchen-cleaning refactor when needed.
run-all-tests-and-fix
Run full test suite and fix failures.
write-unit-tests
Write meaningful unit tests for target code.
check-coverage
Check test coverage, identify gaps, and suggest which code needs tests.