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/kao273183/mk-qa-masterWrote 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/kao273183/mk-qa-master/generate)<a href="https://agentmods.dev/commands/kao273183/mk-qa-master/generate"><img src="https://agentmods.dev/badge/commands/kao273183/mk-qa-master/generate/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/kao273183/mk-qa-master/generate"><img src="https://agentmods.dev/badge/commands/kao273183/mk-qa-master/generate.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 | $0.00019 | $0.00465 |
| Opus 5.5 | $0.00008 | $0.00186 |
| Sonnet 5.5 | $0.00004 | $0.00093 |
| Haiku 4.5 | $0.00002 | $0.00047 |
Grade A, and why
generate 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
You are operating as the mk-qa-master agent in test-generation mode.
Follow Flow 2 in the parent SKILL.md.
Target:
$ARGUMENTS
Steps:
-
Decide web vs mobile. If the target starts with
http:///https://, it's web →analyze_url. If it's a bundle id / package name, it's mobile →analyze_screen. Otherwise ask the user. -
Discover. Run
analyze_url(url, timeout_ms=15000)(oranalyze_screen(...)for mobile). Surface the discovered modules (form,cta,tab_bar, etc.) and the candidate test cases per module to the user BEFORE generating. Let them prune if there are too many (>10 modules is usually too many). -
Pick mode.
- If user said "generate everything" →
auto_generate_tests(url=..., tests_per_module=1). Default to 1 test per module; only go higher (3-5) if the user explicitly wants denser coverage. - If user pointed at one specific flow →
generate_test(description= "<the flow>", filename="<slug>", url=..., module=<the_module>).
- If user said "generate everything" →
-
Verify the generated tests run. Run them once with
run_tests(filter="<the_new_test_slug>"). If pytest collection itself fails, the generated file has a syntax issue — surface the error and fix the file before reporting done. -
Report file paths. The generated test file(s) go under
<PROJECT_ROOT>/tests/. List them by absolute path. Tell the user how to re-run:pytest tests/<filename>.
Don't generate without showing the candidate modules first. Auto-
generation that surprises the user with 50 tests is worse than no
generation. The tests_per_module ceiling is 10 but anything above 3 is
usually garbage from the long tail of candidate_tcs.
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 · 45 lines · 19 tokens per session scan A fa8cedaa92e5
generate is a command published in the GitHub repository kao273183/mk-qa-master (37 stars, last pushed 4mo ago), licensed MIT. It adds 19 tokens to every session and 465 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 2026-08-30.
Other commands, from other repositories
multi-page
Smoke test multiple pages in parallel using alethiatellparallel.
smoke
Quick Alethia smoke test — navigate and assert the page loads.
playwright-test-plan
Create test plan for basic operations of the todo app. Test plan should contain around 20 tests.
playwright-test-heal
Run all my tests and fix the failing ones.
qawolf-cli
Manage QA Wolf through the qawolf CLI. Use when asked to create, update, or list coverage requests, bug reports, or maintenance reports; start a run of flows or tags on the QA Wolf platform or read a run's results; list, set, or delete environment variables; manage environments, flows, or tags; run or list flows…
ui-aqa-flow-test-report-analysis
Phase 7 Test Report Analysis of ui-aqa-flow.