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.
npx skills add zajalist/hayba --skill hayba-qa-smoke-testgit clone --depth 1 https://github.com/zajalist/haybaWrote 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/zajalist/hayba/hayba-qa-smoke-test)<a href="https://agentmods.dev/skills/zajalist/hayba/hayba-qa-smoke-test"><img src="https://agentmods.dev/badge/skills/zajalist/hayba/hayba-qa-smoke-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/skills/zajalist/hayba/hayba-qa-smoke-test"><img src="https://agentmods.dev/badge/skills/zajalist/hayba/hayba-qa-smoke-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 | $0.00031 | $0.00368 |
| Opus 5.5 | $0.00012 | $0.00147 |
| Sonnet 5.5 | $0.00006 | $0.00074 |
| Haiku 4.5 | $0.00003 | $0.00037 |
Grade A, and why
hayba-qa-smoke-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 13d 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
Smoke test a gameplay change
When to use
Use after a concrete edit with a known user-facing behavior and likely regression area. Define one success observation and one failure observation before running tests.
Tool routing
- Discover a relevant automation with
test_list; run a focused subset throughtest_runand inspect failures withtest_get_log. Avoid a broad test sweep when one subsystem can answer the question. - Check
editor_get_statebefore PIE. If this workflow startseditor_start_piefor a user-visible path, capture it witheditor_pie_screenshotwhen visual behavior matters and always calleditor_stop_pieafterward, including on failure. Leave an already running user PIE session alone. For scene mutations, runvalidator_runas a separate post-condition check after PIE stops. - Treat a test runner's success as evidence for the assertions it executed. It does not replace a PIE interaction or a visual check when those are the requested behavior.
- If this pass makes an accepted scene repair, read back the changed actor or world state, save the exact active map with
level_save, and inspect saved, dirty, and verified status. Re-read the edit after saving; if persistence is uncertain, report it as unsaved and route it to hayba-world-save-integrity.
Evidence
Report test names and result, the PIE action and observed response, screenshot if relevant, validation findings, and remaining untested conditions. If a test could not run, state the reason and leave that verification open.
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.
- 13d ago First seen · 25 lines · 31 tokens per session scan A 8577d8172c13
hayba-qa-smoke-test is a skill published in the GitHub repository zajalist/hayba (13 stars, last pushed 3d ago), licensed MIT. It adds 31 tokens to every session and 368 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 2026-10-04.
Other skills, from other repositories
pn-game-logic
Guides game loops, state machines, input handling, collision, scoring, and save state. Use when implementing game logic; covers architecture patterns for 2D/3D games.
unreal-playtest-delivery
Use when Unreal Engine work must be compiled, exercised in PIE, saved and reopened, packaged, launched, smoke-tested, or triaged from logs before a completion or delivery claim.
V3 Core Implementation
Core module implementation for claude-flow v3. Implements DDD domains, clean architecture patterns, dependency injection, and modular TypeScript codebase with comprehensive testing.
team-polish
Orchestrate the polish team — performance-analyst, technical-artist, sound-designer, qa-tester — to optimize and harden a feature or area.
work
Deliver one maintainer-approved EmDash issue, choosing the bug-fix path for a defect and the direct implementation path for an enhancement or task.
unity-agent-workflows
Use for AI-assisted Unity work that needs live repo discovery, project-derived routing, runtime-owner proof, runtime-visible output hard stops, runtime numeric proof for repeated visible-output failures, state-step guards, multi-agent scope ownership, modular C#/asmdef safety, UI/scene/visual asset gates, data-first…