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 hamzaPixl/pixl-ai --skill test-runnergit clone --depth 1 https://github.com/hamzaPixl/pixl-aiWrote 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/hamzapixl/pixl-ai/test-runner)<a href="https://agentmods.dev/skills/hamzapixl/pixl-ai/test-runner"><img src="https://agentmods.dev/badge/skills/hamzapixl/pixl-ai/test-runner/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/hamzapixl/pixl-ai/test-runner"><img src="https://agentmods.dev/badge/skills/hamzapixl/pixl-ai/test-runner.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 | $0.00067 | $0.02512 |
| Opus 5.5 | $0.00027 | $0.01005 |
| Sonnet 5.5 | $0.00013 | $0.00502 |
| Haiku 4.5 | $0.00007 | $0.00251 |
Grade A, and why
test-runner 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.
How it starts
The opening of the file, as written. The whole thing — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Runner
Smart, tiered test runner for Python and TypeScript codebases. Never runs all tests blindly — discovers, categorizes, then runs targeted subsets.
Step 0: Detect Language
Determine the project language and test framework:
| Signal | Framework | Runner command |
|---|---|---|
pyproject.toml, pytest.ini, setup.cfg with pytest config |
pytest | uv run python -m pytest or pytest |
vitest.config.ts / vitest.config.js / vitest in package.json |
vitest | npx vitest or bun vitest |
jest.config.ts / jest.config.js / jest in package.json |
jest | npx jest or bun jest |
If both Python and TypeScript tests exist, ask the user which to run. If unclear, default to whichever has a config file in the project root.
Python (pytest)
Step 1: Discover
- Locate pytest config (
pyproject.toml→[tool.pytest.ini_options],pytest.ini,setup.cfg) - Find test directories (
tests/,test/,**/tests/) - Count tests per directory:
uv run python -m pytest <dir> --co -q 2>&1 | tail -1 - List registered markers:
uv run python -m pytest --markers 2>&1 | head -20 - Check for conftest.py files and fixtures
Report discovery summary before proceeding.
Step 2: Categorize
Classify tests into tiers by markers and file naming patterns:
| Tier | Markers / Patterns | Typical count |
|---|---|---|
| smoke | test_version.py, test_health.py, test_sandbox_routes.py |
5-20 |
| unit/fast | No slow/comprehensive/e2e marker |
Bulk of suite |
| slow | @pytest.mark.slow, test_performance.py, ThreadPool usage |
10-50 |
| comprehensive | @pytest.mark.comprehensive, artifact generation |
5-20 |
| e2e | @pytest.mark.e2e, workflow execution, multi-step flows |
5-30 |
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 · 216 lines · 67 tokens per session scan A dabd74fc1c4d
test-runner is a skill published in the GitHub repository hamzaPixl/pixl-ai (2 stars, last pushed 6mo ago), licensed MIT. It adds 67 tokens to every session and 2,512 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
test-master
Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation…
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
critique
Adversarial design critique of the current work. Render it, look at it, and argue for rejection. Run after the gates are green, never instead of them.