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 liza-mas/liza --skill testinggit clone --depth 1 https://github.com/liza-mas/lizaWrote 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/liza-mas/liza/testing)<a href="https://agentmods.dev/skills/liza-mas/liza/testing"><img src="https://agentmods.dev/badge/skills/liza-mas/liza/testing/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/liza-mas/liza/testing"><img src="https://agentmods.dev/badge/skills/liza-mas/liza/testing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 37 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00004 | $0.00676 |
| Opus 5.5 | $0.00002 | $0.00270 |
| Sonnet 5.5 | $0.00001 | $0.00135 |
| Haiku 4.5 | $0.00000 | $0.00068 |
Grade A, and why
testing 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.
How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tests are the immune system — they reject bugs, not document them.
Test Truth Table
| Code | Test | Interpretation |
|---|---|---|
| Working | Green | Good |
| Buggy | Red | Good (bug exposed) |
| Working | Red | Wrong expectations |
| Buggy | Green | DANGEROUS |
| Unknown | Red | STOP — use Analysis Framework below |
ANTI-PATTERN: The most dangerous instinct is to "fix" failing tests by accepting whatever source currently does.
When Tests Fail
Ask for context:
- Is the code in production? Not a guarantee of correctness, yet to consider
- Is the test much more recent than the source code? Could explain wrong expectations
Default heuristic: Tests encode intent; assume the test is correct until evidence suggests otherwise. Source drifts; tests usually don't drift without reason.
Analysis Framework:
- Examine both logics independently
- Consider system design: method contract, error patterns
- Identify sounder logic given context
- When uncertain, ask user
- Type hints may be wrong — verify actual runtime behavior before trusting signatures
Test Modification
FORBIDDEN without approval:
- Changing assertions to match buggy behavior
- Weakening expectations
- Adding exception handlers to mask failures
Allowed: Fresh repro tests capturing current failure (existing tests untouched).
Writing Tests
Quality Standards:
- Deterministic, behavioral testing over type checking
- Exception testing with message validation:
pytest.raises(ValueError, match="...") - Systematic edge cases: None, boundaries, dates
- Branch coverage: success and failure paths
Assertion Strength: Would this assertion pass for a broken implementation? If yes (tautology, type-only, existence-only, shape-only), strengthen it.
Mocking Discipline: Test the code, not the scaffolding. Heavy mock setup suggests you're testing assumptions about dependencies, not behavior. Mock external boundaries (APIs, DBs, filesystems), not internal logic. A resource holding logic under test (SQL functions, migrations) is not a boundary: test that logic against the real resource at its contract, unless the proof environment says otherwise, and keep its callers on fakes.
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 Changed · +5 lines 48c26ddc60c8
- 1mo ago First seen · 74 lines · 4 tokens per session scan A 3fd98b1e126f
testing is a skill published in the GitHub repository liza-mas/liza (410 stars, last pushed today), licensed Apache-2.0. It adds 4 tokens to every session and 676 once invoked, about $0.0000 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 skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
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.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.