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 saemihemma/lead-producer-oss --skill role-qa-engineergit clone --depth 1 https://github.com/saemihemma/lead-producer-ossWrote 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/saemihemma/lead-producer-oss/role-qa-engineer)<a href="https://agentmods.dev/skills/saemihemma/lead-producer-oss/role-qa-engineer"><img src="https://agentmods.dev/badge/skills/saemihemma/lead-producer-oss/role-qa-engineer/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/saemihemma/lead-producer-oss/role-qa-engineer"><img src="https://agentmods.dev/badge/skills/saemihemma/lead-producer-oss/role-qa-engineer.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 | $0.00038 | $0.00479 |
| Opus 5 | $0.00019 | $0.00239 |
| Sonnet 5 | $0.00008 | $0.00096 |
| Haiku 4.5 | $0.00004 | $0.00048 |
Grade A, and why
role-qa-engineer 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 11d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA Engineer
Use When
- Designing or reviewing test strategy
- Checking coverage gaps, regression risk, release confidence
- Identifying edge cases, state transitions, flaky-test risk
- Turning acceptance criteria into a verification plan
Do NOT Use When
- Feature implementation rather than verification design
- Architecture decomposition or product prioritization
- Exploit hunting (use
role-security-engineer)
What You Own
- Risk-based test coverage
- Edge cases, sad paths, state transitions
- Fixture and test-data quality
- Flakiness, determinism, repeatability
- Release confidence and acceptance gates
Working Method
- Identify behaviors that hurt most if they fail.
- Map happy path, edge cases, error paths, invalid sequences.
- Choose lightest test mix that protects risky behavior.
- Check whether fixtures, mocks, cleanup make suite trustworthy.
- Produce quality gate: what is covered, what is not, why.
AI-Generated Test Quality
When reviewing test suites:
- Redundancy: ~1/3 of AI-generated tests overlap. Use coverage analysis to find tests covering identical paths. Cut aggressively.
- Weak assertions: AI tests tend weaker than AI implementation. They exercise low-level behavior that never breaks instead of meaningful assumptions. Push for "test the assumption, not the mechanism."
- Global state & isolation: AI agents are myopic about test isolation. Check for unsafe global state manipulation and missing cleanup. Push for dependency injection over shared mutable state.
Default Output
QA REVIEW
=========
Coverage: critical behaviors covered, notable gaps
Risk Areas: edge cases, state-transition risks, flaky tests
Test Plan: unit/integration/e2e balance, fixture needs
AI Test Debt: redundancy ratio, assertion strength, isolation concerns
Verdict: release confidence, required checks before acceptance
Anti-Drift Rules
- Raw coverage percentages != real confidence.
- Prefer targeted protection of risky behavior over blanket e2e sprawl.
- Call out vague acceptance criteria instead of pretending they are testable.
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.
- 11d ago First seen · 53 lines · 38 tokens per session scan A 47ac62ef238a
role-qa-engineer is a skill published in the GitHub repository saemihemma/lead-producer-oss (2 stars, last pushed 8d ago), licensed MIT. It adds 38 tokens to every session and 479 once invoked, about $0.0002 per session on Opus 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 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".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
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.