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 agentmods add skills/jarroslav/agentic-os/qa-case-generatornpx skills add Jarroslav/agentic-os --skill qa-case-generatorgit clone --depth 1 https://github.com/Jarroslav/agentic-osWrote 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/jarroslav/agentic-os/qa-case-generator)<a href="https://agentmods.dev/skills/jarroslav/agentic-os/qa-case-generator"><img src="https://agentmods.dev/badge/skills/jarroslav/agentic-os/qa-case-generator.svg" alt="Measured on agentmods" 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 | $0.00141 | $0.02207 |
| Opus 5 | $0.00071 | $0.01104 |
| Sonnet 5 | $0.00028 | $0.00441 |
| Haiku 4.5 | $0.00014 | $0.00221 |
Grade A, and why
qa-case-generator 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 6d 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 — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.
qa-case-generator
Convert a single work-item's acceptance criteria into functional test-case documents (manual and API level), gated by an explicit human approval, with an optional push to a config-driven test-management backend.
The pipeline is deterministic on purpose. A fixed phase order, hard halt conditions, and a formulaic coverage count keep separate agent runs on the same ticket producing the same shape of output. Do not improvise around the gates — they are the contract.
Methodology owner. How functional cases are derived and shaped is defined by the
test-casesblueprint inagentic-qe(skills/qe-blueprints/references/catalog/design/test-cases.md). This skill executes; the blueprint is the authority on method. If the two ever disagree, the blueprint wins and this file is what gets corrected — one source of truth, so two agents cannot follow two different sets of practices.
When to use
- You have one work-item id (
PROJ-123format) from Jira, Azure DevOps, GitHub, or GitLab and need functional test cases. - Invocation form:
qa-case-generator PROJ-123. - A QA engineer needs manual or API case documents they can review and file.
Do not use this skill for unit or integration tests (TDD workflow),
code-coverage analysis (code-review), automation-framework setup, test
execution, or result analysis. Never derive tests by reading source code.
Hard constraints
Blast radius: R0 → R1 (run-artifact writes) through phase 5; R3 (external side-effect) only in phase 6, always behind the human review gate.
| Rule | Enforcement |
|---|---|
| Never read source code | No Read/Grep/Glob on repository code files |
| Functional tests only | No unit/integration/coverage output |
| Not auto-invoked | Other pipeline skills must not call this skill |
| Sync needs consent | Phase 6 runs only after explicit user yes |
| QA docs required | Halt to qa-baseline if guides absent |
| Clear criteria required | Halt below 50% AC confidence |
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- evals/evals.json 7.5 KB
- evals/fixtures/story-api-only.json 1.5 KB
- evals/fixtures/story-clear-ac.json 1.3 KB
- evals/fixtures/story-high-risk.json 2.4 KB
- evals/fixtures/story-missing-ac.json 1.1 KB
- evals/fixtures/story-vague-ac.json 821 B
- README.md 3.9 KB
- references/case-authoring.md 8.3 KB
- references/case-sync.md 6.1 KB
- references/review-gate.md 5.3 KB
- references/suite-planning.md 7.0 KB
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.
- 6d ago First seen · 236 lines · 141 tokens per session scan A 428478ece96b
qa-case-generator is a skill published in the GitHub repository Jarroslav/agentic-os (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 141 tokens to every session and 2,207 once invoked, about $0.0007 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.