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 HirogaKatageri/hirokata --skill qa-mindsetgit clone --depth 1 https://github.com/HirogaKatageri/hirokataWrote 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/hirogakatageri/hirokata/qa-mindset)<a href="https://agentmods.dev/skills/hirogakatageri/hirokata/qa-mindset"><img src="https://agentmods.dev/badge/skills/hirogakatageri/hirokata/qa-mindset.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 | $0.00120 | $0.01277 |
| Opus 5 | $0.00060 | $0.00639 |
| Sonnet 5 | $0.00024 | $0.00255 |
| Haiku 4.5 | $0.00012 | $0.00128 |
Grade A, and why
qa-mindset 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The QA Mindset
This is the discipline shared by the qa-strategist and qa-tester. It is what
separates QA from the chain's reviewers: the reviewers verify that the code matches
the plan; QA validates that the product behaves correctly, including in the cases
nobody specified.
The Five Pillars
-
Validation over verification. Verification asks "did we build the thing right?" Validation asks "did we build the right thing, and what did nobody specify?" The most dangerous bugs live in the gap between the requirement and reality. QA's home turf is unspecified behavior.
-
Disconfirmation, not confirmation. A developer wants the code to pass. QA wants to find where it breaks, and treats "the tests pass" as the start of the investigation, not the end. This includes distrusting tests themselves: a test that never fails when the code is wrong is theater.
-
Empiricism over reasoning. Reading code tells you what it should do. Running it tells you what it does. QA exercises the running system and believes the observation over the source.
-
The oracle problem. Before you can test, answer "how would I know this is wrong?" Half of bad QA is running scenarios with no defined expected outcome. Always state the expected result before observing the actual one.
-
Risk-based triage. You cannot test everything. Prioritize by
likelihood of failure × cost of failure. Auth and payments get hammered; the about-page copy gets a smoke check. Risk sets depth, not whether to cover.
The Hybrid Oracle (testing an existing product)
When auto-authoring tests against software that already exists, the trap is deciding what counts as "correct". The guild uses the hybrid rule:
- Lock current behavior as the regression baseline when it agrees with an oracle (spec/ticket/user) or is clearly sane.
- Flag, don't assert when current behavior contradicts the oracle or fails a what-if sanity check — file a bug instead of encoding the bug as "expected".
- Ask the user when behavior is ambiguous and no oracle exists; record the answer so it becomes the oracle.
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 · +2 lines eb82f1fe4b14
- 8d ago First seen · 120 lines · 120 tokens per session scan A 9c17a2eafec6
qa-mindset is a skill published in the GitHub repository HirogaKatageri/hirokata (5 stars, last pushed yesterday), licensed MIT. It adds 120 tokens to every session and 1,277 once invoked, about $0.0006 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
self-test
A post-coding self-check checklist for reviewing implementation quality and tests. It checks user-visible behavior, data consistency, dependencies, compatibility, code quality, and—when relevant—visual details against a design.
implement
A coding method based on vertical slices: each slice connects the data, interface, display, and tests for one complete path. With a test framework, it follows TDD, meaning tests are written before the smallest implementation and then the code is cleaned up.
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.