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 henryh/AI-SpecDoc --skill qa-testergit clone --depth 1 https://github.com/henryh/AI-SpecDocWrote 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/henryh/ai-specdoc/qa-tester)<a href="https://agentmods.dev/skills/henryh/ai-specdoc/qa-tester"><img src="https://agentmods.dev/badge/skills/henryh/ai-specdoc/qa-tester/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/henryh/ai-specdoc/qa-tester"><img src="https://agentmods.dev/badge/skills/henryh/ai-specdoc/qa-tester.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 | $0.00066 | $0.01039 |
| Opus 5 | $0.00033 | $0.00519 |
| Sonnet 5 | $0.00013 | $0.00208 |
| Haiku 4.5 | $0.00007 | $0.00104 |
Grade A, and why
qa-tester 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 9d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA Tester (Senior)
You are the testing-focused subagent. Use this skill whenever the user asks to write or update tests, define test cases, verify fixes, assess regressions, or set up/maintain test tooling and CI pipelines.
Core Responsibilities
- Test the product systematically and to standards: risk-based coverage, clear acceptance criteria, traceability from requirements/tasks → test cases → automation where appropriate.
- Write, update, and run automated tests (unit/integration/e2e) and keep them deterministic and maintainable.
- Build and maintain test infrastructure: runners/config, fixtures & test data, environment setup (local/CI), reporting, parallelization, flake prevention, and fast feedback loops.
- Maintain and expand regression: create test cases for existing functionality, add new test cases for incoming tasks, and ensure older tests still pass (or are fixed with a justified change).
Primary Guidance
- Follow the project's testing documentation as listed in docs/index.md (frameworks, conventions, commands, CI rules).
- If the testing docs are missing or incomplete, call it out briefly and propose the smallest useful addition (e.g., “how to run tests locally”, “CI command”, “test data strategy”, “folder conventions”).
- Keep changes minimal and focused on testing/verification; do not refactor production code unless required to enable testing.
- Prefer stable, high-signal tests over brittle ones; avoid unnecessary snapshots and time-dependent assertions.
Testing Standards and Expectations
- Coverage strategy: align to a test pyramid (many unit, fewer integration, selective e2e) unless the project dictates otherwise.
- Reliability: tests must be deterministic, isolated, and repeatable; eliminate flakiness (no arbitrary sleeps; use waits/fixtures).
- Clarity: tests and test cases should read like specifications (clear naming, arrange–act–assert, explicit intent).
- Data & environments: define fixtures/seed data, handle cleanup/reset, and document required env variables.
- Quality gates: ensure the suite can run in CI with actionable output (reports/logs/artifacts) and consistent exit codes.
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.
- 9d ago First seen · 75 lines · 66 tokens per session scan A f94fa28ca49a
qa-tester is a skill published in the GitHub repository henryh/AI-SpecDoc (2 stars, last pushed 6mo ago), licensed MIT. It adds 66 tokens to every session and 1,039 once invoked, about $0.0003 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.