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 pnakhat/qa-ai-repo --skill qa-strategygit clone --depth 1 https://github.com/pnakhat/qa-ai-repoWrote 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/pnakhat/qa-ai-repo/qa-strategy)<a href="https://agentmods.dev/skills/pnakhat/qa-ai-repo/qa-strategy"><img src="https://agentmods.dev/badge/skills/pnakhat/qa-ai-repo/qa-strategy/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/pnakhat/qa-ai-repo/qa-strategy"><img src="https://agentmods.dev/badge/skills/pnakhat/qa-ai-repo/qa-strategy.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 | $0.00128 | $0.01832 |
| Opus 5 | $0.00064 | $0.00916 |
| Sonnet 5 | $0.00026 | $0.00366 |
| Haiku 4.5 | $0.00013 | $0.00183 |
Grade A, and why
qa-strategy 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA Strategy
Generate a QA strategy that fits this team — not a generic checklist. The strategy is only as good as its inputs, so always gather the intake first, then produce the strategy against a consistent template. Every recommendation traces back to a stated input and lands as a measurable gate, not an aspiration.
How to run
- Collect the intake. Ask the questions in
intake.md. Ask them in batches (grouped by section), not all at once. If the user has already supplied some answers (in the prompt, a repo, a doc), pre-fill those and only ask what's missing or ambiguous. Do not invent answers — if something is unknown, mark itTBDand note the assumption you'll proceed with. - Infer what you can from the codebase when available: languages, frameworks, existing test dirs, CI config, coverage — confirm rather than ask.
- Score risk. Rank features/flows by likelihood × impact using the rubric
in
reference.md. This drives where coverage goes. - Write the strategy using
strategy-template.md. Every recommendation must trace back to an input (e.g. "daily deploys → block merges on a fast smoke suite"). Tailor depth to team size and maturity. - Make it actionable. End with a phased roadmap (Now / Next / Later) with
concrete first steps, owners, and success metrics defined per
reference.md— not aspirations.
Intake first — why it's non-negotiable
The single biggest failure mode is writing a generic strategy that ignores the team's reality. A strategy built without inputs is filler.
| ✅ Do | ❌ Don't |
|---|---|
Ask the intake.md questions in grouped batches |
Dump all 25 questions at once, or ask none |
| Pre-fill from the repo/CI config, then confirm | Ask for facts the codebase already shows |
Mark unknowns TBD + state the assumption |
Invent a stack, team size, or cadence |
| Proceed on terse answers; note what's missing | Block on a full interview before offering value |
| Tie every recommendation to a specific input | Recommend tools the team's stack can't use |
What ships with it
3 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.
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 · 136 lines · 128 tokens per session scan A f524f335ec83
qa-strategy is a skill published in the GitHub repository pnakhat/qa-ai-repo (2 stars, last pushed 2mo ago), licensed MIT. It adds 128 tokens to every session and 1,832 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
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.