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 fugazi/test-automation-skills-agents --skill qa-investigationgit clone --depth 1 https://github.com/fugazi/test-automation-skills-agentsWrote 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/fugazi/test-automation-skills-agents/qa-investigation)<a href="https://agentmods.dev/skills/fugazi/test-automation-skills-agents/qa-investigation"><img src="https://agentmods.dev/badge/skills/fugazi/test-automation-skills-agents/qa-investigation/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/fugazi/test-automation-skills-agents/qa-investigation"><img src="https://agentmods.dev/badge/skills/fugazi/test-automation-skills-agents/qa-investigation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00094 | $0.01540 |
| Opus 5 | $0.00047 | $0.00770 |
| Sonnet 5 | $0.00019 | $0.00308 |
| Haiku 4.5 | $0.00009 | $0.00154 |
Grade A, and why
qa-investigation 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA Investigation
A persistent, file-backed investigation journal for a specific failing test. This is the execution layer: it resolves a concrete failure. It does not validate strategy or architecture (grill-me-qa) nor generate QA deliverables (qa-manual-istqb).
The core idea: your context window is volatile RAM; the filesystem is persistent disk. Writing goals, evidence, and decisions to markdown prevents context drift during a long investigation.
When to Use This Skill
- A test fails intermittently (flaky) or deterministically (bug), and you need the root cause.
- The investigation spans many tool calls, multiple runs, or more than one session.
- You want a durable record of what you found, decided, and why.
When NOT to Use This Skill
- Authoring a test from scratch — use the relevant automation/framework skill.
- Designing a framework or coverage strategy — strategy validation (
grill-me-qa) or artifact generation (qa-manual-istqb). - Simple questions or quick lookups (fewer than ~5 tool calls).
- General review of non-test production code.
The boundary is not "is it a selector / browser issue / timeout" — any of those can be worth investigating. The boundary is whether the request needs a persistent, multi-step root-cause investigation or is a one-shot tactical task. If uncovering the why takes evidence, runs, and iteration, use this skill.
Tool Agnosticism
This method is independent of any test framework — web, API, mobile, embedded, unit, load. Terms like "browser", "selector", "network requests", or "CI vs local" are illustrative, not requirements; substitute the equivalent in your stack.
Core Process
The phases are the same whether the failure is flaky or a deterministic bug. The skill discovers the classification during triage — it does not assume it up front.
Phase 1: Reproduction & Triage
- Reproduce reliably; isolate variables (parallelism, repeat count, environment, data/state).
- Determine: intermittent (flaky), deterministic (bug), or non-reproducible? This is a finding, not an input.
- Record the classification and the evidence that supports it.
- Goal: a confirmed reproduction or a documented non-reproducible failure.
What ships with it
4 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.
- 9d ago First seen · 99 lines · 94 tokens per session scan A e923ef302869
qa-investigation is a skill published in the GitHub repository fugazi/test-automation-skills-agents (234 stars, last pushed 9d ago), licensed MIT. It adds 94 tokens to every session and 1,540 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
bestow-curse
Bestow Curse saddles a target with a lasting disadvantage. The real-world version is constraint injection: deliberately adding friction, limitations, or handicaps to see how a system, process, or team adapts. This is the skill of resilience testing through artificial adversity — bandwidth throttling, feature removal…
confusion
Confusion makes targets act randomly and unpredictably. The real-world version is chaos engineering: injecting controlled randomness, unexpected inputs, and edge cases to discover how systems behave when things go wrong. This is fuzzing, monkey testing, and the art of breaking things on purpose so they do not break by…
dogfood
Systematic exploratory QA testing of web applications — find bugs, capture evidence, and generate structured reports.
credit-note-fixer
Fix the tiny credit-note formatting bug and rerun the exact targeted test command.
typescript-testing
Select and run TypeScript SDK verification for packages, examples, type checks, linting, builds, Vitest suites, Effect v4 CLI tests, and runtime E2E tests. Use when adding tests, diagnosing TypeScript CI, choosing a focused test command, validating TypeScript package changes, or writing/porting CLI tests against…
bug-fixing
Fix defects in the Composio SDK repository with focused reproduction, root-cause analysis, regression tests, and narrow verification. Use when the user reports a bug, failing test, CI regression, runtime defect, or incorrect SDK behavior. Do not use for new feature design or broad refactors.