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 JeonJe/claude-plugins --skill qa-scenariosgit clone --depth 1 https://github.com/JeonJe/claude-pluginsWrote 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/jeonje/claude-plugins/qa-scenarios)<a href="https://agentmods.dev/skills/jeonje/claude-plugins/qa-scenarios"><img src="https://agentmods.dev/badge/skills/jeonje/claude-plugins/qa-scenarios/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/jeonje/claude-plugins/qa-scenarios"><img src="https://agentmods.dev/badge/skills/jeonje/claude-plugins/qa-scenarios.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 | $0.00097 | $0.02466 |
| Opus 5 | $0.00048 | $0.01233 |
| Sonnet 5 | $0.00019 | $0.00493 |
| Haiku 4.5 | $0.00010 | $0.00247 |
Grade A, and why
qa-scenarios 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 10d 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA Scenarios
Test the feature as users may actually use it, including paths the implementer did not anticipate. Derive behavior from the implementation and running system first; use PRDs or acceptance criteria as additional oracles when available.
Never mark a scenario PASS without observable evidence.
References index
| File | When to read |
|---|---|
| references/scenario-catalog.md | §3 — scenario family selection |
| references/report-template.md | §6 — report skeleton |
Operating contract
- Treat the target feature, implementation diff, running UI/API, and persisted effects as primary inputs.
- Accept PRDs, tickets, designs, and existing tests as optional context. Do not limit coverage to their stated cases.
- Work only in environments and accounts the user has authorized. Prefer local, test, or staging environments.
- Do not perform destructive, irreversible, billable, privacy-sensitive, or production actions without explicit authorization.
- Preserve credentials and personal data. Do not record secrets in commands, screenshots, reports, or tracked files.
- Use existing project boot, browser, database, logging, and E2E workflows when available.
- Distinguish facts observed in the system from inferred expectations and product questions.
- Continue through independent scenarios when one scenario is blocked. Stop only when the blocker prevents meaningful remaining work.
Workflow
1. Fix the test boundary
Identify, from local context where possible: feature entry points (screens, routes, endpoints, jobs, events, commands); changed components and downstream side effects; available environment, account/role, test data, and observability surfaces; actions that need user approval; relevant regressions outside the changed component.
Ask the user only for access, authorization, or a choice that cannot be safely inferred and materially changes the QA. Do not require a PRD.
Record the environment, revision/branch, account role, device/client, and test time so results are reproducible.
What ships with it
2 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.
- 10d ago First seen · 148 lines · 97 tokens per session scan A b4d4195365ce
qa-scenarios is a skill published in the GitHub repository JeonJe/claude-plugins (3 stars, last pushed 1mo ago), licensed MIT. It adds 97 tokens to every session and 2,466 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 2026-08-31.
Other skills, from other repositories
redteam
Run ryk red-team fixtures and summarize results.
orbit
Autonomous pipeline — spec requirements, execute implementation, audit quality, and ship. Runs the full epic-harness orbit cycle in one go. Use when the user says "orbit", "full pipeline", "spec to ship", or describes a feature that needs end-to-end handling.
codex-pipeline
Runs a dev task through the cross-model codex pipeline — spec and held-out tests written here, implementation by mcpcodexcodex, fresh-context diff review, fixes via mcpcodexcodex-reply. Use when the user asks to run the codex pipeline or have Codex or GPT implement something — e.g. "run this through codex", "use the…
systematic-debugging
Systematic debugging approach for errors, test failures, and unexpected behavior. Use when encountering bugs, test failures, errors, or when debugging is needed. Prevents common anti-patterns like random fixes, skipping root cause analysis, and thrashing.
ryk-redteam
Run ryk red-team fixtures and summarize results.
agent-browser
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.