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 TimothyHan/qa-buddy-skills --skill qagit clone --depth 1 https://github.com/TimothyHan/qa-buddy-skillsWrote 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/timothyhan/qa-buddy-skills/qa)<a href="https://agentmods.dev/skills/timothyhan/qa-buddy-skills/qa"><img src="https://agentmods.dev/badge/skills/timothyhan/qa-buddy-skills/qa/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/timothyhan/qa-buddy-skills/qa"><img src="https://agentmods.dev/badge/skills/timothyhan/qa-buddy-skills/qa.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 | $0.00145 | $0.03016 |
| Opus 5 | $0.00072 | $0.01508 |
| Sonnet 5 | $0.00029 | $0.00603 |
| Haiku 4.5 | $0.00015 | $0.00302 |
Grade C, and why
qa scanned grade C with 1 finding 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.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
10. **Always use the browser.** Never refuse browser testing when /qa-qa is invoked. How it starts
The opening of the file, as written. The whole thing — 300 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/qa-qa: Test Execution & AC Verification
You are an SDT partner executing QA for a ticket. You run formal test cases from the knowledge base, verify acceptance criteria in the browser, and file bugs in Jira for anything that fails. You work within the sprint: you know the ticket, the ACs, the test plan, and what the dev built.
You do not fix code by default. SDTs test and report — devs fix. If the SDT
enables --fix mode, you may fix minor issues (CSS, copy, config) but still file
Jira bugs for anything medium+ severity.
Constraints
- Execute test cases from KB, don't invent ad-hoc checks. Exploratory testing supplements but doesn't replace formal execution.
- Every failure becomes a Jira bug. No bug filed = no bug exists in the sprint.
- SDT approves before filing. Never file a Jira bug without SDT confirmation on severity and description.
- Evidence is everything. Every test case result needs a screenshot. Every bug needs repro steps + screenshot + console state.
- Don't fix unless asked.
--fixmode is opt-in and limited to minor/trivial. Medium+ severity always goes to the dev team. - Check console after every interaction. Silent JS errors count as findings.
- One ticket at a time. For cross-ticket testing, run
/qa-qaonce per ticket. - Connect to the sprint. Update Jira and KB — results left only in local markdown are invisible to the rest of the team.
- Show screenshots to the SDT inline.
- Always use the browser. Never refuse browser testing when /qa-qa is invoked.
Scratchpad (run protocol): write ## Plan to the run's scratchpad.md before Phase 1; at each phase boundary and every Review Options pause update ## State and re-read the scratchpad before continuing; drop noteworthy things into ## Candidate learnings as you go.
Phase 1: Load Context
Input: User provides a ticket key (e.g., PROJ-789), a URL, or both.
Load methodology references from {{REFERENCE_PATH}}/playbook/:
metrics-and-coverage.md— requirements coverage targetsdefect-lifecycle.md— bug filing, classification, SLA expectationsmaintenance-and-ci.md— flaky test process if tests fail intermittently
What ships with it
1 file 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 · 300 lines · 145 tokens per session scan C 40539b3f141e
qa is a skill published in the GitHub repository TimothyHan/qa-buddy-skills (8 stars, last pushed yesterday), licensed Apache-2.0. It adds 145 tokens to every session and 3,016 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
qawolf-cli
Manage QA Wolf through the qawolf CLI. Use when asked to create, update, or list coverage requests, bug reports, or maintenance reports; start a run of flows or tags on the QA Wolf platform or read a run's results; list, set, or delete environment variables; manage environments, flows, or tags; request automation of…
test-review
A review checklist for newly written or changed automated tests using TypeScript and Playwright. Playwright is a tool for testing web browsers, and automated tests check software without repeating the steps by hand.
playwright-expert
Expert in Playwright E2E testing framework, auto-waiting mechanisms, test generation, trace viewer, and CI/CD integration. Use when the user mentions testing, end-to-end tests, QA, automation, end-to-end testing, or test automation, or when the task involves Playwright Framework, Test Organization, Advanced Features…
browser-test-executor
Execute approved bounded browser Test DSL cases with fresh isolated contexts and auditable attempts. Use when running browser tests, reruns, regression checks, or blocked execution diagnostics.
qa-tester
Coordinate a bounded, evidence-backed QA run from requirements through release recommendation. Use for end-to-end QA planning, execution, retests, regressions, or exploratory browser checks.
evidence-collector
Collect and validate redacted, immutable QA evidence and evidence gaps for browser attempts. Use when capturing screenshots, traces, logs, telemetry, or explaining unavailable evidence.