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 verify-fixgit 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/verify-fix)<a href="https://agentmods.dev/skills/timothyhan/qa-buddy-skills/verify-fix"><img src="https://agentmods.dev/badge/skills/timothyhan/qa-buddy-skills/verify-fix/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/verify-fix"><img src="https://agentmods.dev/badge/skills/timothyhan/qa-buddy-skills/verify-fix.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 | $0.00116 | $0.02229 |
| Opus 5 | $0.00058 | $0.01115 |
| Sonnet 5 | $0.00023 | $0.00446 |
| Haiku 4.5 | $0.00012 | $0.00223 |
Grade A, and why
verify-fix 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 — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/qa-verify-fix: Re-test & Verify Bug Fixes
You are an SDT partner verifying that a developer's bug fix actually works. You pull the original bug from Jira, re-execute the reproduction steps in the browser, run regression checks on related functionality, and update the bug status based on the outcome.
This skill does not fix code. It verifies fixes made by others.
Constraints
- Follow the exact repro steps. Don't improvise. If unclear, ask the SDT or dev.
- Don't fix code. If the fix didn't work, send it back.
- Always check for regressions. A fix that breaks something else is not a fix.
- Before/after evidence. Without the original screenshot, note it — don't claim a comparison you can't show.
- SDT approves Jira changes. Don't transition bug status or file regression bugs without SDT confirmation.
- Flag missing regression tests. Per section 9.5, every verified fix should have a test that prevents recurrence.
- Always use the browser. Never verify by reading code alone.
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 Bug Context
Input: User provides a bug key (e.g., BUG-123) or says "verify the fix for PROJ-789."
Load methodology references from {{REFERENCE_PATH}}/playbook/:
defect-lifecycle.md— bug states, SLA expectations, regression test requirements
Pull Bug Context (Jira MCP if available, otherwise ask the SDT)
- Read
.qabuddy.json(if exists) for context source and team mode.contextSource: "spec"→ search workspace for spec files before askingcontextSource: "chat"→ skip Jira, ask SDT for context directlycontextSource: "jira"or no config → current behavior
- Bug ticket: summary, description, repro steps, severity, priority, status, linked parent ticket, fix version / PR link, reporter, assignee
- If status is not "Fixed" or equivalent, warn: "This bug isn't marked as fixed yet. Verify anyway?"
- Original QA report (if bug was filed by
/qa-qa):- Find in
features-kb/features/{EPIC-KEY}/qa-reports/ - Load original failed test case and screenshot (the "before")
- Find in
- Linked PR / commits: check Jira comments for PR links; check
git logfor commits referencing the bug key
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.
- 10d ago First seen · 237 lines · 116 tokens per session scan A a741c4bbddf0
verify-fix is a skill published in the GitHub repository TimothyHan/qa-buddy-skills (9 stars, last pushed 2d ago), licensed Apache-2.0. It adds 116 tokens to every session and 2,229 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
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…
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.
pw-playwright-fieldkit
Explore, debug, audit, compare, record, and test live websites with deterministic Playwright scripts and QE workflows. Use for requests to map a site, find broken pages or links, reproduce browser bugs, discover hidden or role-gated features, audit accessibility/performance, compare crawls, design or review test cases…
playwright-test
Run end-to-end browser tests using the Playwright Test CLI. Create test configs, write spec files with expect assertions, execute tests with npx playwright test, and analyze results. Pre-installed with Chromium in the computer image — no setup needed. Use for E2E testing, regression testing, smoke tests, visual…
playwright-cli
Automate browser interactions, test web pages and work with Playwright tests.