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 agentmods add commands/vinnie357/claude-skills/qagit clone --depth 1 https://github.com/vinnie357/claude-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/commands/vinnie357/claude-skills/qa)<a href="https://agentmods.dev/commands/vinnie357/claude-skills/qa"><img src="https://agentmods.dev/badge/commands/vinnie357/claude-skills/qa.svg" alt="Measured on agentmods" 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 | $0.00020 | $0.00718 |
| Opus 5 | $0.00010 | $0.00359 |
| Sonnet 5 | $0.00004 | $0.00144 |
| Haiku 4.5 | $0.00002 | $0.00072 |
Grade A, and why
qa 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 yesterday.
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.
What it actually says
Validate the application against the Gherkin user story at the given path. Spawns the qa-lead agent, which parses the story, detects the application stack, decomposes scenarios into parallel workers (Playwright for UI, Tidewave for Phoenix backends, generic backend probes otherwise), aggregates the workers' delta reports, and routes filed issues through the bees-manager agent into the target repo's .bees/ database.
What it does:
- Parse the user story —
qa-leadreads<path-to-user-story>and validates the Gherkin format. Rejects on bad format. - Detect the stack — Probes the repo for Phoenix (
mix.exs), web UI (package.json+playwright.config.*), or generic backends. Verifies the app is reachable at the URL declared inBackground:. - Spawn workers — One worker per
Scenario:, dispatched by assertion shape (UI → qa-playwright, Phoenix runtime → qa-tidewave, generic → qa-backend, mixed → both, correlated by scenario name). - Aggregate deltas — Each worker emits a
BEES REQUESTS:block in its report. The lead deduplicates across workers and routes ONE batch tobees-managerper run. - Report — Lists filed bees issue IDs, scenarios that passed, scenarios that failed, and the next-step guidance.
- (With
--fix) — Per filed issue, spawns an adversarial TDD pair:qa-test-writer(sonnet, may only edit tests) writes ONE failing test;qa-implementer(sonnet, may only edit production code) writes the smallest fix to make it pass. The lead inspectsgit diffbetween phases to enforce the boundary — neither agent can touch the other's files. Runsmise run ci/mise run testafter the fix, re-runs the originating validator. Three rounds max. Reports the diff and halts; the user decides whether to commit.
Arguments:
<path-to-user-story>— path to a Gherkin file underdocs/user-stories/<slug>.mdin the target repo. Required.--fix— opt-in to the post-validation fix loop.
Examples:
/qa docs/user-stories/checkout.md
/qa docs/user-stories/checkout.md --fix
Skills the lead loads (no globs — explicit names):
/qa:qa/core:agent-loop/core:tdd/core:anti-fabrication/core:bees/core:nushell/claude-code:claude-teams
Task instructions:
Use the qa-lead subagent. Pass it the absolute path of the user-story file (resolve `` against the current working directory), the repo root (current working directory unless the path is in a subrepo — in that case, walk up to find the nearest .git/), and the --fix flag if present. Reject before spawning if the file does not exist or sits outside docs/user-stories/.
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.
- yesterday First seen · 42 lines · 20 tokens per session scan A f49be86ab420
qa is a command published in the GitHub repository vinnie357/claude-skills (24 stars, last pushed today), licensed MIT. It adds 20 tokens to every session and 718 once invoked, about $0.0001 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 2026-09-04.
Other commands, from other repositories
implement
E2E-first Test driven development — unit tests written last.
fix
Correction automatisee des bugs identifies par la QA Recette.
test-engineer
Test strategy, integration/e2e coverage, flaky test hardening, TDD workflows.
build-from-figma
You are the master orchestrator for converting a Figma design into a fully working, tested React application. You receive a Figma URL and guide the entire process through 9 phases, using specialized skills and agents.
build-from-screenshot
You are the master orchestrator for converting screenshots or a live URL into a fully working, tested application. You receive one or more image file paths OR a URL and guide the entire process through 12 phases, using specialized skills and agents. The output target (React, Vue, Svelte, React Native) is determined…
build-from-canva
You are the master orchestrator for converting a Canva design into a fully working, tested React application. You receive a Canva URL and guide the entire process through 12 phases, using specialized skills and agents.