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.
git clone --depth 1 https://github.com/FlorianBruniaux/claude-code-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/commands/florianbruniaux/claude-code-plugins/qa)<a href="https://agentmods.dev/commands/florianbruniaux/claude-code-plugins/qa"><img src="https://agentmods.dev/badge/commands/florianbruniaux/claude-code-plugins/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/commands/florianbruniaux/claude-code-plugins/qa"><img src="https://agentmods.dev/badge/commands/florianbruniaux/claude-code-plugins/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 | $0.00023 | $0.01652 |
| Opus 5.5 | $0.00009 | $0.00661 |
| Sonnet 5.5 | $0.00005 | $0.00330 |
| Haiku 4.5 | $0.00002 | $0.00165 |
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 1mo 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 — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA — Web Application Testing
Systematically test a web application for bugs, then fix and verify each issue found.
Three tiers of thoroughness. Diff-aware scoping — tests what actually changed.
Instructions
Step 1: Scope Detection
Determine which pages and features to test.
Diff-aware mode (default): Identify affected routes from the current branch changes.
# Files changed in this branch
git diff --name-only origin/main...HEAD 2>/dev/null || git diff --name-only HEAD~5
# Identify affected routes from changed files
# e.g., changes in src/pages/dashboard/ → test /dashboard
# changes in api/payments/ → test payment flows
Full mode (/qa --full): Test the entire application, starting with critical paths.
Explicit scope (/qa /dashboard /settings): Test specified pages only.
Step 2: Tier Selection
| Tier | Flag | Scope | Use when |
|---|---|---|---|
| Quick | --quick |
Critical + High severity only | Pre-commit fast check |
| Standard | (default) | + Medium severity | Pre-PR review |
| Exhaustive | --exhaustive |
+ Low + cosmetic | Release candidate |
Step 3: Clean Working Tree
Before testing, ensure you can commit fixes atomically.
git status --short
If there are uncommitted changes: stash them first (git stash), or commit them. Testing on a dirty tree makes it impossible to isolate fix commits.
Step 4: Testing
For each page in scope, systematically check all categories relevant to the selected tier.
How to test
Use whatever browser tooling is available:
- MCP browser tools (if configured) — automated navigation and screenshots
- Playwright/Puppeteer (if in the project) — scripted test runs
- Manual testing — navigate to the URL, document findings systematically
For each page, cover:
1. Load the page — does it render without errors?
2. Check console — any uncaught errors, failed requests, warnings?
3. Test primary user action — the core thing this page is for
4. Test empty state — what shows when there's no data?
5. Test error state — what happens when an action fails?
6. Test on narrow viewport — does it break below 375px?
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.
- 1mo ago First seen · 215 lines · 23 tokens per session scan A 5d8994acbdb4
qa is a command published in the GitHub repository FlorianBruniaux/claude-code-plugins (42 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 1,652 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.
Other commands, from other repositories
a11y-audit
Web accessibility (WCAG 2.1) audit command. axe-core-based checks via PageSpeed Insights.
api-test
HTTP API endpoint testing. Send GET/POST/PUT/DELETE requests, analyze status + response, assertions.
refactor
Refactoring command. Detects code smells and creates a safe refactoring plan.
prompt-test
Regression test for slash command and agent files. Format and content validation.
qa
QA sign-off command. Verifies a change against acceptance criteria, runs the test suite, probes edge cases, and issues a ship / no-ship verdict via the qa-lead agent.
verify-loop
A command that repeatedly checks recent code changes and tries to fix failures, with a configurable retry limit. It can run code review, builds, tests, linting, and type checks according to the project language.