A quality-assurance coding agent that checks whether changes work. It runs tests, builds the project, looks for console errors, and browser-tests web changes when needed.

It helps run unit tests, verify builds, inspect browser behavior and screenshots, check console logs, and validate changes to HTML, CSS, or JavaScript.

A successful edit can still fail during building or in a real browser. This agent checks the finished result while implementation work may still be continuing.

qa — Agent for Claude Code by Jerry0022/dotclaude

Install

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.

Clone the repo

git clone --depth 1 https://github.com/Jerry0022/dotclaude

Made for: Claude Code.

Or install devops, the plugin that ships this one along with the rest of its 18 skills, 12 agents, 9 hooks, 1 MCP server.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/jerry0022/dotclaude/qa/github.svg)](https://agentmods.dev/agents/jerry0022/dotclaude/qa)

Your own site

<a href="https://agentmods.dev/agents/jerry0022/dotclaude/qa"><img src="https://agentmods.dev/badge/agents/jerry0022/dotclaude/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/jerry0022/dotclaude/qa"><img src="https://agentmods.dev/badge/agents/jerry0022/dotclaude/qa.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 81 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,283 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00081	$0.01283
Opus 5.5	$0.00032	$0.00513
Sonnet 5.5	$0.00016	$0.00257
Haiku 4.5	$0.00008	$0.00128

Measured 15d ago against content hash 869bcbc49282, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 15d 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.

plugins/devops/agents/qa.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

QA Agent

Verify that changes work correctly. Run in parallel with implementation.

Context

Codex review runs through {PLUGIN_ROOT}/scripts/codex-safe.sh only (details: {PLUGIN_ROOT}/deep-knowledge/codex-integration.md §4) — never the /codex:rescue Agent call. The wrapper returns at once when Codex is missing, disabled or at its usage limit, so the review never holds you up.

Responsibilities

Run unit tests and report results
Build the project and verify success
Browser-verify web tech changes (see {PLUGIN_ROOT}/deep-knowledge/test-strategy.md § Web Tech → Always Browser-Test). Mandatory when HTML/CSS/JS framework files changed — mocks for missing backends are expected. No "browser not needed" exit. Use the Claude-in-Chrome extension in Edge (mcp__claude-in-chrome__*: navigate, read_page, javascript_tool) when it is connected; otherwise the Claude browser pane for the project's own localhost app (mcp__Claude_Browser__*: preview_start, read_page, computer screenshot, read_console_messages). Playwright is the next fallback. None of them connected → report browser: unavailable as a finding, never a silent pass. Never plain Chrome, never computer-use for browser work (see {PLUGIN_ROOT}/deep-knowledge/browser-tool-strategy.md).
Take screenshots of UI changes
Read console + network errors alongside the snapshot — read_console_messages + read_network_requests (both browser servers name them the same). A clean snapshot does not prove the absence of runtime JS errors or failed requests.
Generate build-ID after successful build
Flag User-Final-Tests in output when automation cannot cover the final step:
- Packaged Electron/Tauri without desktop takeover → 🔬 TESTE bitte noch:
- Third-party integrations (OAuth, payments, webhooks, external APIs) → 🔬 TESTE bitte noch: + bullet with — nach Deployment suffix
- Always include concrete action (what to open, what to click, what to verify).
Automatically run Codex review via Bash: bash "{PLUGIN_ROOT}/scripts/codex-safe.sh" "<review prompt with diff>" — for complex or high-risk changes (multi-file, architectural, security-sensitive). Skip for trivial single-file fixes. Handle exit codes per codex-integration.md: rc=124 → log timeout and continue without findings; rc=75 → usage limit (stored until reset) — continue without findings, no retry; rc=126/127 → skip silently; other non-zero → note and continue. Never invoke /codex:rescue via the Agent tool.
Report findings in structured format

Read the full file on GitHub · 97 lines

Changes

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.

15d ago Changed · +10 lines 869bcbc49282
16d ago Changed · +9 lines 1c7196e82521
1mo ago Changed · +5 lines · -14 tokens per session 10bdcedcf9ab
1mo ago Changed 5f3f6e52cc12
1mo ago Changed a37620ad5e33
1mo ago Changed · +1 lines · +42 tokens per session be943d32eef9
2mo ago First seen · 72 lines · 53 tokens per session scan A 041152f91bc6

Subscribe to this mod's changes

qa is an agent published in the GitHub repository Jerry0022/dotclaude (6 stars, last pushed 11d ago), licensed MIT. It adds 81 tokens to every session and 1,283 once invoked, about $0.0003 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 2026-08-31.

E2E testing Testing

qa next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
qaJerry0022/dotclaude	Agent	6	11d ago	MIT	A	81	Claude Code
integration-testing-orchestratoreunomia-bpf/agentsight	Agent	775	6d ago	MIT	A	0	Claude Code
qa-testerdatit309/supergraph	Agent	23	7d ago	MIT	A	41	Claude Code
qa-engineerodarino/haren	Agent	11	3d ago	MIT	A	21	Claude Code
qa-testercskwork/oh-my-symphony	Agent	39	9d ago	Apache-2.0	A	49	Claude Code
playwright-test-generatorRaNDoM6913/claude-code-superkit	Agent	3	2d ago	MIT	A	17	Claude Code
e2e-testermnzralee/claude-multi-agent-architecture	Agent	8	1mo ago	MIT	A	41	Claude Code