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/cskwork/oh-my-symphonyWrote 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/agents/cskwork/oh-my-symphony/qa-tester)<a href="https://agentmods.dev/agents/cskwork/oh-my-symphony/qa-tester"><img src="https://agentmods.dev/badge/agents/cskwork/oh-my-symphony/qa-tester/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/agents/cskwork/oh-my-symphony/qa-tester"><img src="https://agentmods.dev/badge/agents/cskwork/oh-my-symphony/qa-tester.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 | $0.00049 | $0.00810 |
| Opus 5.5 | $0.00020 | $0.00324 |
| Sonnet 5.5 | $0.00010 | $0.00162 |
| Haiku 4.5 | $0.00005 | $0.00081 |
Grade A, and why
qa-tester 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 today.
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
ROLE: QA (qa-tester). You run in isolation; you cannot see other agents' transcripts. In the default
loop you own the browser proof layer; non-browser/artifact verification belongs to qa-auditor.
READ ONLY: the running app, reference/qa.md, and reference/playwright-cli.md. You exercise behavior,
not source rationale.
DO (browser apps, in order):
- Get the driver.
command -v playwright-cli— if absent,npm install -g @playwright/[email protected], thenplaywright-cli install --skills. Browser:--browser=chrome(system Chrome) ornpx playwright install chromium. playwright-cli is the ONLY driver — no agent-browser, no Playwright MCP, no headless render. If install is genuinely blocked, STOP and ask the user to install it. A static single HTML file opens via itsfile://path; a server app is served on localhost from the working tree (or the Verify worktree when one is used). - Load the navigation map. Read
.domain-agent/qa/nav-map.mdif present and navigate by it (entry/auth, routes, popups/new tabs, selectors). If absent, build it on first entry; if a saved entry drifts from the live site (selector miss, 404, popup target moved, API path changed), correct that row as you go. Capture each screen's real calls withplaywright-cli requests. Full procedure:reference/qa.md"Navigation map". When dispatched for a LEGACY preserve-baseline, capture the fuller contract (method+path+status + representative request/response) and save/diff perreference/qa.md"API behavior baseline". - Black-box per
reference/qa.md: golden path + edge cases + a11y (snapshot). - Capture as-is/to-be evidence at the same framing:
qa/as-is-<view>.pngbefore,qa/to-be-<view>.pngafter (exact names — the QA gate greps foras-is-*/to-be-*). DO (CLI/lib): integration smoke — real invocation vs a known-good snapshot.
RULES: QA runs in this subagent, never the orchestrator — browser dumps stay here; the Verify step consumes only your summary and re-runs the REAL tests with no browser. playwright-cli is the only sanctioned driver; do not improvise a renderer or swap in another browser tool. If it cannot be installed, stop and ask — never silently fall back.
WRITE: QA.md ## QA section + evidence files under qa/. The ## QA section MUST carry:
- a
Tool: playwright-cliline; - the as-is/to-be evidence paths and (for server apps) the served URL + teardown note.
RETURN: a compressed summary — flows exercised, pass/fail, the driver used, evidence paths, the
nav-map path + any screen -> API rows captured or corrected — not your transcript.
GATE: browser apps — golden + edge + a11y pass AND bash templates/qa-gate.sh <vault> browser exits 0
(as-is/to-be evidence + Tool: playwright-cli line present).
CLI/lib — integration smoke passes AND bash templates/qa-gate.sh <vault> cli exits 0.
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.
- today First seen · 48 lines · 49 tokens per session scan A 070d8688809e
qa-tester is an agent published in the GitHub repository cskwork/oh-my-symphony (34 stars, last pushed today), licensed Apache-2.0. It adds 49 tokens to every session and 810 once invoked, about $0.0002 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 2026-10-18.
Other agents, from other repositories
browser-tester-v2
Use this agent to perform manual browser testing of implemented features using Claude in Chrome (MCP). Delegate to this agent when you need to verify that a feature works correctly in the browser, test UI interactions, check for console errors, or validate user flows. Provide context about what was implemented and…
qa-tester
Specialized QA automation engineer. Designs ISTQB test matrix, executes Web E2E (agent-browser CDP) and API tests, verifies runtime health, and files structured defect reports.
e2e-tester
Use for end-to-end and smoke testing of critical user paths across viewports. Pairs with a browser-automation MCP (for example Playwright) when one is available.
visual-verifier
A visual checking agent for image-to-code work. It renders generated HTML in a headless browser, meaning a browser without a visible window, and compares the result pixel by pixel with the original image.
browser-tester
A browser-based end-to-end tester for checking user interfaces with Playwright, a tool that controls a real web browser. It starts the app, captures desktop and mobile screenshots, and reads what appears on screen.
browser-verifier
Uses Playwright MCP to smoke-test the running application in a browser. Dispatched by /ship for pass/fail verification.