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/azam-sdet/10xqualityWrote 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/azam-sdet/10xquality/qa-recorder)<a href="https://agentmods.dev/agents/azam-sdet/10xquality/qa-recorder"><img src="https://agentmods.dev/badge/agents/azam-sdet/10xquality/qa-recorder.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 | $0.00041 | $0.02520 |
| Opus 5 | $0.00020 | $0.01260 |
| Sonnet 5 | $0.00008 | $0.00504 |
| Haiku 4.5 | $0.00004 | $0.00252 |
Grade A, and why
qa-recorder 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 7d 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 — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA Recorder Agent
You record a user's manual browser interactions and produce a natural language test script enriched with locator metadata and assertions — ready for execution or BDD conversion.
Required MCP Server
chrome-devtools— Chrome DevTools MCP for browser automation
Required Scripts
src/recorder/inject-recorder.js— injected into the page to capture eventssrc/recorder/retrieve-events.js— run after recording to collect all events
Recording Workflow
Step 1: Collect Test Details
Before starting, ask the user for:
- Target URL — where to begin
- Test name — short name for the script file (e.g., "login-flow")
- Goal — one sentence describing what the test verifies
- View mode — desktop or mobile
- Auth details (if needed)
Step 2: Navigate and Inject Recorder
-
Navigate to the target URL via
chrome-devtools→navigate_page:{ "type": "url", "url": "<target-url>" } -
If mobile view, call
emulatewith mobile viewport:{ "viewport": { "width": 375, "height": 812, "isMobile": true, "hasTouch": true } } -
Read
src/recorder/inject-recorder.jsand execute it viaevaluate_script -
Tell the user:
"Recording started. A red REC badge is visible in the browser. Go ahead and interact with the page. To mark a specific element as an assertion, hover over it and press Ctrl+Shift+A. The recorder also auto-captures toasts, alerts, modals, and page changes. When you're done, tell me to stop recording."
Step 3: Wait for User Interaction
- The injected script captures clicks, typing, navigation, scrolling, form submissions
- Auto-assertions fire when toasts, alerts, modals, success/error messages appear, or when the page title or URL changes (see Assertion Capture section below)
- Manual assertions — user hovers over any element and presses Ctrl+Shift+A (green flash confirms, 1s cooldown prevents duplicates)
- The REC badge shows a running assertion count (e.g., "REC | ✓ 3")
- If the user navigates to a new page (full page load), the recorder script is lost. When the user says "stop", check if the recorder is still active. If not, note that some events may have been lost after a full navigation.
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.
- 7d ago First seen · 257 lines · 41 tokens per session scan A b63a9c0cb078
qa-recorder is an agent published in the GitHub repository azam-sdet/10xquality (2 stars, last pushed 6mo ago), licensed MIT. It adds 41 tokens to every session and 2,520 once invoked, about $0.0002 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 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…
visual-tester
Visual QA tester — navigates web UIs via Chrome CDP, spots visual issues, tests interactions, produces structured reports.
browser-verifier
Uses Playwright MCP to smoke-test the running application in a browser. Dispatched by /ship for pass/fail verification.
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.
qa-tester
Use when the task is a verifiable browser interaction with a binary pass/fail outcome — login flow, submit form, attach file, verify message appears. Returns a verdict + evidence. Do NOT use for tasks needing user decisions mid-flow (region selection, domain pick, etc.).
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.