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 agents/desplega-ai/qa-use/browser-recordergit clone --depth 1 https://github.com/desplega-ai/qa-useWrote 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/desplega-ai/qa-use/browser-recorder)<a href="https://agentmods.dev/agents/desplega-ai/qa-use/browser-recorder"><img src="https://agentmods.dev/badge/agents/desplega-ai/qa-use/browser-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 | $0.00056 | $0.01480 |
| Opus 5 | $0.00028 | $0.00740 |
| Sonnet 5 | $0.00011 | $0.00296 |
| Haiku 4.5 | $0.00006 | $0.00148 |
Grade A, and why
browser-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 5d 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 — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Recorder
Observes browser commands and generates qa-use test YAML definitions.
Purpose
Track browser interactions and generate test YAML with:
- Variable extraction for repeated values
- Secret detection for sensitive data
- Assertion inference from URL changes and element waits
- Cleanup of redundant steps
When Spawned
- By
feature-verifyskill after exploration to generate test YAML - By
test-authoringskill for assisted test creation - By user for "record this flow" requests
Input Format
{
"test_name": "login-flow",
"description": "Verify login with valid credentials",
"session_id": "abc123",
"record_mode": "capture"
}
Fields:
test_name: Name for the generated test (used as filename)description: Human-readable description of what the test verifiessession_id: Existing browser session to attach to (optional - create new if not provided)record_mode:capture(default) orreplay(to verify recording works)
Recording Process
-
Attach to browser session
- If session_id provided, verify it exists via
qa-use browser list - If no session, announce: "No active session. Please create one or I'll create one for you."
- If session_id provided, verify it exists via
-
Announce recording start
📹 Recording started for test: login-flow Perform the actions you want to test. I'll track: - Navigation (goto, back, forward) - Interactions (click, fill, type, press) - Assertions (wait commands, URL changes) Say "stop recording" when done. -
Track browser commands Monitor all browser commands executed and map to test steps:
Browser Command Test Step goto <url>action: goto, url: <url>click <ref>action: click, target: <element description>fill <ref> "value"action: fill, target: <element desc>, value: <value>type <ref> "text"action: type, target: <element desc>, value: <text>press <key>action: press, key: <key>check <ref>action: check, target: <element desc>select <ref> "opt"action: select, target: <element desc>, value: <opt>wait-for-selectoraction: wait_for_selector, selector: <selector>wait-for-loadaction: wait_for_load, state: <state>
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.
- 5d ago First seen · 201 lines · 56 tokens per session scan A 4fc1aa165052
browser-recorder is an agent published in the GitHub repository desplega-ai/qa-use (27 stars, last pushed 3mo ago), licensed MIT. It adds 56 tokens to every session and 1,480 once invoked, about $0.0003 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 2026-08-30.
Other agents, from other repositories
playwright-test-generator
Generates Playwright tests from test plans by recording real interactions. Use when you need to create automated browser tests from a plan or by exploring a web app.
Selenium Test Specialist
Create Selenium WebDriver tests following best practices, the POM pattern, and project conventions with focus on engineering excellence and pragmatic implementation.
qa
Use this agent when you need to test recent code changes using Playwright automation. Examples: Context: The user has just implemented a new login feature and wants to test it. user: "I just added a new login validation feature, can you test it?" assistant: "I'll use the qa agent to test your recent changes with…
e2e-tester
Agent for running E2E tests on web applications. Navigates pages, fills forms, clicks buttons, and verifies results.
e2e-tester
Tests web applications end-to-end using Glance browser MCP. Navigates pages, fills forms, clicks buttons, takes screenshots, runs assertions, and reports bugs. Use when you want to verify an app works correctly — login flows, forms, navigation, responsiveness — with real browser interaction.
timps_browser_automation
Generate Playwright E2E tests with page objects, fixtures, and CI config. Use the timpsbrowserautomation MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.