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 skills/adbarc92/mcp-browser-bridge/qa-runnernpx skills add adbarc92/mcp-browser-bridge --skill qa-runnergit clone --depth 1 https://github.com/adbarc92/mcp-browser-bridgeWrote 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/skills/adbarc92/mcp-browser-bridge/qa-runner)<a href="https://agentmods.dev/skills/adbarc92/mcp-browser-bridge/qa-runner"><img src="https://agentmods.dev/badge/skills/adbarc92/mcp-browser-bridge/qa-runner.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 | $0.00044 | $0.01775 |
| Opus 5 | $0.00022 | $0.00888 |
| Sonnet 5 | $0.00009 | $0.00355 |
| Haiku 4.5 | $0.00004 | $0.00178 |
Grade A, and why
qa-runner 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.
QA Runner
Executes structured QA checklists against a running app using Browser Bridge MCP tools. Reads a checklist markdown file with YAML frontmatter and CSS selectors, drives the browser through each scenario, captures evidence (screenshots, console logs, content checks), and reports pass/fail results.
When to Use
- User says "run QA" or "qa check"
- User says "test checklist" or "run checklist"
- User wants to execute a QA checklist against a live app
When NOT to Use
- Running unit tests or E2E test suites (use the project's test runner)
- Writing new tests
Prerequisites Check
Before running any scenario, verify ALL of these:
digraph prereqs {
"Start" [shape=doublecircle];
"browser_status?" [shape=diamond];
"Extension connected" [shape=box];
"STOP: Tell user to load extension" [shape=box, style=filled, fillcolor="#ffcccc"];
"App running?" [shape=diamond];
"Navigate to app_url" [shape=box];
"STOP: Tell user to start dev server" [shape=box, style=filled, fillcolor="#ffcccc"];
"Checklist exists?" [shape=diamond];
"Parse and execute" [shape=box];
"STOP: Checklist not found" [shape=box, style=filled, fillcolor="#ffcccc"];
"Start" -> "browser_status?";
"browser_status?" -> "Extension connected" [label="connected: true"];
"browser_status?" -> "STOP: Tell user to load extension" [label="connected: false"];
"Extension connected" -> "App running?";
"App running?" -> "Navigate to app_url" [label="yes"];
"App running?" -> "STOP: Tell user to start dev server" [label="no"];
"Navigate to app_url" -> "Checklist exists?";
"Checklist exists?" -> "Parse and execute" [label="yes"];
"Checklist exists?" -> "STOP: Checklist not found" [label="no"];
}
Step 1: Check browser connection
Call browser_status. If connected: false, stop and tell the user:
Chrome extension is not connected. Please:
- Open
chrome://extensionsand ensure "Browser Bridge MCP" is enabled- Click the extension icon and verify it shows "Connected"
- If disconnected, click "Reconnect"
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 · 44 tokens per session scan A 9f6eb5ad2aa6
qa-runner is a skill published in the GitHub repository adbarc92/mcp-browser-bridge (1 stars, last pushed 6d ago), licensed MIT. It adds 44 tokens to every session and 1,775 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 skills, from other repositories
browser
Use this skill when the user says browser, /browser, test in Chrome, inspect a webpage, verify a localhost app, capture screenshots, check console/network errors, run browser QA, or automate browser flows with the Mochi browser MCP.
tabnexus-mcp-evals
Generate, validate, and run isolated Codex-to-TabNexus MCP evaluations with a curated 600-query dataset, executable gold tool labels, safety checks, and best-of-three stability scoring. Use when testing TabNexus MCP tool coverage, Agent behavior, regression quality, destructive-action safety, prompt changes, or a…
add-chrome-tool
Add a new browser tool to the Chrome Bridge end to end — MCP tool in server/index.js, handler in extension/background.js, e2e assertion, README row. Use when asked to add, rename, or remove a browser capability exposed to Claude Code.
signed-in-browser
Drive the browser the user is already signed into, instead of a cold automation profile. Use when a task lives behind a login — a dashboard, an admin console, an internal tool, a ticket queue, a bank or billing page, webmail, a social account — or when a scripted login is failing on SSO, MFA, CAPTCHA or bot detection.…
post-to-hacker-news
Submit to Hacker News, including Show HN, by driving a signed-in browser. Use when launching a product, tool or MCP server, or when a submission needs its customary author comment. Covers the title rules, when a Show HN is allowed, the url-or-text choice, and how to tell a real submission from a silent failure.
verify
Drive the running ClawStash app in a real browser to verify UI/UX changes end-to-end. Use after nontrivial frontend changes, before committing — tests and tsc alone have missed lifecycle/timing bugs in this repo before (see MEMORY.md.