qa-runner

qa-runner is a skill for Claude Code, Codex from adbarc92/mcp-browser-bridge. It costs 44 tokens per session (1,775 once invoked), scanned A, original, MIT.

A browser-based quality-check runner for a live web app. It follows a checklist in a Markdown file, uses browser automation, and records evidence such as screenshots, console logs, and content checks.

In plain words
What is it for?
Use it to run QA checklists against a running app through a browser. It is not for unit tests, end-to-end test suites, or writing new tests.
Why use it?
It gives a repeatable way to check user-facing scenarios without manually testing every step and records whether each scenario passed or failed.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/adbarc92/mcp-browser-bridge/qa-runner
Any agent
npx skills add adbarc92/mcp-browser-bridge --skill qa-runner
Clone the repo
git clone --depth 1 https://github.com/adbarc92/mcp-browser-bridge

Made for: Claude Code, Codex.

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.

agentmods badge for qa-runner

README.md
[![agentmods](https://agentmods.dev/badge/skills/adbarc92/mcp-browser-bridge/qa-runner.svg)](https://agentmods.dev/skills/adbarc92/mcp-browser-bridge/qa-runner)
Your own site
<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>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,775 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce 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

Measured 5d ago against content hash 9f6eb5ad2aa6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

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.

skills/qa-runner/SKILL.md · 201 lines

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:

  1. Open chrome://extensions and ensure "Browser Bridge MCP" is enabled
  2. Click the extension icon and verify it shows "Connected"
  3. If disconnected, click "Reconnect"

Read the full file on GitHub · 201 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.

  1. 5d ago First seen · 201 lines · 44 tokens per session scan A 9f6eb5ad2aa6

Subscribe to this mod's changes

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.

Related

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.

DevZonayed/Mochi · 50 tokens

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…

KaichenCurry/TabNexus · 75 tokens

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.

TranHuyQn/cc-chrome-extension · 57 tokens

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.…

t3ratech/mcp-session-bridge · 109 tokens

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.

t3ratech/mcp-session-bridge · 75 tokens

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.

fo0/clawstash · 54 tokens