frontend-10x-browser-debugging

A browser-debugging rule that sets Chrome DevTools as the preferred way to inspect live browser sessions and localhost sites. Playwright remains available when isolated, repeatable browser tests are needed.

In plain words
What is it for?
Use it when inspecting localhost applications, debugging an existing Chrome session, choosing between live DevTools and a dedicated debug browser, or deciding when to use Playwright.
Why use it?
It prevents debugging from losing the current browser state, such as an open page or logged-in account. It also provides a clear fallback when a clean and deterministic test environment matters.

Cursor rule for Cursor

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 rules/kevin-liu-01/loop/frontend-10x-browser-debugging
Clone the repo
git clone --depth 1 https://github.com/Kevin-Liu-01/Loop

Made for: Cursor.

Per session 436 This file is loaded in full into every session.
When invoked 436 The same file — it is already loaded in full.
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 $0.00436 $0.00436
Opus 5 $0.00218 $0.00218
Sonnet 5 $0.00087 $0.00087
Haiku 4.5 $0.00044 $0.00044

Measured 2d ago against content hash 8eb49c507578, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

frontend-10x-browser-debugging 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 2d 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.

.cursor/rules/frontend-10x-browser-debugging.mdc · 32 lines

What it actually says

Browser Debugging Preference

When browser automation or debugging is needed:

  • Prefer chrome-devtools-live when the user already has Chrome open, is logged in, or wants the agent to inspect the current browser state.
  • Prefer chrome-devtools-port when testing localhost repeatedly or when a reusable dedicated debug browser is better than the user’s normal browsing session.
  • Use Playwright when isolation, deterministic repro, or fresh auth state is the actual goal.
  • Do not default to Playwright if the user clearly wants the current browser session or selected DevTools state.
  • For localhost work, favor going straight into the browser via Chrome DevTools MCP before spinning up a fresh browser automation lane.

Operational rules:

  • chrome-devtools-live requires remote debugging enabled at chrome://inspect/#remote-debugging and a user approval prompt.
  • chrome-devtools-port assumes Chrome was launched with a remote debug port, for example via /Users/kevinliu/.codex/bin/open-chrome-debug.sh http://localhost:3000.
  • Playwright is fallback, not the first move, for manual browser debugging.

Cleanup rules:

MCP processes (chrome-devtools-mcp, playwright-mcp) and Playwright-managed Chrome instances accumulate across sessions and waste memory. When the user asks to clean up, shut down, or wrap up:

  • Kill stale MCP processes: pkill -f "chrome-devtools-mcp" and pkill -f "playwright-mcp"
  • Kill Playwright-managed Chrome: pkill -f "ms-playwright/mcp-chrome"
  • Verify nothing remains: ps aux | grep -iE "chrome-devtools-mcp|playwright-mcp|ms-playwright" | grep -v grep | wc -l
  • Never kill the user's normal Chrome browser or Cursor processes.
  • Report what was cleaned up and confirm zero remaining.
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. 2d ago First seen · 32 lines · 436 tokens per session scan A 8eb49c507578

Subscribe to this mod's changes

frontend-10x-browser-debugging is a cursor rule published in the GitHub repository Kevin-Liu-01/Loop (18 stars, last pushed 1mo ago), licensed MIT. It adds 436 tokens to every session, about $0.0022 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.