native_browser_debugging

A rule for using the browser to investigate and verify user-interface, login, and frontend problems, including checking its error console.

In plain words
What is it for?
Use it when reproducing or confirming UI behavior, OAuth login flows, or frontend changes.
Why use it?
It requires runtime evidence that a fix works and catches browser errors that may not appear in code review alone.

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/markmhendrickson/foundation/native_browser_debugging
Clone the repo
git clone --depth 1 https://github.com/markmhendrickson/foundation

Made for: Cursor.

Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 494 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 $0.00027 $0.00494
Opus 5 $0.00014 $0.00247
Sonnet 5 $0.00005 $0.00099
Haiku 4.5 $0.00003 $0.00049

Measured yesterday against content hash bac5dc1cddeb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

native_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 yesterday.

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/native_browser_debugging.mdc · 65 lines

What it actually says

Native Browser Debugging Rule

Purpose

Ensure debugging and verification use the native browser for UI flows.

Trigger Patterns

When investigating or verifying UI issues, OAuth flows, or frontend behavior.

Agent Actions

  1. Use the native browser tools for reproduction and verification.
  2. Check browser console for errors when making UI changes:
    • Use browser MCP tools (browser_console_messages) to check for console errors
    • Verify no Uncaught SyntaxError, Uncaught TypeError, or missing export errors
    • Fix all console errors before marking UI changes complete
  3. Capture runtime evidence in the native browser before claiming resolution.
  4. Use Playwright only as supplemental coverage, not as the primary confirmation step.

Constraints

  • MUST use the native browser to reproduce UI issues when possible.
  • MUST use the native browser to confirm fixes for UI flows.
  • MUST check browser console for errors when making UI-impacting changes.
  • MUST fix all console errors (import/export errors, runtime errors) before marking UI changes complete.
  • MUST NOT claim UI fixes without native browser confirmation.
  • MUST NOT mark UI changes complete if console errors exist.

Agent Instructions

When to Load This Document

Load when debugging UI flows or confirming UI fixes.

Required Co-Loaded Documents

  • Repository documentation standards

Constraints Agents Must Enforce

  1. Use native browser tooling for UI debugging and verification.
  2. Collect runtime evidence from the native browser before concluding resolution.
  3. Check browser console for errors after all UI changes.
  4. Fix all console errors before marking UI work complete.

Forbidden Patterns

  • Declaring UI bugs fixed without native browser verification.
  • Relying only on headless tests for UI verification.
  • Ignoring console errors in the browser.
  • Marking UI changes complete with console errors present.

Validation Checklist

  • Native browser used to reproduce the issue
  • Native browser used to confirm the fix
  • Browser console checked for errors (using browser_console_messages MCP tool)
  • No console errors present (no import/export errors, no runtime errors)
  • Runtime evidence captured during reproduction and verification
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. yesterday First seen · 65 lines · 27 tokens per session scan A bac5dc1cddeb

Subscribe to this mod's changes

native_browser_debugging is a cursor rule published in the GitHub repository markmhendrickson/foundation (2 stars, last pushed 1mo ago), licensed MIT. It adds 27 tokens to every session and 494 once invoked, about $0.0001 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.