agentmods.dev

mcp-playwright-browser: Instructions file for Gemini CLI

GEMINI.md

mcp-playwright-browser GEMINI.md is an instructions file for Gemini CLI from Mhrnqaruni/mcp-playwright-browser. It costs 957 tokens per session, scanned A, original, ISC.

Project instructions for Gemini CLI, a command-line AI assistant, that require browser actions through a Playwright MCP server and set rules for reading job-application files.

In plain words
What is it for?
Use them when applying for jobs with browser automation, CVs, cover letters, and job descriptions stored in project folders.
Why use it?
They give the agent a consistent way to inspect browser pages and CV or job files while choosing document-structure checks before visual inspection.

Instructions file for Gemini CLI

Written for Gemini CLI: the file is GEMINI.md.

This is Mhrnqaruni/mcp-playwright-browser's own configuration. It tells Gemini CLI how to work on mcp-playwright-browser itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-playwright-browser configures →

not rated 0repo 6mo ago A scan 957 tokens original ISC
View source ↗ Mhrnqaruni/mcp-playwright-browser
Reuse

Borrowing it

Nothing to install: this file belongs to Mhrnqaruni/mcp-playwright-browser. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Mhrnqaruni/mcp-playwright-browser/master/GEMINI.md
Clone the repo
git clone --depth 1 https://github.com/Mhrnqaruni/mcp-playwright-browser

Made for: Gemini CLI.

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 mcp-playwright-browser GEMINI.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mhrnqaruni/mcp-playwright-browser/gemini-md/github.svg)](https://agentmods.dev/instructions/mhrnqaruni/mcp-playwright-browser/gemini-md)
Your own site
<a href="https://agentmods.dev/instructions/mhrnqaruni/mcp-playwright-browser/gemini-md"><img src="https://agentmods.dev/badge/instructions/mhrnqaruni/mcp-playwright-browser/gemini-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for mcp-playwright-browser GEMINI.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/mhrnqaruni/mcp-playwright-browser/gemini-md"><img src="https://agentmods.dev/badge/instructions/mhrnqaruni/mcp-playwright-browser/gemini-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 957 This file is loaded in full into every session.
When invoked 957 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00957 $0.00957
Opus 5 $0.00478 $0.00478
Sonnet 5 $0.00191 $0.00191
Haiku 4.5 $0.00096 $0.00096

Measured 8d ago against content hash 82d7a856083e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

mcp-playwright-browser GEMINI.md 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 8d 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.

GEMINI.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gemini Project Instructions (Auto)

Always Use MCP Server

Use MCP server playwrightBrowser for all browser actions.

Reading CV / Job Files

  • Prefer MCP file tools (avoid built-in ReadFile/Shell because workspace restrictions can fail unexpectedly):
    • Use files.list_dir to locate CV/cover letter/jobdescription under Applied Jobs/<job-folder>/.
    • Use files.read_text for *.md/*.txt.
    • Use files.read_pdf_text for *.pdf.
    • If the needed info is missing/unreadable: ask the user (do not hunt/scan across folders).

DOM vs Visual

  • Prefer DOM actions first.
  • Set capture profile at start of work:
    • Call browser.set_capture_profile with profile: "light" unless the user asks for debug-level detail.
  • Follow this capture ladder (least expensive first):
    1. browser.snapshot with detail: "low"
    2. browser.list with detail: "low"
    3. browser.query_dom with detail: "low" for targeted reads
    4. browser.take_snapshot with detail: "low" only when uid targeting is needed
    5. browser.visual_snapshot with detail: "low" only as last resort
  • Use detail: "high" only when low detail is insufficient.
  • Do not repeat browser.take_snapshot / browser.visual_snapshot unless one of these is true:
    • domVersion changed
    • you intentionally scrolled and need a fresh scan of newly visible content
    • MCP returned STALE_REF
    • target cannot be found after browser.wait_for
    • user explicitly asked for a fresh visual check
  • If browser.list reports needsScrollForMore: true or hasOffViewportCandidates: true, scroll and run browser.list again before concluding the page is complete.

Element IDs (Critical)

  • elementIds are short-lived. After any click, dropdown, or navigation:
    • call browser.list (or browser.visual_snapshot) again
    • do not reuse old element IDs
  • Waiting: use browser.wait_for (selector/text/uid) instead of fixed sleeps.

Multi-Tab / Popups

  • Popup tools do not auto-select new tabs by default.
  • If a popup/new tab opens, always use:
    • browser.list_pages
    • browser.select_page
    • browser.close_page

Read the full file on GitHub · 75 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. 8d ago First seen · 75 lines · 957 tokens per session scan A 82d7a856083e

Subscribe to this mod's changes

mcp-playwright-browser GEMINI.md is an instructions file published in the GitHub repository Mhrnqaruni/mcp-playwright-browser (0 stars, last pushed 6mo ago), licensed ISC. It adds 957 tokens to every session, about $0.0048 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.

Browser automation
Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens