agentmods.dev

generate-apple-doc

generate-apple-doc is a command for Claude Code from drisplabs/browser-mcp. It costs 22 tokens per session (1,839 once invoked), scanned A, original, MIT.

A browser-automation command that visits Apple’s website, adds an iPhone to a cart, and documents the tool calls and responses.

In plain words
What is it for?
Use it to generate the Markdown example at docs/examples/tool-use-example-add-iphone-to-cart.md.
Why use it?
It creates a recorded example of a multi-step browser task, including token analysis and any product-model substitution.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths.

Part of the drisp-browser plugin — 1 skill, 1 command, 1 MCP server shipped together

not rated 15repo 22d ago A scan 22 tokens original MIT

Good fit Use it to generate the Markdown example at docs/examples/tool-use-example-add-iphone-to-cart.md.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/drisplabs/browser-mcp/generate-apple-doc
View source ↗ drisplabs/browser-mcp agent-web-interface.com
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.

Clone the repo
git clone --depth 1 https://github.com/drisplabs/browser-mcp

Made for: Claude Code.

Or install drisp-browser, the plugin that ships this one along with the rest of its 1 skill, 1 command, 1 MCP server.

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 generate-apple-doc

README.md
[![agentmods](https://agentmods.dev/badge/commands/drisplabs/browser-mcp/generate-apple-doc.svg)](https://agentmods.dev/commands/drisplabs/browser-mcp/generate-apple-doc)
Your own site
<a href="https://agentmods.dev/commands/drisplabs/browser-mcp/generate-apple-doc"><img src="https://agentmods.dev/badge/commands/drisplabs/browser-mcp/generate-apple-doc.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,839 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00022 $0.01839
Opus 5 $0.00011 $0.00920
Sonnet 5 $0.00004 $0.00368
Haiku 4.5 $0.00002 $0.00184

Measured 7d ago against content hash 275f41d45473, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

generate-apple-doc 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 7d 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.

commands/generate-apple-doc.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.

Generate Apple.com iPhone-to-Cart Tool Use Example

You are generating a documented tool-use example for Drisp Browser. You will drive a live browser session through apple.com's iPhone purchase flow, record every tool call and response, then produce a comprehensive markdown document with token analysis.

Output File

Write the final document to: docs/examples/tool-use-example-add-iphone-to-cart.md

Phase 1: Browser Automation

Execute the following steps using Drisp Browser tools. After EACH tool call, record:

  • The tool name (without the mcp__drisp-browser__ prefix)
  • The exact input JSON you sent
  • The full XML response you received (you will trim it later for the doc)

Step-by-step flow

  1. navigate to https://www.apple.com

    • If a country/region selector overlay appears, dismiss it by clicking the close button.

  2. click the "iPhone" link in the nav region.

  3. On the iPhone landing page, click the "Buy, iPhone 17" link.

    • If iPhone 17 is not listed, use the latest available iPhone model and note this in the doc.

  4. find_elements with kind: "radio", region: "main", limit: 20 to discover all configuration options.

  5. Configure the iPhone by clicking radio buttons in sequence. Each selection enables the next tier:

    • Color: Select "Lavender" (or the first available color)
    • Storage: Select "256GB"
    • Trade-in: Select "No trade-in"
    • Payment: Select "Buy" (full price)
    • Carrier: Select "Connect to any carrier later" (unlocked)
    • AppleCare: Select "No AppleCare coverage"

    IMPORTANT: Wait for each tier to become enabled before clicking. If a radio button shows enabled="false", you must first complete the preceding selection.

  6. click the "Add to Bag" button (look for it in the form region with val="add-to-cart").

  7. After the accessories upsell page loads, scroll_page down to find the "Review Bag" button, then click it.

  8. On the Bag page, verify the iPhone is in the cart by checking:

    • The nav shows "Shopping Bag with item count : 1"
    • The main region contains the product name and "Check Out" button

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. 7d ago First seen · 201 lines · 22 tokens per session scan A 275f41d45473

Subscribe to this mod's changes

generate-apple-doc is a command published in the GitHub repository drisplabs/browser-mcp (15 stars, last pushed 22d ago), licensed MIT. It adds 22 tokens to every session and 1,839 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 2026-08-30.

Browser automationE-commerceai-agentsbrowser-automationchromiumclaudellm-toolsmcp
Related

Other commands, from other repositories

analyze

Analyze a webpage's structure using Actionbook's verified selectors and show available elements for scraping.

actionbook/actionbook · 0 tokens

interactive-dev

Start a persistent interactive development session with natural language browser control, auto-error monitoring, and full dev tool access.

brennhill/Kaboom-Browser-AI-Devtools-MCP · 25 tokens

playbook

Manage Mochi playbooks (list, show, run, delete). Plays through the browser MCP tools.

DevZonayed/Mochi · 21 tokens

intercept

HTTP sniffer for tandem's Chrome via CDP: captures request+response bodies (including HttpOnly, CSRF tokens, private APIs). Subcommands: start, show, clear, count.

bgmacris/quimera-ai · 39 tokens

cookies

Exports cookies from tandem's Chrome via CDP (includes HttpOnly/Secure). Filter with --domain . Formats: list (table, default), json, curl, headers, netscape.

bgmacris/quimera-ai · 40 tokens

naive-test

Drive the live app as a naive first-time user and report UX/behavior gaps before deploy.

TechGardenCode/naive-user · 18 tokens