ios-safari-debug

ios-safari-debug is a skill for Claude Code, Codex from nnemirovsky/iwdp-mcp. It costs 17 tokens per session (1,678 once invoked), scanned A, original, MIT.

A workflow for inspecting and debugging webpages open in Safari on a connected iPhone or iPad. It uses ios-webkit-debug-proxy, a bridge that exposes Safari pages to debugging tools.

In plain words
What is it for?
Use it to list connected iOS devices, find Safari tabs, select a page, and debug its webpage through the available inspector tools.
Why use it?
It lets you inspect the actual mobile Safari page and find problems that may not appear on a desktop browser. The workflow also helps identify the right device and open tab.

Skill for Claude CodeCodex

Part of the iwdp-mcp plugin — 1 skill, 1 MCP server shipped together

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/nnemirovsky/iwdp-mcp/ios-safari-debug
Any agent
npx skills add nnemirovsky/iwdp-mcp --skill ios-safari-debug
Clone the repo
git clone --depth 1 https://github.com/nnemirovsky/iwdp-mcp

Made for: Claude Code, Codex.

Or install iwdp-mcp, the plugin that ships this one along with the rest of its 1 skill, 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 ios-safari-debug

README.md
[![agentmods](https://agentmods.dev/badge/skills/nnemirovsky/iwdp-mcp/ios-safari-debug.svg)](https://agentmods.dev/skills/nnemirovsky/iwdp-mcp/ios-safari-debug)
Your own site
<a href="https://agentmods.dev/skills/nnemirovsky/iwdp-mcp/ios-safari-debug"><img src="https://agentmods.dev/badge/skills/nnemirovsky/iwdp-mcp/ios-safari-debug.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,678 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 $0.00017 $0.01678
Opus 5 $0.00009 $0.00839
Sonnet 5 $0.00003 $0.00336
Haiku 4.5 $0.00002 $0.00168

Measured 4d ago against content hash c3c76ecb1c81, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ios-safari-debug 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 4d 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/ios-safari-debug/SKILL.md · 180 lines

How it starts

The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.

iOS Safari Debugging

Use this skill to inspect and debug Safari tabs on a connected iOS device through ios-webkit-debug-proxy (iwdp).

Prerequisites

  1. Check iwdp status — call iwdp_status first. It checks if ios-webkit-debug-proxy is running and auto-starts it if needed (no manual shell commands required).

  2. An iOS device must be connected via USB with Safari open and Web Inspector enabled (Settings > Safari > Advanced > Web Inspector).

Port Layout

  • Port 9221 — listing port: returns all connected devices
  • Port 9222 — first device's pages
  • Port 9223 — second device's pages (and so on)

Each device entry from port 9221 includes a URL field (e.g., localhost:9222) indicating which port to query for that device's pages.

Workflow

  1. Ensure iwdp is running — call iwdp_status to verify (it auto-starts if needed).

  2. List devices — use list_devices to see connected iOS devices and their port assignments.

  3. List pages — use list_pages (optionally with port for a specific device) to discover open Safari tabs. Each entry includes a title, URL, and webSocketDebuggerUrl.

  4. Select a page — use select_page with the WebSocket URL from the listing to connect to the target tab.

  5. Use debugging tools for the task at hand. Available tools include:

    • navigate — go to a URL
    • evaluate_script — run JavaScript in the page
    • take_screenshot — capture the page as a PNG file (returns path — use Read to view)
    • get_document / query_selector / get_outer_html — inspect the DOM
    • click / fill / type_text — interact with page elements
    • get_cookies / set_cookie / delete_cookie — manage cookies (incl. httpOnly)
    • get_local_storage / get_session_storage — read web storage
    • get_computed_style / get_matched_styles — inspect CSS
    • network_enable / list_network_requests — monitor network traffic
    • get_console_messages — collect console output
    • Debugger, Timeline, Memory, Profiler, and more

Read the full file on GitHub · 180 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. 4d ago First seen · 180 lines · 17 tokens per session scan A c3c76ecb1c81

Subscribe to this mod's changes

ios-safari-debug is a skill published in the GitHub repository nnemirovsky/iwdp-mcp (14 stars, last pushed 4mo ago), licensed MIT. It adds 17 tokens to every session and 1,678 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.

Related

Other skills, from other repositories

asc-app-create-ui

Create a new App Store Connect app record via browser automation. Use when there is no public API for app creation and you need an agent to drive the New App form.

rorkai/app-store-connect-cli-skills · 39 tokens

browserenginekit

Build alternative browser engines using BrowserEngineKit. Use when developing a non-WebKit browser engine for iOS/iPadOS in supported regions, managing web content/rendering/networking extension processes, configuring GPU and networking process capabilities, checking alternative-engine device eligibility, or reviewing…

dpearson2699/swift-ios-skills · 68 tokens

browserenginekit

Build alternative browser engines using BrowserEngineKit. Use when developing a non-WebKit browser engine for iOS in the EU, managing web content rendering processes, configuring GPU and networking processes for browser functionality, checking device eligibility for alternative engines, or working with…

JordanCoin/ios-skills-collection · 60 tokens

use-agent-browser-for-airi

Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…

moeru-ai/airi · 87 tokens

opencli-sitemap-author

Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.

jackwener/OpenCLI · 67 tokens

pinchtab-mcp

Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.

pinchtab/pinchtab · 52 tokens