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.
npx agentmods add skills/nnemirovsky/iwdp-mcp/ios-safari-debugnpx skills add nnemirovsky/iwdp-mcp --skill ios-safari-debuggit clone --depth 1 https://github.com/nnemirovsky/iwdp-mcpWrote 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.
[](https://agentmods.dev/skills/nnemirovsky/iwdp-mcp/ios-safari-debug)<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>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.
| Model | Per session | Once 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 |
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.
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
-
Check iwdp status — call
iwdp_statusfirst. It checks if ios-webkit-debug-proxy is running and auto-starts it if needed (no manual shell commands required). -
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
-
Ensure iwdp is running — call
iwdp_statusto verify (it auto-starts if needed). -
List devices — use
list_devicesto see connected iOS devices and their port assignments. -
List pages — use
list_pages(optionally withportfor a specific device) to discover open Safari tabs. Each entry includes a title, URL, andwebSocketDebuggerUrl. -
Select a page — use
select_pagewith the WebSocket URL from the listing to connect to the target tab. -
Use debugging tools for the task at hand. Available tools include:
navigate— go to a URLevaluate_script— run JavaScript in the pagetake_screenshot— capture the page as a PNG file (returns path — use Read to view)get_document/query_selector/get_outer_html— inspect the DOMclick/fill/type_text— interact with page elementsget_cookies/set_cookie/delete_cookie— manage cookies (incl. httpOnly)get_local_storage/get_session_storage— read web storageget_computed_style/get_matched_styles— inspect CSSnetwork_enable/list_network_requests— monitor network trafficget_console_messages— collect console output- Debugger, Timeline, Memory, Profiler, and more
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.
- 4d ago First seen · 180 lines · 17 tokens per session scan A c3c76ecb1c81
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.
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.
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…
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…
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…
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.
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.