agentmods.dev

ios-debugger-agent

A set of instructions for building, launching, inspecting, testing, and debugging iOS apps with the repository's XcodeBuildMCP server. An iOS Simulator is a Mac program that runs an iPhone or iPad app without a physical device.

In plain words
What is it for?
Building apps in Xcode, running focused tests, driving app screens, taking screenshots, reading logs, and investigating failures on macOS.
Why use it?
It provides a repeatable workflow for checking native iOS changes and explains what to do when the required Apple tools are unavailable.

Skill for Claude CodeCodex

21k 2d ago A scan 61 tokens original MIT
View the source file pingdotgg/t3code
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/pingdotgg/t3code/ios-debugger-agent
Any agent
npx skills add pingdotgg/t3code --skill ios-debugger-agent
Clone the repo
git clone --depth 1 https://github.com/pingdotgg/t3code

Made for: Claude Code, Codex.

Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 978 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 $0.00061 $0.00978
Opus 5 $0.00030 $0.00489
Sonnet 5 $0.00012 $0.00196
Haiku 4.5 $0.00006 $0.00098

Measured yesterday against content hash 2f6dcfc24926, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ios-debugger-agent 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.

.agents/skills/ios-debugger-agent/SKILL.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

iOS Debugger Agent

Use the repository-configured xcodebuildmcp tools instead of requiring a globally installed Codex plugin. Prefer MCP tools over raw xcodebuild, xcrun, or simctl when the client exposes them.

Confirm availability

This workflow requires macOS 14.5 or newer, Xcode 16 or newer, and Node.js 18 or newer. The repository pins XcodeBuildMCP in both .mcp.json for Claude Code and .codex/config.toml for Codex. Project MCP servers may require one-time trust or approval followed by a new session.

If the tools are missing:

  1. Confirm the repository is trusted and its project MCP server was approved.
  2. Restart or recreate the agent session after approving configuration.
  3. Run npx --yes [email protected] doctor when the server starts but simulator or UI-automation tools are unavailable. Follow its actionable Xcode or AXe setup guidance.
  4. Fall back to the pinned XcodeBuildMCP CLI or native Apple CLIs only when the current agent client cannot expose project MCP tools.

Do not ask contributors to install the OpenAI build-ios-apps plugin globally.

Establish one simulator context

  1. Call session_show_defaults before discovery, build, launch, or UI work.
  2. Call list_sims and select one explicit simulator UDID. Prefer a simulator that is already booted; boot an installed simulator when verification requires it, but do not create or download runtimes without user authorization.
  3. Call session_set_defaults with the project or workspace, scheme, Debug configuration, simulator ID, and bundle identifier when known.
  4. Keep every subsequent build, launch, screenshot, log capture, and UI action pinned to that same UDID.

Avoid generic Mac window automation for switching among Simulator windows. Explicit device identity is more reliable.

Choose build or launch

  • Use build_run_sim when native source, native dependencies, entitlements, or project configuration changed.
  • Use test_sim for the smallest relevant native test target or test cases; do not run an entire workspace test matrix routinely.
  • Use launch_app_sim when a compatible app is already installed and no native rebuild is needed.
  • To reuse an existing build artifact, use get_sim_app_path or get_app_bundle_id, install it with install_app_sim when necessary, and then launch it.
  • Do not run a build-only action immediately before build_run_sim unless the task requires both artifacts.

Read the full file on GitHub · 65 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 61 tokens per session scan A 2f6dcfc24926

Subscribe to this mod's changes

ios-debugger-agent is a skill published in the GitHub repository pingdotgg/t3code (21,041 stars, last pushed 2d ago), licensed MIT. It adds 61 tokens to every session and 978 once invoked, about $0.0003 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.

DebuggingFrontendTesting
Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens