xcode-debugger-mcp-workflow

xcode-debugger-mcp-workflow is a skill for Claude Code, Codex from gaelic-ghost/socket. It costs 70 tokens per session (1,350 once invoked), scanned A, original, Apache-2.0.

A guide for inspecting and controlling a running Apple app through Xcode’s debugger, including breakpoints, stack frames, variables, and LLDB commands.

In plain words
What is it for?
Use it to investigate runtime bugs, inspect program state, evaluate expressions, issue debugger commands, and determine whether an Xcode debugger session is available.
Why use it?
It helps developers use the active Xcode debugging session correctly and distinguish it from a separate experimental debugger connection.

Skill for Claude CodeCodex

Part of the apple-dev-skills plugin — 65 skills, 2 MCP servers 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/gaelic-ghost/socket/xcode-debugger-mcp-workflow
Any agent
npx skills add gaelic-ghost/socket --skill xcode-debugger-mcp-workflow
Clone the repo
git clone --depth 1 https://github.com/gaelic-ghost/socket

Made for: Claude Code, Codex.

Or install apple-dev-skills, the plugin that ships this one along with the rest of its 65 skills, 2 MCP servers.

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 xcode-debugger-mcp-workflow

README.md
[![agentmods](https://agentmods.dev/badge/skills/gaelic-ghost/socket/xcode-debugger-mcp-workflow.svg)](https://agentmods.dev/skills/gaelic-ghost/socket/xcode-debugger-mcp-workflow)
Your own site
<a href="https://agentmods.dev/skills/gaelic-ghost/socket/xcode-debugger-mcp-workflow"><img src="https://agentmods.dev/badge/skills/gaelic-ghost/socket/xcode-debugger-mcp-workflow.svg" alt="Measured on agentmods" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,350 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 $0.00070 $0.01350
Opus 5 $0.00035 $0.00675
Sonnet 5 $0.00014 $0.00270
Haiku 4.5 $0.00007 $0.00135

Measured yesterday against content hash fc5d571a5d29, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

xcode-debugger-mcp-workflow 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.

plugins/apple-dev-skills/skills/xcode-debugger-mcp-workflow/SKILL.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Xcode Debugger MCP Workflow

Purpose

Use Xcode's active debugger session through xcrun mcpbridge as the stable agent-facing LLDB route. Treat the standalone xcrun lldb-mcp executable as experimental until it starts successfully on the selected Xcode toolchain and exposes a documented tool contract.

Xcode And LLDB MCP Boundaries

Xcode 27 exposes two distinct MCP paths:

  • xcrun mcpbridge is Xcode's STDIO bridge. It connects an external MCP client to a running Xcode process, selecting it with MCP_XCODE_PID or MCP_XCODE_SESSION_ID when needed. It owns Xcode project tools and the active run/debug-session tools. On the locally observed surface, InvokeDebuggerCommand sends a focused LLDB command to that active debugging session.
  • xcrun lldb-mcp is LLDB's standalone STDIO-to-socket bridge. It discovers an LLDB MCP server or launches a separate background lldb process when none exists. Its documented surface is one general lldb_command tool plus debugger and target resources. It does not document a way to select or take ownership of Xcode's active debugging session.

For a running Xcode app, start with mcpbridge, the active session, and the smallest Xcode-provided debugger command. Use standalone lldb-mcp only for a separately owned LLDB workflow after its startup and tool discovery both succeed.

Current Xcode 27 Beta 3 State

On 2026-07-12, the selected Xcode 27.0 Beta 3 toolchain (27A5218g) resolves both mcpbridge and lldb-mcp. mcpbridge --help works and documents STDIO bridge behavior, Xcode PID/session selection, and agent export behavior. lldb-mcp --help fails before startup because dyld cannot resolve @rpath/lib_CompilerSwiftIDEUtils.dylib, even though that library exists elsewhere inside the Xcode bundle.

This is a local Beta 3 packaging observation. Public Xcode release notes announce lldb-mcp, but neither those notes nor the public LLDB documentation identify this dyld failure as a known issue. Do not claim it affects every Xcode installation or beta. Do not work around this with copied libraries, symlinks, modified Xcode bundles, or a persistent loader-path override. Recheck a later Xcode beta or release before claiming standalone lldb-mcp support.

Read the full file on GitHub · 55 lines

Files

What ships with it

4 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 · 55 lines · 70 tokens per session scan A fc5d571a5d29

Subscribe to this mod's changes

xcode-debugger-mcp-workflow is a skill published in the GitHub repository gaelic-ghost/socket (7 stars, last pushed 9d ago), licensed Apache-2.0. It adds 70 tokens to every session and 1,350 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 2026-09-03.

Related

Other skills, from other repositories

app-store-optimization

Improves visibility and conversion in the App Store and Google Play — metadata, keywords, screenshots, ratings, and the listing experience that turns an impression into an install. Use this to audit or optimize an app listing, plan a launch listing, diagnose poor install conversion, or improve store search visibility.

cbrock84/headcount · 64 tokens

flutter-ui

Build Flutter UI from Figma MCP or image input. Scans src for design tokens (colors, sizes, text styles), existing components, and naming conventions before writing a single line of code. Never hard-codes values.

datit309/supergraph · 48 tokens

flutter-dart-code-review

Library-agnostic Flutter/Dart code review checklist covering widget best practices, state management patterns (BLoC, Riverpod, Provider, GetX, MobX, Signals), Dart idioms, performance, accessibility, security, and clean architecture.

datit309/supergraph · 56 tokens

setup

Start DeployGate onboarding — set up app distribution from first upload to team-wide deployment.

DeployGate/deploygate-agent-plugin · 18 tokens

pipeline

Use when the user wants a feature idea taken end-to-end in one autonomous run — phrases like "run the whole pipeline", "take this feature from idea to finished branch", "brainstorm then build it autonomously", "do everything from idea to merged", "implement all phases without stopping". Triggers when they want…

kardebadas/claude-plugin · 80 tokens

sdk-setup

Add the DeployGate SDK to your Android app for crash reporting and screen capture.

DeployGate/deploygate-agent-plugin · 19 tokens