xcode-build-fixer

xcode-build-fixer is a skill for Claude Code from omarshahine/HomeClaw. It costs 77 tokens per session (2,562 once invoked), scanned A, a copy of xcode-build-fixer, MIT.

A procedure for applying approved Xcode build optimizations and measuring the result afterward. Xcode is Apple's tool for building Apple-platform apps, and benchmarking means recording build performance before and after a change.

In plain words
What is it for?
Use it to apply specified build-setting, script-phase, or source-level fixes, change one logical item at a time, and report the files changed and measured difference.
Why use it?
It keeps build changes limited to decisions the developer has approved and makes regressions visible. Rechecking the benchmark shows whether a change actually improved build performance.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Part of the homeclaw plugin — 17 skills, 4 commands 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/omarshahine/homeclaw/xcode-build-fixer
Any agent
npx skills add omarshahine/HomeClaw --skill xcode-build-fixer
Clone the repo
git clone --depth 1 https://github.com/omarshahine/HomeClaw

Made for: Claude Code.

Or install homeclaw, the plugin that ships this one along with the rest of its 17 skills, 4 commands.

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-build-fixer

README.md
[![agentmods](https://agentmods.dev/badge/skills/omarshahine/homeclaw/xcode-build-fixer.svg)](https://agentmods.dev/skills/omarshahine/homeclaw/xcode-build-fixer)
Your own site
<a href="https://agentmods.dev/skills/omarshahine/homeclaw/xcode-build-fixer"><img src="https://agentmods.dev/badge/skills/omarshahine/homeclaw/xcode-build-fixer.svg" alt="Measured on agentmods" height="20"></a>
Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,562 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00077 $0.02562
Opus 5 $0.00039 $0.01281
Sonnet 5 $0.00015 $0.00512
Haiku 4.5 $0.00008 $0.00256

Measured 6d ago against content hash 0904653e7871, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

xcode-build-fixer 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 6d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/benchmark_builds.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Origin

This is a copy

100% identical to xcode-build-fixer — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/skills/xcode-build-fixer/SKILL.md · 219 lines

How it starts

The opening of the file, as written. The whole thing — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Xcode Build Fixer

Use this skill to implement approved build optimization changes and verify them with a benchmark.

Core Rules

  • Only apply changes that have explicit developer approval.
  • Apply one logical fix at a time so changes are reviewable and reversible.
  • Re-benchmark after applying changes to verify improvement.
  • Report exactly what changed, which files were touched, and the measured delta.
  • If a change produces no improvement or causes a regression, flag it immediately.

Inputs

The fixer expects one of:

  • An approved optimization plan at .build-benchmark/optimization-plan.md with checked approval boxes.
  • An explicit developer instruction describing the fix to apply (e.g., "set DEBUG_INFORMATION_FORMAT to dwarf for Debug").

When working from an optimization plan, read the approval checklist and implement only the checked items.

Fix Categories

Build Settings

Change project.pbxproj values to match the recommendations in build-settings-best-practices.md.

Typical fixes:

  • Set DEBUG_INFORMATION_FORMAT = dwarf for Debug
  • Set SWIFT_COMPILATION_MODE = singlefile for Debug
  • Enable COMPILATION_CACHE_ENABLE_CACHING = YES
  • Enable EAGER_LINKING = YES for Debug
  • Align cross-target settings to eliminate module variants

When editing project.pbxproj, locate the correct buildSettings block by matching the target name and configuration name. Verify the change with xcodebuild -showBuildSettings after applying.

Script Phases

Fix run script phases that waste time during incremental or debug builds.

Typical fixes:

  • Add input and output file declarations so Xcode can skip unchanged scripts.
  • Add configuration guards: [[ "$CONFIGURATION" != "Release" ]] && exit 0 for release-only scripts.
  • Move input/output lists into .xcfilelist files when the list is long.
  • Enable Based on dependency analysis when inputs and outputs are declared.

Source-Level Compilation Fixes

Read the full file on GitHub · 219 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. 6d ago First seen · 219 lines · 77 tokens per session scan A 0904653e7871

Subscribe to this mod's changes

xcode-build-fixer is a skill published in the GitHub repository omarshahine/HomeClaw (164 stars, last pushed 5d ago), licensed MIT. It adds 77 tokens to every session and 2,562 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to xcode-build-fixer, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories

workflow-audit

Systematic UI workflow auditing for SwiftUI applications. Discovers entry points, traces user flows, detects dead ends and broken promises, audits data wiring, evaluates from user perspective. Triggers: "workflow audit", "audit flows", "find dead ends", "check navigation".

Terryc21/workflow-audit · 59 tokens

swift-expert

Expert-level Swift development for iOS, macOS with SwiftUI, Combine, and modern Swift 5.9+. Use when the user mentions iOS, macOS, SwiftUI, Combine, async await, or Apple platforms, or when the task involves Modern Swift Features, Basics and Optionals, Functions and Closures, or Structs and Classes.

personamanagmentlayer/pcl · 76 tokens

swift-focusengine-pro

Reviews, writes, and fixes focus management code for all Apple platforms (tvOS, iOS/iPadOS, watchOS, visionOS, macOS), covering SwiftUI, UIKit, AppKit, and RealityKit. Use when reading, writing, or reviewing apps that handle focus, hover, key view loops, or Digital Crown navigation.

mhaviv/Swift-FocusEngine-Agent-Skill · 74 tokens

ttb-skill-bugfix

Systematic bug fixing workflow for TTBaseUIKit apps: root cause analysis, fix strategy, xcodebuild verify, zero regression.

tqtuan1201/TTBaseUIKit · 34 tokens

swift-agent-debug-log

Instrument Swift/iOS apps for Cursor DEBUG MODE: NDJSON hypothesis logs on the host or simulator Documents. Use with XcodeBazelMCP agentdebug tools (clear, read, pull, repro) instead of Read/deletefile on host paths from sim code.

DebugSwift/XcodeBazelMCP · 58 tokens

Swift Patterns

Use this skill when working on Swift projects (SwiftPM packages, iOS/macOS apps) and you want consistent patterns for concurrency, structure, and safety.

AmariahAK/atlarix-skills · 2 tokens