build-agent

build-agent is an agent for coding agents from markdavidgan/apple-dev-skills. It costs 32 tokens per session (961 once invoked), scanned A, original, MIT.

A coding agent for building and compiling iOS and Swift projects, including projects managed with Xcode. It focuses on finding causes of build and compilation failures.

In plain words
What is it for?
Use it to investigate compiler errors, failed build scripts, dependency resolution problems, CI/CD failures, and Xcode Cloud build failures.
Why use it?
It helps locate problems in Xcode projects, build scripts, dependencies, and automated build services without requiring you to diagnose each failure manually.

Agent

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 agents/markdavidgan/apple-dev-skills/build-agent
Clone the repo
git clone --depth 1 https://github.com/markdavidgan/apple-dev-skills

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 build-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/markdavidgan/apple-dev-skills/build-agent.svg)](https://agentmods.dev/agents/markdavidgan/apple-dev-skills/build-agent)
Your own site
<a href="https://agentmods.dev/agents/markdavidgan/apple-dev-skills/build-agent"><img src="https://agentmods.dev/badge/agents/markdavidgan/apple-dev-skills/build-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 961 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 $0.00032 $0.00961
Opus 5 $0.00016 $0.00481
Sonnet 5 $0.00006 $0.00192
Haiku 4.5 $0.00003 $0.00096

Measured 3d ago against content hash 7010b86ae116, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

build-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 3d 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.

platforms/claude/agents/build-agent.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fast build troubleshooting and build system management agent for iOS development.

Provider Model Equivalents

Tier: Fast — build error parsing is pattern-matching, not deep reasoning. Escalate to Standard only for novel concurrency issues.

Provider Model Notes
Claude claude-haiku-4-5, effort: low Default
GPT gpt-4.1-mini
Gemini gemini-3.0-flash
Kimi CLI kimi-for-coding Only model available in Kimi Code CLI
Kimi API kimi-for-coding Use for fast tasks
Antigravity Gemini 3 Flash or GPT-OSS-120b Select in model dropdown; no subagent dispatch

When to Use

  • Build compilation errors
  • Xcode project issues
  • Build script failures
  • Dependency resolution problems
  • CI/CD build issues
  • Xcode Cloud failures

Common Build Commands

# iOS Simulator Build
xcodebuild -scheme <YourScheme> \
  -destination 'platform=iOS Simulator,name=iPhone 17 Pro Max' \
  build

# Watch Build
xcodebuild -scheme <YourWatchScheme> \
  -destination 'platform=watchOS Simulator,name=Apple Watch Series 11 (46mm)' \
  build

# Archive Build (catches strict concurrency errors)
xcodebuild -scheme <YourScheme> -configuration Release \
  -destination 'generic/platform=iOS' archive

# Package Tests
cd <YourPackage> && swift test

# Regenerate project (XcodeGen)
xcodegen generate

Build Troubleshooting Checklist

Compilation Errors

  • Swift syntax errors
  • Missing imports
  • Type mismatches
  • Access control issues (public/internal/private)

Concurrency Issues

  • MainActor isolation errors (often only in archive builds)
  • Sendable conformance issues
  • @preconcurrency imports are ONLY present where the compiler specifically demanded them (prophylactic use is obsolete for iOS 26 frameworks)

Project Issues

  • project.yml syntax errors
  • Missing files in target
  • Duplicate symbols
  • Framework not found

Swift Package Issues

  • Package.resolved conflicts
  • Dependency version mismatches
  • Binary framework issues

Read the full file on GitHub · 150 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. 3d ago First seen · 150 lines · 32 tokens per session scan A 7010b86ae116

Subscribe to this mod's changes

build-agent is an agent published in the GitHub repository markdavidgan/apple-dev-skills (5 stars, last pushed 4d ago), licensed MIT. It adds 32 tokens to every session and 961 once invoked, about $0.0002 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 2026-08-31.