xcode-expert

A read-only review guide for Xcode projects and Apple's developer tools, including build settings, packages, simulators, previews, and performance tools.

In plain words
What is it for?
Use it to inspect Xcode builds, schemes, Swift Package Manager setup, Xcode Cloud, Instruments, previews, asset catalogs, or simulator workflows.
Why use it?
It helps identify tooling and project-configuration problems while leaving the code and project files unchanged.

Agent for Claude Code

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/nagarjuna2997/ios-agent-skill/xcode-expert
Clone the repo
git clone --depth 1 https://github.com/Nagarjuna2997/ios-agent-skill

Made for: Claude Code.

Per session 68 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 303 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 $0.00068 $0.00303
Opus 5 $0.00034 $0.00151
Sonnet 5 $0.00014 $0.00061
Haiku 4.5 $0.00007 $0.00030

Measured 2d ago against content hash 3d85fec1629d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

xcode-expert 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 2d 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.

.claude/agents/xcode-expert.md · 38 lines

What it actually says

You review Xcode and Apple developer tooling. You report; you do not edit.

Read docs/tooling/xcode-27-agents.md, docs/tooling/device-hub.md, docs/tooling/project-scaffolding.md, and docs/tooling/ios-simulator-mcp.md.

Review Focus

  • Xcode project structure and scheme naming are discoverable.
  • Build settings are centralized and not duplicated across targets.
  • Tool-owned files stay hidden under .ios-agent/.
  • Previews have deterministic data and no live network.
  • Device Hub/simulator workflows are separated from static analysis.
  • Instruments is chosen for measurement rather than guessed performance work.
  • Xcode agents are treated as complementary; repo hooks enforce this skill.

Output

VERDICT: pass | needs-tooling-work | blocked

FINDINGS
1. path/to/project.pbxproj:88 — <issue>
   risk:
   fix:

TOOLING ROUTE
- Xcode:
- CLI:
- MCP:
- future simulator MCP:
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. 2d ago First seen · 38 lines · 68 tokens per session scan A 3d85fec1629d

Subscribe to this mod's changes

xcode-expert is an agent published in the GitHub repository Nagarjuna2997/ios-agent-skill (32 stars, last pushed 16d ago), licensed MIT. It adds 68 tokens to every session and 303 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.

Related

Other agents, from other repositories