ios-agent-skill: Agent for Claude Code

.claude/agents/metal-expert.md

metal-expert is an agent for Claude Code from Nagarjuna2997/ios-agent-skill. It costs 52 tokens per session (256 once invoked), scanned A, original, MIT.

A read-only reviewer for Apple Metal graphics code, including GPU shaders, rendering views, and command buffers.

In plain words
What is it for?
Use it to review custom GPU rendering, compute work, camera textures, particles, and Metal performance.
Why use it?
It finds correctness, performance, synchronization, and device-resource risks without changing the code.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is Nagarjuna2997/ios-agent-skill's own configuration. It tells Claude Code how to work on ios-agent-skill itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ios-agent-skill configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Nagarjuna2997/ios-agent-skill. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Nagarjuna2997/ios-agent-skill/main/.claude/agents/metal-expert.md
Clone the repo
git clone --depth 1 https://github.com/Nagarjuna2997/ios-agent-skill

Made for: Claude Code.

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 metal-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/nagarjuna2997/ios-agent-skill/metal-expert.svg)](https://agentmods.dev/agents/nagarjuna2997/ios-agent-skill/metal-expert)
Your own site
<a href="https://agentmods.dev/agents/nagarjuna2997/ios-agent-skill/metal-expert"><img src="https://agentmods.dev/badge/agents/nagarjuna2997/ios-agent-skill/metal-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 256 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00052 $0.00256
Opus 5 $0.00026 $0.00128
Sonnet 5 $0.00010 $0.00051
Haiku 4.5 $0.00005 $0.00026

Measured 8d ago against content hash 98bb64007568, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

metal-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 8d 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/metal-expert.md · 37 lines

What it actually says

You review Metal integrations. You report; you do not edit.

Read docs/frameworks/metal.md, docs/graphics/README.md, and patterns/metal/README.md.

Review Focus

  • Metal is justified over SwiftUI shaders, Core Image, SpriteKit, or RealityKit.
  • Command queue, pipeline state, buffers, and textures are not recreated per frame.
  • Drawable acquisition is guarded.
  • Pixel formats, depth formats, and color spaces are consistent.
  • Buffer sizing and alignment are explicit.
  • CPU/GPU synchronization avoids stalls.
  • Long-running effects consider thermal, battery, and Reduce Motion.

Output

VERDICT: pass | needs-metal-work | blocked

FINDINGS
1. path/to/File.swift:88 — <issue>
   why:
   fix:

PERFORMANCE RISKS
- per-frame allocation:
- synchronization:
- frame pacing:
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. 8d ago First seen · 37 lines · 52 tokens per session scan A 98bb64007568

Subscribe to this mod's changes

metal-expert is an agent published in the GitHub repository Nagarjuna2997/ios-agent-skill (32 stars, last pushed 22d ago), licensed MIT. It adds 52 tokens to every session and 256 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

designer

Design routing and UI/UX specialist — owns contextual selection among design skills (frontend-design, frontend-design-review, web-design-guidelines, design-assessment, design-improvement, Figma family, accessibility/review). Use when: new visual direction, design review, WIG audit, holistic UX diagnosis…

ulises-jeremias/agent-toolkit · 78 tokens

architect

Software architecture and system design specialist. Use when designing systems, choosing patterns, evaluating technical approaches, or planning large-scale structural changes.

ulises-jeremias/agent-toolkit · 28 tokens

code-reviewer

Expert code review specialist — quality/correctness/security/performance/testing with severity-ranked findings. Use when reviewer/qa-engineer delegates deep craft or PR explicitly warrants independent verification; opt-in via holistic caller.

ulises-jeremias/agent-toolkit · 45 tokens

e2e-runner

End-to-end testing specialist using Playwright — selector discipline, POM, and flake avoidance with explicit browser-output isolation. Use when qa-engineer delegates E2E authoring/debugging or task explicitly requires Playwright specs; opt-in via holistic caller — not a daily entry point.

ulises-jeremias/agent-toolkit · 64 tokens

security-reviewer

App-code security review specialist — OWASP Top 10 (injection, auth, data exposure, deps), CVE-mapped. Use when security-engineer delegates app-surface hardening or code change touches auth/data/API; opt-in via holistic caller.

ulises-jeremias/agent-toolkit · 56 tokens

ndv-forecast

Estimation realist. Use when reviewing estimates, sprint plans, roadmaps, or any commitment about time. Calibrates optimistic projections against known laws of software estimation. Temporal dysphoria as a cognitive style — viscerally aware that "almost done" is a trap, the last 10% is where time goes to die, and every…

emb715/neurodiveragents · 87 tokens