ios-agent-skill: Agent for Claude Code

.claude/agents/core-ai-expert.md

core-ai-expert is an agent for Claude Code from Nagarjuna2997/ios-agent-skill. It costs 60 tokens per session (281 once invoked), scanned A, original, MIT.

A read-only reviewer for Apple Core AI integrations, which let apps run certain custom machine-learning models on Apple devices. It gives guidance about model assets, loading, device support, privacy, and testing without changing code.

In plain words
What is it for?
Use it to review custom .aimodel or .aimodelc files, Core AI integration, model specialization, provider choice, on-device inference, and debugging. It also helps distinguish Core AI from Foundation Models and Core ML.
Why use it?
It helps identify whether Core AI is the right Apple technology and whether an integration handles model loading, device availability, privacy, and tests correctly.

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/core-ai-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 core-ai-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/nagarjuna2997/ios-agent-skill/core-ai-expert.svg)](https://agentmods.dev/agents/nagarjuna2997/ios-agent-skill/core-ai-expert)
Your own site
<a href="https://agentmods.dev/agents/nagarjuna2997/ios-agent-skill/core-ai-expert"><img src="https://agentmods.dev/badge/agents/nagarjuna2997/ios-agent-skill/core-ai-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 60 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 281 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 $0.00060 $0.00281
Opus 5 $0.00030 $0.00140
Sonnet 5 $0.00012 $0.00056
Haiku 4.5 $0.00006 $0.00028

Measured 8d ago against content hash cfd41bc89ff4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

core-ai-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/core-ai-expert.md · 38 lines

What it actually says

You review Core AI integrations. You report; you do not edit.

Read docs/frameworks/core-ai.md and docs/ai/README.md before giving guidance.

Review Focus

  • Core AI is chosen for custom neural model assets, not language generation.
  • Foundation Models is used for prompts, structured generation, and tool calling.
  • Core ML remains the route for existing .mlmodel pipelines.
  • .aimodel assets are validated before app integration.
  • Model loading, specialization, and caching are off the main actor.
  • Availability and device capability checks gate the feature.
  • Privacy copy explains local inference and any provider escalation.
  • Tests use deterministic inputs and fixture outputs.

Output

VERDICT: pass | needs-core-ai-work | blocked

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

ROUTING
- Core AI vs Foundation Models vs Core ML:
- availability:
- privacy:
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 · 38 lines · 60 tokens per session scan A cfd41bc89ff4

Subscribe to this mod's changes

core-ai-expert is an agent published in the GitHub repository Nagarjuna2997/ios-agent-skill (32 stars, last pushed 22d ago), licensed MIT. It adds 60 tokens to every session and 281 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

data-engineer

Data engineering specialist — dbt/Snowflake validation, Jupyter notebooks, data artifact stewardship. Use when: dbt parse/compile/test, Snowflake read-only checks, notebook scaffolding, or validating data pipelines and dbt models per repo docs.

ulises-jeremias/agent-toolkit · 55 tokens

Prompt Builder

Expert prompt engineering and validation system for creating high-quality prompts - Brought to you by microsoft/edge-ai.

github/awesome-copilot · 24 tokens

data-engineer

Build scalable data pipelines, modern data warehouses, and real-time streaming architectures. Implements Apache Spark, dbt, Airflow, and cloud-native data platforms. Use PROACTIVELY for data pipeline design, analytics infrastructure, or modern data stack implementation.

wshobson/agents · 54 tokens

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