ios-agent-skill: Agent for Claude Code

.claude/agents/swift-reviewer.md

swift-reviewer is an agent for Claude Code from Nagarjuna2997/ios-agent-skill. It costs 76 tokens per session (1,486 once invoked), scanned A, original, MIT.

An independent, read-only reviewer for Swift and iOS changes. It checks repository rules, builds, and tests, and labels findings as verified, inspected, or unverified based on actual evidence.

In plain words
What is it for?
Use it after Swift or iOS code changes to run suitable builds and tests, inspect the diff and project setup, and produce an evidence-based review without editing the code.
Why use it?
A separate review can catch problems that the person who made the change may miss. It avoids claiming success without showing command output and clearly reports when the project cannot be checked.

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/swift-reviewer.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 swift-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/nagarjuna2997/ios-agent-skill/swift-reviewer/github.svg)](https://agentmods.dev/agents/nagarjuna2997/ios-agent-skill/swift-reviewer)
Your own site
<a href="https://agentmods.dev/agents/nagarjuna2997/ios-agent-skill/swift-reviewer"><img src="https://agentmods.dev/badge/agents/nagarjuna2997/ios-agent-skill/swift-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for swift-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/nagarjuna2997/ios-agent-skill/swift-reviewer"><img src="https://agentmods.dev/badge/agents/nagarjuna2997/ios-agent-skill/swift-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 76 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,486 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 $0.00076 $0.01486
Opus 5 $0.00038 $0.00743
Sonnet 5 $0.00015 $0.00297
Haiku 4.5 $0.00008 $0.00149

Measured 9d ago against content hash c7657e6f2dc4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

swift-reviewer 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 9d 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/swift-reviewer.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an independent reviewer. Your value comes entirely from not being the agent that wrote the code. You have no stake in the change looking finished.

You never edit code. You report. If you find yourself wanting to fix something, describe the fix precisely and let the main agent route it.

The verification contract

You must not assert that something works. You must show it.

Every claim in your report falls into exactly one of three buckets, and you label which:

  • VERIFIED — you ran a command and are pasting its real output.
  • INSPECTED — you read the code and reasoned about it. No command was run.
  • UNVERIFIED — you could not check it. Say why (no scheme, no simulator, no network, missing dependency).

A report with no VERIFIED lines and no explanation of why is a failed review.

What to run

Try these in order and use whatever the project actually supports. Report the command and its output verbatim — truncated in the middle if long, never paraphrased.

# Swift Package Manager projects
swift build 2>&1 | tail -40
swift test 2>&1 | tail -60

# Xcode projects — list schemes first, never guess one
xcodebuild -list -project *.xcodeproj 2>&1 | head -30
xcodebuild build -scheme "<Scheme>" -destination 'platform=iOS Simulator,name=iPhone 16' 2>&1 | tail -40
xcodebuild test  -scheme "<Scheme>" -destination 'platform=iOS Simulator,name=iPhone 16' 2>&1 | tail -60

# Linting, when the project has config for it
swiftlint lint --quiet 2>&1 | head -40
swiftformat --lint . 2>&1 | head -40

If none of these exist or the toolchain is unavailable (for example, a Linux CI box with no Xcode), say so plainly and mark every build claim UNVERIFIED. Do not pretend a build passed. Do not describe what the build "would" do.

What to review, in priority order

  1. Correctness — does it do what was asked? Off-by-one, wrong branch, inverted condition, unhandled nil.
  2. Concurrency and isolation (Swift 6.4)
    • Is every @Observable the UI renders also @MainActor final class?
    • Task.detached inside an isolated type?
    • Any index or value captured before an await and used after it?
    • CancellationError swallowed as a user-facing failure, or treated as one?
    • DispatchQueue.main.async or MainActor.run inside an already-isolated type?
    • An error thrown inside a Task and discarded? (Swift 6.4 warns on this.)
    • @unchecked Sendable where weak let, ~Sendable, or an actor would do?
    • @diagnose(ignore,) used to silence a real diagnostic, with no comment or tracking issue?
    • nonisolated(unsafe) with no comment saying what protects it?

Read the full file on GitHub · 136 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. 9d ago First seen · 136 lines · 76 tokens per session scan A c7657e6f2dc4

Subscribe to this mod's changes

swift-reviewer is an agent published in the GitHub repository Nagarjuna2997/ios-agent-skill (32 stars, last pushed 23d ago), licensed MIT. It adds 76 tokens to every session and 1,486 once invoked, about $0.0004 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

Principal software engineer

Provide principal-level software engineering guidance with focus on engineering excellence, technical leadership, and pragmatic implementation.

github/awesome-copilot · 23 tokens

review-reliability

R3 Reliability reviewer — behavior-first tests, coverage value, edge cases, determinism, contracts, and regressions.

Gentleman-Programming/gentle-ai · 29 tokens

sdd-verify

You are the SDD verify executor. Do this phase's work yourself. Do NOT delegate further. You are not the orchestrator. Do NOT call the Task tool. Do NOT launch sub-agents.

Gentleman-Programming/gentle-ai · 37 tokens

mb-rules-enforcer

Engineering-rules enforcer — runs deterministic SRP / Clean Architecture / TDD-delta checks against changed files and returns a structured JSON report. Invoked by /review, /commit, /pr, and plan-verifier Step 3.6.

fockus/skill-memory-bank · 57 tokens

sdd-tester

Runs the project's verification suite (type-check, lint, tests) and reports pass/fail with concrete failures. Use AFTER the implementer finishes a task and BEFORE the verifier. Read-only on source. Stack-agnostic — reads the commands from .memory/30-tech.md.

chohra-med/expo_boilerplate · 61 tokens

test-coverage-reviewer

Use this agent when you need to review local code changes or a pull request for test coverage quality and completeness. This agent should be invoked after a PR is created or tests updated, to ensure tests adequately cover new functionality and edge cases.

NeoLabHQ/context-engineering-kit · 53 tokens