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.
curl -O https://raw.githubusercontent.com/Nagarjuna2997/ios-agent-skill/main/.claude/agents/swift-reviewer.mdgit clone --depth 1 https://github.com/Nagarjuna2997/ios-agent-skillWrote 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.
[](https://agentmods.dev/agents/nagarjuna2997/ios-agent-skill/swift-reviewer)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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
- Correctness — does it do what was asked? Off-by-one, wrong branch, inverted condition, unhandled nil.
- Concurrency and isolation (Swift 6.4)
- Is every
@Observablethe UI renders also@MainActor final class? Task.detachedinside an isolated type?- Any index or value captured before an
awaitand used after it? CancellationErrorswallowed as a user-facing failure, or treated as one?DispatchQueue.main.asyncorMainActor.runinside an already-isolated type?- An error thrown inside a
Taskand discarded? (Swift 6.4 warns on this.) @unchecked Sendablewhereweak let,~Sendable, or anactorwould do?@diagnose(ignore,)used to silence a real diagnostic, with no comment or tracking issue?nonisolated(unsafe)with no comment saying what protects it?
- Is every
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.
- 9d ago First seen · 136 lines · 76 tokens per session scan A c7657e6f2dc4
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.
Other agents, from other repositories
Principal software engineer
Provide principal-level software engineering guidance with focus on engineering excellence, technical leadership, and pragmatic implementation.
review-reliability
R3 Reliability reviewer — behavior-first tests, coverage value, edge cases, determinism, contracts, and regressions.
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.
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.
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.
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.