analyze

analyze is a command for coding agents from CarolaneLFBV/ios-development-agents. It costs 13 tokens per session (723 once invoked), scanned A, original, MIT.

An iOS code-analysis and review command that examines code for quality, performance, security, and architecture. It can route different parts of the review to specialised agents.

In plain words
What is it for?
Use it to analyse a target, focus on security, performance, architecture, or quality, create a review checklist, suggest Instruments checks, score quality, or format findings for a pull request.
Why use it?
It brings several kinds of review into one command, so important issues are less likely to be missed during development or code review.

Command

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 commands/carolanelfbv/ios-development-agents/analyze
Clone the repo
git clone --depth 1 https://github.com/CarolaneLFBV/ios-development-agents

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 analyze

README.md
[![agentmods](https://agentmods.dev/badge/commands/carolanelfbv/ios-development-agents/analyze.svg)](https://agentmods.dev/commands/carolanelfbv/ios-development-agents/analyze)
Your own site
<a href="https://agentmods.dev/commands/carolanelfbv/ios-development-agents/analyze"><img src="https://agentmods.dev/badge/commands/carolanelfbv/ios-development-agents/analyze.svg" alt="Measured on agentmods" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 723 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 $0.00013 $0.00723
Opus 5 $0.00006 $0.00362
Sonnet 5 $0.00003 $0.00145
Haiku 4.5 $0.00001 $0.00072

Measured 4d ago against content hash 1287134a8b10, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

analyze 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 4d 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.

commands/analyze.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/ios:analyze - iOS Code Analysis & Review

Analyze $ARGUMENTS for performance, architecture, security, quality, and code review.

Delegation

Route by --focus, spawning specialists in parallel via the Task tool (one Task per specialist), then consolidate their findings into the output below:

  • securitysecurity-specialist
  • performanceperformance-specialist
  • architecturearchitecture-specialist
  • quality (default) or --reviewswift-specialist + swiftui-specialist

Arguments

Flag Values Default Description
--focus performance|security|architecture|quality quality Analysis focus
--review - - Code review mode
--checklist - - Generate review checklist
--score - - Include quality score (0-100)
--pr - - PR review format
--instruments - - Include Instruments recommendations
--export <path> - Export results

Analysis Modes

Mode Output
Default Deep analysis with findings
--review Code review with suggestions
--checklist Structured checklist output
--score Numeric quality assessment
--pr PR approve/request changes format

Review Checklist (--checklist)

Swift Best Practices

  • Uses @Observable over ObservableObject
  • Proper error handling (no force unwraps)
  • Memory management (weak/unowned)
  • Async/await over completion handlers

SwiftUI Patterns

  • LazyVStack for lists
  • Proper state management
  • Small, focused views
  • Modern navigation APIs

Architecture

  • Single responsibility
  • Protocol-based abstractions
  • Dependency injection

Security

  • Keychain for sensitive data
  • No hardcoded secrets
  • Input validation

Quality Score (--score)

# Quality Score: 85/100
| Category | Score | Details |
|----------|-------|---------|
| Architecture | 90 | Clean separation |
| Performance | 80 | Minor optimizations |
| Security | 85 | Good practices |
| Maintainability | 85 | Clear code |

Read the full file on GitHub · 96 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. 4d ago First seen · 96 lines · 13 tokens per session scan A 1287134a8b10

Subscribe to this mod's changes

analyze is a command published in the GitHub repository CarolaneLFBV/ios-development-agents (7 stars, last pushed 1mo ago), licensed MIT. It adds 13 tokens to every session and 723 once invoked, about $0.0001 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 2026-08-31.