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.
npx agentmods add commands/carolanelfbv/ios-development-agents/improvegit clone --depth 1 https://github.com/CarolaneLFBV/ios-development-agentsWhat 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 | $0.00011 | $0.00588 |
| Opus 5 | $0.00005 | $0.00294 |
| Sonnet 5 | $0.00002 | $0.00118 |
| Haiku 4.5 | $0.00001 | $0.00059 |
Grade A, and why
improve 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 2d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ios:improve - iOS Code Improvement
Improve code from $ARGUMENTS for quality, performance, and maintainability.
Delegation
Route by --focus / --to via the Task tool:
performance→ performance-specialistaccessibility→ swiftui-specialistarchitecture/--to swiftdata→ architecture-specialistquality/--to observable|async|actor→ swift-specialist
With --preview, have the specialist report proposed changes before applying.
Arguments
| Flag | Values | Default | Description |
|---|---|---|---|
--focus |
performance|accessibility|architecture|quality | quality | Improvement focus |
--to |
observable|swiftdata|async|actor | - | Refactor to modern pattern |
--safe |
- | - | Apply only safe, low-risk improvements |
--preview |
- | - | Show improvements without applying |
--iterative |
- | - | Apply improvements in multiple passes |
Refactoring Patterns (--to)
| Pattern | From | To |
|---|---|---|
--to observable |
ObservableObject | @Observable |
--to async |
Completion handlers | async/await |
--to actor |
NSLock/DispatchQueue | actor |
--to swiftdata |
CoreData | SwiftData |
Focus Areas
| Focus | Improvements |
|---|---|
performance |
LazyVStack, image optimization, memory |
accessibility |
VoiceOver labels, Dynamic Type, contrast |
architecture |
Protocol abstractions, DI, separation |
quality |
Naming, SOLID, error handling |
Examples
# Quality improvements
/ios:improve Views/ --focus quality --safe --preview
# Performance optimization
/ios:improve ProductListView.swift --focus performance --iterative
# Refactoring
/ios:improve ViewModel.swift --to observable
/ios:improve DataService.swift --to async
/ios:improve Cache.swift --to actor
Output
# Improvements: [Target]
## Summary: Files analyzed | Issues found | Applied | Risk level
## Changes Made: File | Issue | Solution | Impact
## Performance Impact: Before → After metrics
## Next Steps: Tests, profiling, verification
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.
- 2d ago First seen · 73 lines · 11 tokens per session scan A e709d1f991cf
improve is a command published in the GitHub repository CarolaneLFBV/ios-development-agents (7 stars, last pushed 1mo ago), licensed MIT. It adds 11 tokens to every session and 588 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.
Other commands, from other repositories
android
Command "android" from zhagqn/agentwork, covering /android [subcommand] [args] and 执行前必读.
compose-test
Run Compose UI tests with Espresso. Verify critical user flows.
app-store-audit
Run an enterprise pre submission compliance audit on an iOS or Android app against Apple App Store and Google Play rejection rules. Pass a project path or run from the project root.
build-verify
Run the full build / test / analyze / format verification pass for this Flutter app.
ios-privacy
Prepare privacy labels, permissions, policy links, and data-use truth for iOS release.
initialize-ios
Manual override: initialize ast-index for iOS/Swift/ObjC project.