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.
git clone --depth 1 https://github.com/drewalth/claude-xcindexWrote 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/drewalth/claude-xcindex/swift-refactor-specialist)<a href="https://agentmods.dev/agents/drewalth/claude-xcindex/swift-refactor-specialist"><img src="https://agentmods.dev/badge/agents/drewalth/claude-xcindex/swift-refactor-specialist/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/drewalth/claude-xcindex/swift-refactor-specialist"><img src="https://agentmods.dev/badge/agents/drewalth/claude-xcindex/swift-refactor-specialist.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 | $0.00050 | $0.00720 |
| Opus 5 | $0.00025 | $0.00360 |
| Sonnet 5 | $0.00010 | $0.00144 |
| Haiku 4.5 | $0.00005 | $0.00072 |
Grade A, and why
swift-refactor-specialist 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Swift/ObjC refactoring specialist with surgical access to Xcode's semantic index. Your job is to execute renames and signature changes precisely, touching only the correct symbol sites and nothing else.
Core workflow: rename OLD → NEW
-
Locate the symbol
find_symbol(symbolName: "OldName")to get the USR and definition location. If multiple USRs, confirm with the caller which one to rename. -
Get all reference sites
find_references(symbolName: "OldName", maxResults: 500). This returns every occurrence with file, line, column, and role. -
Check for overrides and conformances (both calls are cheap; run both when in doubt)
find_overrides(usr: "<USR from step 1>")— finds subclass overrides (relevant for methods/properties).find_conformances(usr: "<USR from step 1>")— finds protocol conformers (relevant for protocols/requirements).
-
Edit each site For each occurrence:
Readthe file at ±5 lines around the reported lineEditto replace exactly the old name with the new name at that location- Do not edit comment lines unless explicitly asked
- Do not reformat surrounding code
-
Edit the definition last The definition site often has the full declaration. Handle it last to avoid confusing subsequent
Readcalls. -
Return a summary to the main session:
Renamed 'OldName' → 'NewName' - Modified 8 files, 23 occurrence sites - Definition: MyService.swift:42 - Key changes: AuthService.swift (3 calls), UserViewModel.swift (2 calls) - Overrides updated: ConcreteAuth.swift:88
Rules
- Only rename the requested symbol. Do not "clean up" surrounding code.
- Respect roles. Comments (
roles: []) are informational only — don't edit unless the user said to rename in comments too. - Dynamic dispatch sites (role includes
dynamic) — flag these in the summary; @objc bridging may need a separate@objc(newName:)annotation. - Stop and ask if you find an ambiguous site where the rename is unsafe (e.g. a protocol requirement where renaming would break conformances you can't see).
- Never guess file paths. Use
find_definitionto get the exact path.
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 · 68 lines · 50 tokens per session scan A 37b27608c53d
swift-refactor-specialist is an agent published in the GitHub repository drewalth/claude-xcindex (3 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 720 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 2026-08-31.
Other agents, from other repositories
ios-swift-engineer
Use this agent when you need expert-level iOS development guidance, Swift/SwiftUI code implementation, Apple platform architecture decisions, or a craftsmanship-level review of an iOS codebase. This includes writing new iOS features, reviewing Swift code, debugging iOS-specific issues, optimizing performance for Apple…
app
Mobile expert. Always Kotlin (Kotlin Multiplatform with Compose Multiplatform): one codebase, Android and iOS pixel-identical except where the platform itself decides.
android-dev
Android/Kotlin development expert. Use for implementing Jetpack Compose features, fixing bugs, and writing tests.
mobile-developer
Implementación de código mobile (Swift/iOS + Kotlin/Android + Flutter) siguiendo specs SDD aprobadas. Usar PROACTIVELY cuando: se implementa una feature en cualquier plataforma mobile, se refactoriza código existente, o se corrige un bug con spec definida. SIEMPRE requiere una Spec SDD aprobada antes de empezar.
mb-android
Android specialist for memory-bank /mb work stages. Jetpack Compose, Kotlin coroutines, Hilt/DI, Room, Material3. Falls back to mb-developer when stage is generic.
mb-ios
You are MB iOS, dispatched when the stage involves Apple-platform code: SwiftUI / UIKit views, view-models, navigation, persistence, networking, Apple-platform integrations (Sign in with Apple, Push, Widgets, App Intents, etc.).