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 skills add troyjthomas/ios-agent-skills --skill polish-and-refinementgit clone --depth 1 https://github.com/troyjthomas/ios-agent-skillsWrote 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/skills/troyjthomas/ios-agent-skills/polish-and-refinement)<a href="https://agentmods.dev/skills/troyjthomas/ios-agent-skills/polish-and-refinement"><img src="https://agentmods.dev/badge/skills/troyjthomas/ios-agent-skills/polish-and-refinement/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/skills/troyjthomas/ios-agent-skills/polish-and-refinement"><img src="https://agentmods.dev/badge/skills/troyjthomas/ios-agent-skills/polish-and-refinement.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 | $0.00080 | $0.01988 |
| Opus 5 | $0.00040 | $0.00994 |
| Sonnet 5 | $0.00016 | $0.00398 |
| Haiku 4.5 | $0.00008 | $0.00199 |
Grade A, and why
polish-and-refinement 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 10d 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 — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Polish and Refinement
The app works. Data persists. Navigation flows. Now make it feel like YOUR app.
When to Use
- All screens are built and functional
- Data persistence is working
- You're ready to move from "works" to "feels great"
- You have Figma comps you want to match (optional)
The Polish Checklist
Work through these categories. Each one is a focused Claude Code session or Conductor workspace.
1. Color and Tinting
Apply the app's color system:
- Primary tint color: [hex] throughout the app
- Verify all interactive elements use the tint (buttons, links, toggles)
- Check that semantic colors (destructive red, success green) still
use system defaults
- Verify dark mode: tint should still be readable and vibrant
2. Liquid Glass (iOS 26)
Apply Liquid Glass material to:
- Navigation bars
- Tab bar
- [Any other chrome elements you want]
Do not apply Liquid Glass to:
- Content areas
- Cards or list rows
- Sheets (use system default presentation)
Use Sosumi MCP to look up the latest Liquid Glass APIs. These are new and evolving. Tell Claude Code:
Search Sosumi for "glassEffect" and "Liquid Glass" to get the
latest API documentation before implementing.
See references/liquid-glass.md for known patterns and the AvdLee SwiftUI Agent Skill repo for comprehensive Liquid Glass guidance.
Known gotchas:
.glassEffect()must be applied AFTER background modifiers, not before- System chrome (nav bars, tab bars) gets Liquid Glass automatically in iOS 26
- Do NOT manually apply
.glassEffectto system chrome (doubles the effect) - Leave intensity and tinting at system defaults for v1
Glass-button label rules — read carefully before building any custom glass button:
- NEVER apply
.foregroundColor(.white)or.foregroundStyle(.white)to labels inside.glassProminentbuttons. The system applies a vibrancy treatment that produces the correct tinted-white automatically; forcing.whiteoverrides vibrancy and gives flat pure-white glyphs that look painted-on. The rule is specifically about WHITE — explicitColor.blackfor dark-mode legibility against pale-tint pills (see below) is a different and acceptable concern.
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.
- 10d ago First seen · 215 lines · 80 tokens per session scan A e49d604710d3
polish-and-refinement is a skill published in the GitHub repository troyjthomas/ios-agent-skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 80 tokens to every session and 1,988 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 2026-08-31.
Other skills, from other repositories
ios-accessibility
Build and audit SwiftUI, UIKit, and AppKit accessibility for VoiceOver, Voice Control, Switch Control, Full Keyboard Access, Dynamic Type, focus restoration, labels/traits/actions, traversal, custom rotors, NSAccessibility, XCTest checks, adaptive system preferences, and App Store accessibility declarations. Use when…
pencilkit
Add Apple Pencil drawing with PKCanvasView, PKToolPicker, PKDrawing serialization/export, stroke inspection, and PencilKit/PaperKit handoffs. Use when building drawing apps, annotation features, handwriting capture, signature fields, content-version-safe ink workflows, or Apple Pencil-powered experiences on…
swiftui-liquid-glass
Implement, review, or improve SwiftUI Liquid Glass effects for iOS 26+. Covers glassEffect modifier, GlassEffectContainer, glass button styles, glass toolbar/tab bar, static status badges vs interactive controls, morphing transitions, tinting, interactive glass, ToolbarSpacer, scrollEdgeEffectStyle…
swiftui-design-principles
Design principles for building polished, native-feeling SwiftUI apps and widgets. Use this skill when creating or modifying SwiftUI views, iOS widgets (WidgetKit), or any native Apple UI. Ensures proper spacing, typography, colors, and widget implementations that look and feel like quality apps rather than…
swift-accessibility-skill
Apply platform accessibility best practices to SwiftUI, UIKit, and AppKit code. Essential companion to any SwiftUI, UIKit, or AppKit skill — always use together. Use whenever writing, editing, or reviewing ANY SwiftUI views, UIKit view controllers, AppKit views/window controllers, or platform UI — even when the user…
figma-to-swiftui
Translate Figma designs into production-ready SwiftUI code with 1:1 visual fidelity using the Figma MCP workflow. Trigger when the user provides Figma URLs or node IDs and wants iOS/SwiftUI implementation, asks to implement a design or component from Figma for an iOS app, or references Figma selections in the context…