feature-directory-structure

feature-directory-structure is a skill for Claude Code, Codex from moasq/ios-dev-agent. It costs 66 tokens per session (1,170 once invoked), scanned A, original, MIT.

A project-organization guide for SwiftUI feature folders. It recommends keeping small features flat and grouping larger features into folders such as Sections, Sheets, Overlays, and Backdrop.

In plain words
What is it for?
Use it when a feature grows beyond about five files or gains extra screens, sheets, overlays, or background views.
Why use it?
It prevents features with many files from becoming difficult to browse and maintain. Related views stay grouped by their role.

Skill for Claude CodeCodex

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 skills/moasq/ios-dev-agent/feature-directory-structure
Any agent
npx skills add moasq/ios-dev-agent --skill feature-directory-structure
Clone the repo
git clone --depth 1 https://github.com/moasq/ios-dev-agent

Made for: Claude Code, Codex.

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 feature-directory-structure

README.md
[![agentmods](https://agentmods.dev/badge/skills/moasq/ios-dev-agent/feature-directory-structure.svg)](https://agentmods.dev/skills/moasq/ios-dev-agent/feature-directory-structure)
Your own site
<a href="https://agentmods.dev/skills/moasq/ios-dev-agent/feature-directory-structure"><img src="https://agentmods.dev/badge/skills/moasq/ios-dev-agent/feature-directory-structure.svg" alt="Measured on agentmods" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,170 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 $0.00066 $0.01170
Opus 5 $0.00033 $0.00585
Sonnet 5 $0.00013 $0.00234
Haiku 4.5 $0.00007 $0.00117

Measured 3d ago against content hash 90d3a773e345, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

feature-directory-structure 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 3d 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.

.agents/skills/feature-directory-structure/SKILL.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Feature Directory Structure

Features with many files must use nested subdirectories. Flat is fine up to a point; past that, subfolders are required.

The Rule

Flat — up to 5 files total per feature

When a feature has 5 or fewer files, keep it flat:

Features/Profile/
  ProfileView.swift
  ProfileViewModel.swift
  ProfileView+Header.swift

Three files, still scannable. No need for subfolders.

Nested — 6+ files per feature

Past ~5 files, group into subfolders by role:

Features/Home/
  HomeView.swift          ← main shell (body is table of contents)
  HomeViewModel.swift     ← one @Observable class
  Sections/               ← extracted body sections (View+X.swift)
    HomeView+Idle.swift
    HomeView+Recording.swift
    HomeView+Result.swift
  Sheets/                 ← .sheet / .fullScreenCover contents
    PillarDetailSheet.swift
    HistoryBrowseSheet.swift
  Overlays/               ← ZStack overlays, toasts, celebration
    CelebrationOverlay.swift
    StreakToastView.swift
  Backdrop/               ← ambient backgrounds, visual effects
    AmbientBackdrop.swift

The shell (HomeView.swift + HomeViewModel.swift) stays at the feature root. Everything else goes into a subfolder.

Canonical Subfolder Names

Use these names consistently across features. Don't invent new ones.

Folder What goes in it
Sections/ View+X.swift extensions — extracted body sections of the main view
Sheets/ Views presented via .sheet or .fullScreenCover — each is its own standalone View
Overlays/ ZStack overlays, toasts, celebration cards, modal affordances
Backdrop/ Ambient backgrounds, particle scenes, blur effects, visual-only layers
Components/ Feature-local reusable subviews that don't fit the above and aren't shared (shared components belong in Features/Common/)
Rows/ List row views when a feature has 3+ row variants

When NOT to split

Don't create a subfolder for a single file. Sheets/PillarDetailSheet.swift alone is fine only if you expect another sheet to land in v1.1 — otherwise keep it at the feature root until a second sheet forces the split.

Read the full file on GitHub · 117 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. 3d ago First seen · 117 lines · 66 tokens per session scan A 90d3a773e345

Subscribe to this mod's changes

feature-directory-structure is a skill published in the GitHub repository moasq/ios-dev-agent (4 stars, last pushed 3mo ago), licensed MIT. It adds 66 tokens to every session and 1,170 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens