A guide for fetching Apple developer documentation as Markdown text. It covers references for Swift, SwiftUI, UIKit, and other Apple APIs, as well as Human Interface Guidelines and WWDC transcripts.

Use it when answering or implementing questions about Apple frameworks, API reference details, interface guidelines, WWDC sessions, or Swift documentation hosted outside Apple’s main site.

It helps a coding agent find precise Apple API details, including function signatures, availability, and behavior. This reduces reliance on incomplete or outdated assumptions when writing Apple-platform code.

sosumi — Skill for Claude Code and Codex by NSHipster/sosumi.ai

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.

Any agent

npx skills add NSHipster/sosumi.ai --skill public

Clone the repo

git clone --depth 1 https://github.com/NSHipster/sosumi.ai

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/nshipster/sosumi.ai/public/github.svg)](https://agentmods.dev/skills/nshipster/sosumi.ai/public)

Your own site

<a href="https://agentmods.dev/skills/nshipster/sosumi.ai/public"><img src="https://agentmods.dev/badge/skills/nshipster/sosumi.ai/public/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/nshipster/sosumi.ai/public"><img src="https://agentmods.dev/badge/skills/nshipster/sosumi.ai/public.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 952 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00036	$0.00952
Opus 5.5	$0.00014	$0.00381
Sonnet 5.5	$0.00007	$0.00190
Haiku 4.5	$0.00004	$0.00095

Measured 16d ago against content hash 858b3080a57e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sosumi 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 16d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (webmcp.js), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

public/SKILL.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sosumi Skill

Use this skill to reliably fetch Apple docs as Markdown when coding agents need precise API details.

When to Use

Use Sosumi when the request involves any of the following:

Apple platform APIs (Swift, SwiftUI, UIKit, AppKit, Foundation, etc.)
API signatures, availability, parameter behavior, or return semantics
Human Interface Guidelines questions
WWDC session transcript lookup
External Swift-DocC documentation (for example, GitHub Pages or Swift Package Index hosts)

Core Workflow

If you already have a developer.apple.com URL, replace the host with sosumi.ai and keep the same path.
If you do not know the exact page path, search first, then fetch the best match.
Prefer specific symbol pages instead of broad top-level pages when answering implementation questions.

Optional CLI Preflight

If the Sosumi CLI is available, quickly verify local access before deeper debugging:

sosumi --version confirms the CLI is installed and on PATH.
sosumi --help shows top-level usage.
sosumi <command> --help is the manual for command-specific behavior.

HTTP Usage

Replace developer.apple.com with sosumi.ai:

Original: https://developer.apple.com/documentation/swift/array
AI-readable: https://sosumi.ai/documentation/swift/array

Content Types

Apple API Reference

Pattern: https://sosumi.ai/documentation/{framework}/{symbol}
Examples:
- https://sosumi.ai/documentation/swift/array
- https://sosumi.ai/documentation/swiftui/view

Human Interface Guidelines

Pattern: https://sosumi.ai/design/human-interface-guidelines/{topic}
Examples:
- https://sosumi.ai/design/human-interface-guidelines
- https://sosumi.ai/design/human-interface-guidelines/foundations/color

Apple Video Transcripts

Pattern: https://sosumi.ai/videos/play/{collection}/{id}
Examples:
- https://sosumi.ai/videos/play/wwdc2021/10133
- https://sosumi.ai/videos/play/meet-with-apple/208

Read the full file on GitHub · 101 lines

Files

What ships with it

10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

16d ago Changed · +1 lines 858b3080a57e
2mo ago First seen · 100 lines · 36 tokens per session scan A 4530e014b049

Subscribe to this mod's changes

sosumi is a skill published in the GitHub repository NSHipster/sosumi.ai (483 stars, last pushed 16d ago), licensed MIT. It adds 36 tokens to every session and 952 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.

Research

sosumi next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
sosumiNSHipster/sosumi.ai	Skill	483	16d ago	MIT	A	36	Claude Code, Codex
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code