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 itsnex1s/awesome-claude-skills --skill apple-docsgit clone --depth 1 https://github.com/itsnex1s/awesome-claude-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/itsnex1s/awesome-claude-skills/apple-docs)<a href="https://agentmods.dev/skills/itsnex1s/awesome-claude-skills/apple-docs"><img src="https://agentmods.dev/badge/skills/itsnex1s/awesome-claude-skills/apple-docs/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/itsnex1s/awesome-claude-skills/apple-docs"><img src="https://agentmods.dev/badge/skills/itsnex1s/awesome-claude-skills/apple-docs.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 | $0.00057 | $0.00813 |
| Opus 5.5 | $0.00023 | $0.00325 |
| Sonnet 5.5 | $0.00011 | $0.00163 |
| Haiku 4.5 | $0.00006 | $0.00081 |
Grade A, and why
apple-docs scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apple Documentation Lookup
Fetch Apple Developer Documentation and WWDC session transcripts as clean markdown using the sosumi CLI tool.
Installation
npm install -g @nshipster/sosumi
# or use directly with npx (no install needed)
Commands
Search documentation
When the user needs to find an API, framework, or concept:
npx @nshipster/sosumi search "$ARGUMENTS" 2>/dev/null
Fetch specific documentation page
When the user provides a documentation path or URL:
npx @nshipster/sosumi fetch "$ARGUMENTS" 2>/dev/null
Fetch WWDC session transcript
When the user asks about a WWDC session:
npx @nshipster/sosumi fetch "/videos/play/wwdc{year}/{session-id}" 2>/dev/null
How to decide which command to use
- If
$ARGUMENTSstarts with/documentationor/videosorhttps://developer.apple.com→ usefetch - If
$ARGUMENTSis a search query (e.g. "SwiftData", "HealthKit sleep") → usesearch - If no arguments provided → ask the user what they want to look up
Workflow
- Run the appropriate sosumi command
- Read the output (markdown-formatted Apple documentation)
- Present the relevant information to the user in a concise summary
- If the search returned multiple results, pick the most relevant and offer to fetch the full docs
- When fetching API docs, highlight: signature, availability, key parameters, and usage notes
Common documentation paths
/documentation/swiftui
/documentation/swiftdata
/documentation/observation
/documentation/charts
/documentation/healthkit
/documentation/widgetkit
/documentation/backgroundtasks
/documentation/foundation
/documentation/uikit
/documentation/combine
/documentation/concurrency
/documentation/corelocation
/documentation/mapkit
/documentation/avfoundation
/documentation/coreml
/documentation/createml
/documentation/vision
/documentation/naturallanguage
/documentation/appintents
Example usage
User: /apple-docs HKCategoryValueSleepAnalysis
→ Run: npx @nshipster/sosumi search "HKCategoryValueSleepAnalysis"
→ Then fetch the top result if needed
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.
- 2mo ago First seen · 106 lines · 57 tokens per session scan A 79d252aef8c2
apple-docs is a skill published in the GitHub repository itsnex1s/awesome-claude-skills (5 stars, last pushed 8mo ago), licensed MIT. It adds 57 tokens to every session and 813 once invoked, about $0.0002 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 2026-08-31.
apple-docs compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| apple-docsitsnex1s/awesome-claude-skills | Skill | 5 | 8mo ago | MIT | A | 57 | Claude Code |
| agent-browserx-cmd/x-cmd | Skill | 4.7k | 9d ago | Apache-2.0 | A | 39 | Claude Code, Codex |
| winapp-mauimicrosoft/winappCli | Skill | 1.4k | 2d ago | MIT | A | 68 | Claude Code |
| sweetpadsweetpad-dev/sweetpad | Skill | 1.9k | today | MIT | A | 90 | Claude Code, Codex |
| compose-multiplatform-patternshashgraph-online/awesome-codex-plugins | Skill | 1.5k | yesterday | Apache-2.0 | A | 37 | Claude Code, Codex |
| Swift Performance Optimization Skilltermio-sh/termio | Skill | 787 | 6d ago | MIT | A | 68 | Claude Code, Codex |
| asctermio-sh/termio | Skill | 787 | 6d ago | MIT | A | 108 | Claude Code, Codex |