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 agentmods add instructions/prisma-labs-dev/apple-skills/agents-mdgit clone --depth 1 https://github.com/Prisma-Labs-Dev/apple-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/instructions/prisma-labs-dev/apple-skills/agents-md)<a href="https://agentmods.dev/instructions/prisma-labs-dev/apple-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/prisma-labs-dev/apple-skills/agents-md.svg" alt="Measured on agentmods" 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 | $0.01120 | $0.01120 |
| Opus 5 | $0.00560 | $0.00560 |
| Sonnet 5 | $0.00224 | $0.00224 |
| Haiku 4.5 | $0.00112 | $0.00112 |
Grade A, and why
apple-skills AGENTS.md 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 4d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apple Skills Maintainer Guide
This file is for agents maintaining this repository. It is not end-user documentation, and it is not the runtime instruction file for agents that install these skills into Claude Code, Codex, Cursor, or another coding agent.
Table of Contents
| Need | Start Here | Notes |
|---|---|---|
| Explain the project to humans | README.md |
Keep it brief, friendly, and installation-focused. Put copy-pasteable user commands here, not maintainer runbooks. |
| Understand install surfaces | README.md and .claude-plugin/ |
Claude Code installs via the plugin marketplace; Codex and Cursor use the Skills CLI to copy skills/ entries into agent skill directories. |
| Maintain generated Apple docs | MAINTAINING.md |
Refresh workflow, DocC rendering details, tooling, and repo structure live there. |
| Update skill behavior | skills/<name>/SKILL.md |
These are the installed agent-facing instructions for a specific skill. Edit them deliberately; they are consumed by downstream agents. |
| Update generated reference docs | skills/<name>/*.md |
Use the generated-vs-hand-authored rules below. Prefer refresh tooling over hand edits for generated files. |
| Work on doc rendering tooling | scripts/apple-docs.ts and scripts/apple-docs/ |
TypeScript tooling fetches Apple's DocC JSON and renders markdown. |
| Run checks | package.json |
Use pnpm check for the full gate; individual commands are listed in MAINTAINING.md. |
| Validate install commands | README.md install blocks |
Test in a temporary HOME/XDG_CONFIG_HOME so real agent configs are not modified. |
| Publish Claude Code plugin metadata | .claude-plugin/ |
Marketplace/plugin metadata for Claude Code lives here. |
Generated vs Hand-Authored Files
Do not classify an entire skill directory as generated or hand-authored. A single skills/<name>/ directory can contain both.
| Pattern | Ownership | How to Change |
|---|---|---|
skills/**/SKILL.md |
Hand-authored | Edit directly when changing installed skill instructions. |
skills/**/*.md with YAML frontmatter containing source: https://developer.apple.com/... |
Generated from Apple's DocC JSON | Regenerate with the tooling in MAINTAINING.md; avoid hand edits except to repair the generator or unblock a refresh. |
skills/**/*.videos.md |
Generated sidecar for Apple DocC video references | Regenerate with the docs refresh flow; keep sidecar behavior generic. |
skills/**/references/**, skills/**/docs/**, skills/**/assets/**, skills/**/scripts/**, skills/**/agents/** |
Hand-authored unless the file itself has generated frontmatter | Edit directly, preserving local guide or asset conventions. |
Root docs such as README.md, MAINTAINING.md, AGENTS.md, and CHANGELOG.md |
Hand-authored | Edit directly for human or maintainer documentation. |
scripts/**, tests/**, package.json, biome.json, tsconfig.json |
Hand-authored tooling | Edit directly and run the relevant checks. |
| Generated-looking failure output or stale fetched content | Generated artifact to fix at the source | Do not polish it manually; refresh, remove, or fix the generator/source mapping. |
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.
- 4d ago First seen · 55 lines · 1,120 tokens per session scan A 0a8a81960581
apple-skills AGENTS.md is an instructions file published in the GitHub repository Prisma-Labs-Dev/apple-skills (323 stars, last pushed 24d ago), licensed MIT. It adds 1,120 tokens to every session, about $0.0056 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 2026-08-30.
Other instructions, from other repositories
MobiAI-Core CLAUDE.md
Claude Code instructions for ArisGuimera/MobiAI-Core, covering mobiai — mobile development ai ecosystem, bootstrap and principles.
freetube CLAUDE.md
Instructions for leshkodev/freetube, covering claude.md, 1. what this project is, 2. non-negotiable constraints, 3. tech stack (locked) and 4. project structure.
dev-challenge CLAUDE.md
Claude Code instructions for micheltlutz/dev-challenge, covering claude.md, the one rule to internalise, slash commands, subagents and skills.
android-media-pack CLAUDE.md
Instructions for sunnat629/android-media-pack, covering claude.md, what this repository is, commands, markdown lint (config in .markdownlint-cli2.jsonc) and shell script lint.
android-qa-kit AGENTS.md
Instructions for willbytee-sudo/android-qa-kit, covering agents.md — setting up and driving an android device, 1. how to work with the user, 2. start by finding out what's already there, 3. what you can do in each mode and 4. if there's no device: ask first.
ios-WK-UI-WebView AGENTS.md
Instructions for emilianoeloi/ios-WK-UI-WebView, covering agents.md, build, structure, conventions and skills.