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 Neeeophytee/agent-stylebooks --skill apple-interface-writinggit clone --depth 1 https://github.com/Neeeophytee/agent-stylebooksWrote 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/neeeophytee/agent-stylebooks/apple-interface-writing)<a href="https://agentmods.dev/skills/neeeophytee/agent-stylebooks/apple-interface-writing"><img src="https://agentmods.dev/badge/skills/neeeophytee/agent-stylebooks/apple-interface-writing/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/neeeophytee/agent-stylebooks/apple-interface-writing"><img src="https://agentmods.dev/badge/skills/neeeophytee/agent-stylebooks/apple-interface-writing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00066 | $0.00709 |
| Opus 5.5 | $0.00026 | $0.00284 |
| Sonnet 5.5 | $0.00013 | $0.00142 |
| Haiku 4.5 | $0.00007 | $0.00071 |
Grade A, and why
apple-interface-writing 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apple interface writing
Use language as part of the interaction. Make each screen's purpose, choice, and result understandable with minimal text.
Protect interaction truth
- Preserve the actual action, consequence, permission, data state, and recovery path.
- Do not make a destructive action sound reversible.
- Do not claim data is saved, private, secure, or recoverable without evidence.
- Respect supplied character, localization, platform, and accessibility constraints.
Define voice, then adapt tone
Choose a stable app voice from its audience and purpose. Adapt the tone to the moment:
- Routine action: neutral and direct.
- Success: specific and proportionate.
- Delay or interruption: calm and informative.
- Error or loss risk: serious, plain, and recovery-focused.
- Permission request: transparent about purpose and user benefit.
Do not copy a recognizable corporate personality. Apply the interaction principles to the product's own voice.
Write each screen
- State the screen's single purpose and the decision or action it supports.
- Put the most important information before explanation.
- Use a verb for an action label and make the label predict the result.
- Keep terminology and navigation labels consistent across the flow.
- Use supporting text only for a consequence, requirement, unfamiliar concept, or choice that the label cannot carry.
- Make completion, cancellation, and the next step explicit.
Write errors and alerts
- Name the problem in terms the person can observe.
- Give the most useful recovery action and preserve state information when known.
- Use specific button labels for consequential choices. Avoid generic confirmation when the action itself can be named.
- Put irreversible consequences beside the action that triggers them.
- Remove interjections, jokes, and apologies that do not help recovery.
- Do not use
wewhen it is unclear whether it means the app, company, device, or team.
Write for the device and everyone
What ships with it
2 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.
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 · 76 lines · 66 tokens per session scan A 90921d01e97d
apple-interface-writing is a skill published in the GitHub repository Neeeophytee/agent-stylebooks (78 stars, last pushed 2mo ago), licensed MIT. It adds 66 tokens to every session and 709 once invoked, about $0.0003 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.
apple-interface-writing compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| apple-interface-writingNeeeophytee/agent-stylebooks | Skill | 78 | 2mo ago | MIT | A | 66 | Claude Code, Codex |
| openai-frontend-designfcakyon/claude-codex-settings | Skill | 1.2k | yesterday | Apache-2.0 | A | 71 | Claude Code, Codex |
| email-designfcakyon/claude-codex-settings | Skill | 1.2k | yesterday | Apache-2.0 | A | 57 | Claude Code |
| ultralytics-brandingfcakyon/claude-codex-settings | Skill | 1.2k | yesterday | Apache-2.0 | A | 90 | Claude Code |
| motion-graphicsChatCut-Inc/agent-plugin | Skill | 1.0k | yesterday | Apache-2.0 | A | 34 | Claude Code |
| llm-demo-websitecafe3310/public-agent-skills | Skill | 256 | yesterday | Apache-2.0 | A | 37 | Claude Code, Codex |
| polyhaven-material-swapcafe3310/public-agent-skills | Skill | 256 | yesterday | Apache-2.0 | A | 55 | Claude Code, Codex |