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 skills/chama-x/groundrules/watchosnpx skills add chama-x/GroundRules --skill watchosgit clone --depth 1 https://github.com/chama-x/GroundRulesWrote 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/chama-x/groundrules/watchos)<a href="https://agentmods.dev/skills/chama-x/groundrules/watchos"><img src="https://agentmods.dev/badge/skills/chama-x/groundrules/watchos.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 | $0.00047 | $0.03959 |
| Opus 5 | $0.00023 | $0.01980 |
| Sonnet 5 | $0.00009 | $0.00792 |
| Haiku 4.5 | $0.00005 | $0.00396 |
Grade A, and why
watchos-design-guidelines 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.
This is a copy
100% identical to watchos-design-guidelines — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 368 lines — stays where its author put it; the contents beside it link to each section on GitHub.
watchOS Design Guidelines
Apple Watch is a personal, glanceable device worn on the wrist. Interactions are measured in seconds, not minutes. Every design decision must prioritize speed of comprehension and brevity of interaction.
1. Glanceable Design (CRITICAL)
The defining constraint of watchOS. If a user cannot extract the key information within 2 seconds of raising their wrist, the design has failed.
Rules
- W-GL-01: Primary information must be visible without scrolling. The first screen is the only guaranteed screen.
- W-GL-02: Target interaction sessions of 5 seconds or less. Design for raise-glance-lower.
- W-GL-03: Use large, high-contrast text. Minimum effective body text is 16pt (system font). Titles should be 18pt or larger.
- W-GL-04: Limit text to essential content. Truncate or abbreviate aggressively. Use SF Symbols instead of text labels where meaning is unambiguous.
- W-GL-05: Respect wrist-down time. When the wrist lowers, the app enters an inactive state. Do not assume continuous user attention.
- W-GL-06: Prioritize a single piece of information per screen. If showing multiple data points, establish clear visual hierarchy with size, weight, and color.
Screen Dimensions Reference
| Device | Screen Width | Screen Height | Corner Radius |
|---|---|---|---|
| 41mm (Series 9) | 176px | 215px | 36px |
| 45mm (Series 9) | 198px | 242px | 39px |
| 42mm (Series 10) | 180px | 220px | 37px |
| 46mm (Series 10) | 205px | 251px | 40px |
| 49mm (Ultra 2) | 205px | 251px | 40px |
Anti-Patterns
- Walls of text requiring scroll to understand context
- Small, dense data tables
- Requiring multiple taps before showing useful information
- Replicating an iPhone screen layout on Watch
2. Digital Crown (HIGH)
The Digital Crown is the primary physical input for scrolling and precise value selection. It provides haptic feedback and should feel purposeful.
Rules
- W-DC-01: Use the Digital Crown as the primary scroll mechanism for vertical content. Do not rely solely on swipe gestures for scrolling.
- W-DC-02: For value pickers (time, quantity, sliders), bind the Crown to precise adjustments with haptic detents at each discrete value.
- W-DC-03: Do not override or conflict with system Crown behaviors. The system uses the Crown for volume control during media playback, scrolling in system UI, and Time Travel in complications.
- W-DC-04: Provide visual feedback synchronized with Crown rotation. The UI must respond frame-by-frame to Crown input with no perceptible lag.
- W-DC-05: Update on each Crown increment. Values, selection, and highlight states should move with each detent. Do not debounce Crown input until the gesture ends.
What ships with it
3 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.
- 3d ago First seen · 368 lines · 47 tokens per session scan A 4075957fb71f
watchos-design-guidelines is a skill published in the GitHub repository chama-x/GroundRules (5 stars, last pushed 20d ago), licensed MIT. It adds 47 tokens to every session and 3,959 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to watchos-design-guidelines, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
wifi-skill
Control Android WiFi - enable, disable, get status, scan for networks, and get current connection info.
app-launcher-skill
Launch Android applications by package name. Open any installed app programmatically.
app-list-skill
Get list of installed Android applications with package names, versions, and metadata.
audio-skill
Control Android audio - get/set volume, mute/unmute for media, ringtone, notification, and call volumes.
bluetooth-skill
Control Android Bluetooth - enable, disable, get status, and list paired devices.
camera-skill
Control Android camera - get camera info, take photos, and access camera capabilities.