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/tvosnpx skills add chama-x/GroundRules --skill tvosgit 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/tvos)<a href="https://agentmods.dev/skills/chama-x/groundrules/tvos"><img src="https://agentmods.dev/badge/skills/chama-x/groundrules/tvos.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 | $0.00055 | $0.04311 |
| Opus 5 | $0.00028 | $0.02155 |
| Sonnet 5 | $0.00011 | $0.00862 |
| Haiku 4.5 | $0.00006 | $0.00431 |
Grade A, and why
tvos-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 tvos-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 — 380 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tvOS Design Guidelines
Apple TV is a living room device driven entirely by focus-based navigation and the Siri Remote. There is no pointer, no touch screen, and no mouse. Every design decision must account for the 10-foot viewing distance, the simplicity of the remote, and the lean-back nature of TV consumption.
1. Focus-Based Navigation (CRITICAL)
The focus system is the foundation of all tvOS interaction. There is no cursor -- users move focus between elements using the Siri Remote touch surface.
Rules
FOCUS-01: Every interactive element must have a clearly visible focus state. The focused item must be unmistakably distinguished from unfocused items. Use scaling (typically 1.05x-1.1x), elevation via shadow, brightness changes, or border highlights. Never rely on color alone.
FOCUS-02: Focus movement must be predictable and follow a logical spatial layout. When a user swipes right, focus must move to the element visually to the right. Avoid layouts where focus jumps unexpectedly across the screen. Grid and linear layouts are safest.
FOCUS-03: Use focus guides (UIFocusGuide) to bridge gaps in layouts. When visual gaps exist between focusable elements, add invisible focus guides so the user does not get stuck. Every swipe should move focus somewhere meaningful.
FOCUS-04: Apply the parallax effect to focused items. Focused cards, posters, and icons should exhibit a subtle parallax tilt responding to touch surface movement. Use layered images (LSR format) with foreground, midground, and background layers. This communicates depth and confirms focus.
Correct:
// SwiftUI — custom focus engine with explicit focus state
struct ContentView: View {
@FocusState private var focusedItem: String?
var body: some View {
HStack(spacing: 40) {
ForEach(items) { item in
CardView(item: item)
.focusable()
.focused($focusedItem, equals: item.id)
.scaleEffect(focusedItem == item.id ? 1.1 : 1.0)
.shadow(radius: focusedItem == item.id ? 20 : 0)
.animation(.easeInOut(duration: 0.15), value: focusedItem)
}
}
}
}
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 · 380 lines · 55 tokens per session scan A 249088f96e1c
tvos-design-guidelines is a skill published in the GitHub repository chama-x/GroundRules (5 stars, last pushed 20d ago), licensed MIT. It adds 55 tokens to every session and 4,311 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to tvos-design-guidelines, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
hive.chart-creation-foundations
Required reading whenever any chart tool is available. Teaches the one-tool embedding contract (call chartrender → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no…
browser-edge-cases
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.
openai-whisper-api
Transcribe audio via OpenAI Audio Transcriptions API (Whisper).
chat-complex-documents
Chat with and search your complex documents — ask questions, extract tables and fields, and get answers grounded in the source. Connects the hosted Unstructured Transform MCP server to parse, structure, and enrich PDFs, Word/Excel/PowerPoint, images, scanned files, emails, and 60+ other formats into clean, AI-ready…
perf-code-paths
Use when mapping code paths, entrypoints, and likely hot files before profiling.
github-skill
Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.