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/hig-inputsnpx skills add chama-x/GroundRules --skill hig-inputsgit 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/hig-inputs)<a href="https://agentmods.dev/skills/chama-x/groundrules/hig-inputs"><img src="https://agentmods.dev/badge/skills/chama-x/groundrules/hig-inputs.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 | $0.00181 | $0.01371 |
| Opus 5 | $0.00090 | $0.00685 |
| Sonnet 5 | $0.00036 | $0.00274 |
| Haiku 4.5 | $0.00018 | $0.00137 |
Grade A, and why
hig-inputs 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.
This is a copy
100% identical to hig-inputs — 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apple HIG: Inputs
Check for .claude/apple-design-context.md before asking questions. Use existing context and only ask for information not already covered.
Key Principles
-
Support multiple input methods. Touch, pointer, keyboard, pencil, voice, eyes, hands, controllers. Design for the inputs available on each platform. On iPadOS, support both touch and pointer; on macOS, both pointer and keyboard.
-
Consistent feedback for every input action. Visible, audible, or haptic response.
-
Standard gestures must behave consistently. Tap to activate, swipe to scroll/navigate, pinch to zoom, long press for context menus, drag to move. Don't override system gestures (edge swipes for back, Home, notifications).
-
Use standard recognizers; keep custom gestures discoverable. Apple's built-in recognizers handle edge cases and accessibility. If you add non-standard gestures, provide hints or coaching to teach them.
-
Apple Pencil: precision drawing, markup, and selection. Support pressure, tilt, and hover. Distinguish finger from Pencil when appropriate (finger pans, Pencil draws).
-
Support Scribble in text fields. Users expect to write with Pencil in any text input.
-
Keyboard shortcuts and full navigation. Standard shortcuts (Cmd+C/V/Z) plus custom ones visible in the iPadOS Command key overlay. Logical tab order.
-
Respect the software keyboard. Adjust layout when keyboard appears. Use keyboard-avoidance APIs.
-
Game controllers: MFi controllers with on-screen fallbacks. Map to extended gamepad profile, sensible defaults, remappable. Always offer touch or keyboard alternatives.
-
Pointer and trackpad: native feel. Hover effects, pointer shape adaptation, standard cursor behaviors. Two-finger scroll, pinch to zoom, swipe to navigate.
-
Digital Crown: primary scrolling and value-adjustment input on watchOS. Scrolling lists, adjusting values, navigating views. Haptic feedback at detents.
-
Eyes and spatial (visionOS): look and pinch. Generous hit targets (eye tracking is less precise than touch). Avoid sustained gaze for activation. Direct hand manipulation in immersive experiences.
What ships with it
13 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.
- references/apple-pencil-and-scribble.md 2.8 KB
- references/camera-control.md 1.5 KB
- references/digital-crown.md 1.5 KB
- references/eyes.md 2.4 KB
- references/focus-and-selection.md 2.0 KB
- references/game-controls.md 2.2 KB
- references/gestures.md 2.5 KB
- references/gyro-and-accelerometer.md 1007 B
- references/keyboards.md 1.6 KB
- references/nearby-interactions.md 1.5 KB
- references/pointing-devices.md 2.9 KB
- references/remotes.md 1.6 KB
- references/spatial-interactions.md 1.5 KB
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 · 95 lines · 181 tokens per session scan A 28aac5b39b80
hig-inputs is a skill published in the GitHub repository chama-x/GroundRules (5 stars, last pushed 20d ago), licensed MIT. It adds 181 tokens to every session and 1,371 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to hig-inputs, 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).
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.
compare-harnesses
Diff two scaffolded harnesses (ADR-031). Reports manifest meta drift + host list + per-file fingerprint changes (added/removed/changed). Exits 0 IDENTICAL, 1 DRIFT, 2 missing manifest. Use --bundle for the ADR-031 schema-1 JSON envelope.