riff-setup

riff-setup is a skill for Claude Code, Codex from remotehumans/riff. It costs 86 tokens per session (790 once invoked), scanned A, original, MIT.

A setup guide for Riff, a hands-free system that uses a Bluetooth smart ring to control apps and a voice service to read AI responses aloud.

In plain words
What is it for?
It is for setting up the ring controls, voice narration, or both together for hands-free interaction with AI agents and other apps.
Why use it?
It helps users choose and install the right parts, check requirements, pair the ring, and configure voice input or spoken output.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code.

Good fit It is for setting up the ring controls, voice narration, or both together for hands-free interaction with AI agents and other apps.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/remotehumans/riff/riff-setup
Install

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.

Any agent
npx skills add remotehumans/riff --skill riff-setup
Clone the repo
git clone --depth 1 https://github.com/remotehumans/riff

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for riff-setup

README.md
[![agentmods](https://agentmods.dev/badge/skills/remotehumans/riff/riff-setup/github.svg)](https://agentmods.dev/skills/remotehumans/riff/riff-setup)
Your own site
<a href="https://agentmods.dev/skills/remotehumans/riff/riff-setup"><img src="https://agentmods.dev/badge/skills/remotehumans/riff/riff-setup/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.

agentmods 80×15 button for riff-setup

Your own site · 80×15
<a href="https://agentmods.dev/skills/remotehumans/riff/riff-setup"><img src="https://agentmods.dev/badge/skills/remotehumans/riff/riff-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 790 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00086 $0.00790
Opus 5.5 $0.00034 $0.00316
Sonnet 5.5 $0.00017 $0.00158
Haiku 4.5 $0.00009 $0.00079

Measured 2mo ago against content hash 88ff252ffb24, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

riff-setup 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.

skills/riff-setup/SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Riff Setup

Set up Riff for hands-free interaction with AI agents and apps. Riff has two independent components that can be installed separately or together:

  • Riff Bridge - Maps a JX-11 Bluetooth smart ring to keyboard events (voice recording toggle, send, delete, scroll, interrupt)
  • Riff Voice - Speaks AI agent output aloud using on-device TTS (Kokoro via MLX on Apple Silicon)

Setup Workflow

1. Determine which components to install

Ask the user which components they want:

  • Riff Bridge only - Control AI agents or any app by voice using the smart ring. Read output on screen.
  • Riff Voice only - Type normally at the desk. Hear AI agent output spoken aloud.
  • Both - Full hands-free loop: speak via ring, hear responses via Riff Voice.

If unclear, recommend starting with Riff Bridge - it's the core hands-free experience.

2. Check prerequisites

Read references/setup-guide.md for the full prerequisite checklist per component. Verify each prerequisite before proceeding. Key checks:

Riff Bridge: Verify swiftc --version works, confirm JX-11 ring is paired in Bluetooth settings, confirm user has a voice-to-text app installed.

Riff Voice: Verify uname -m returns arm64 (Apple Silicon required), verify Python 3.10+, verify uv is installed.

3. Install the selected components

Follow the step-by-step installation in references/setup-guide.md. Run the commands and verify each step before proceeding to the next.

For Riff Bridge:

cd riff-bridge
make all && make install

Then guide the user through granting Input Monitoring and Accessibility permissions.

For Riff Voice:

cd riff-voice
make install

Then verify with riff-say "Riff Voice is working".

4. Configure key mappings (Riff Bridge)

After installation, ask the user:

  • Which voice-to-text app they use
  • What keyboard shortcut their app uses for push-to-talk

If their app's shortcut differs from Option key (the default), modify riff_bridge.swift to match. See references/setup-guide.md for the constants to change and common macOS virtual keycodes.

Read the full file on GitHub · 81 lines

Files

What ships with it

1 file 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.

Changes

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.

  1. 2mo ago First seen · 81 lines · 86 tokens per session scan A 88ff252ffb24

Subscribe to this mod's changes

riff-setup is a skill published in the GitHub repository remotehumans/riff (26 stars, last pushed 2mo ago), licensed MIT. It adds 86 tokens to every session and 790 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.

Related

riff-setup compared with skills from other repositories

riff-setup next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
riff-setupremotehumans/riffSkill262mo agoMITA86Claude Code, Codex
gke-compute-classesgoogle/skillsSkill22kyesterdayApache-2.0A83Claude Code, Codex
jetson-diagnosticNVIDIA/skillsSkill3.9kyesterdayApache-2.0A30Claude Code, Codex
holoscan-install-wheelNVIDIA/skillsSkill3.9kyesterdayApache-2.0A34Claude Code, Codex
offensive-z-waveSnailSploit/Claude-RedSkill10k25d agoMITA113Claude Code, Codex
doca-socket-relayNVIDIA/skillsSkill3.9kyesterdayApache-2.0A236Claude Code, Codex
hsb-flashNVIDIA/skillsSkill3.9kyesterdayApache-2.0B94Claude Code