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 instructions/remotehumans/riff/claude-mdgit clone --depth 1 https://github.com/remotehumans/riffWrote 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/instructions/remotehumans/riff/claude-md)<a href="https://agentmods.dev/instructions/remotehumans/riff/claude-md"><img src="https://agentmods.dev/badge/instructions/remotehumans/riff/claude-md.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 | $0.00403 | $0.00403 |
| Opus 5 | $0.00201 | $0.00201 |
| Sonnet 5 | $0.00081 | $0.00081 |
| Haiku 4.5 | $0.00040 | $0.00040 |
Grade A, and why
riff CLAUDE.md 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.
What it actually says
Riff
Monorepo for hands-free AI interaction — smart ring input and voice narrator.
Components
riff-bridge
macOS daemon that bridges a JX-11 smart ring (BLE HID) to keyboard events for hands-free voice interaction.
- Tap: Toggle Left Option key (voice-to-text push-to-talk)
- Swipe right: Enter key (submit messages)
- Swipe left: Backspace/Delete
Uses IOKit HID Manager for device-specific detection (VendorID/ProductID) and CGEvent tap to block default media key behavior.
riff-voice
Voice narrator daemon that speaks AI agent output aloud using MLX-Audio Kokoro TTS.
- FIFO queue: Multiple sessions send text, one voice at a time
- Per-agent voices: 54 Kokoro presets mapped by project directory
- Session announcements: "project-name says:" before each message
- Interrupt support: Stop speech instantly via
riff-ctl interruptor ring Escape button - Speed control: Adjustable playback speed (0.5-3.0x) via
riff-ctl speed
Socket protocol over /tmp/riff.sock. Claude Code Stop hook auto-sends summaries.
Build & Run
riff-bridge
cd riff-bridge
swiftc riff_bridge.swift -o riff-bridge -framework CoreGraphics -framework IOKit
./riff-bridge
Requires macOS Accessibility permission. Signed with Apple Development certificate for stable permissions across recompiles.
LaunchAgent: ~/Library/LaunchAgents/co.remotehumans.riff-bridge.plist
riff-voice
cd riff-voice
make install # uv sync + LaunchAgent + CLI symlinks + hook
riff-say "hello"
riff-ctl status
LaunchAgent: ~/Library/LaunchAgents/co.remotehumans.riff-voice.plist
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 · 47 lines · 403 tokens per session scan A df58dc49c3d9
riff CLAUDE.md is an instructions file published in the GitHub repository remotehumans/riff (24 stars, last pushed 21d ago), licensed MIT. It adds 403 tokens to every session, about $0.0020 per session on Opus 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.
Other instructions, from other repositories
firmware CLAUDE.md
Claude Code instructions for OpenIPC/firmware, covering claude.md, what this is, before you start: is this the right repository?, build and common tasks.
Tutorial_AwesomeModernCPP AGENTS.md
AGENTS.md instructions for Awesome-Embedded-Learning-Studio/Tutorial_AwesomeModernCPP, covering agents.md, 这是什么, 通用 essentials(所有 agent 必读) and 你来做什么?(按场景路由).
brilliant_sdk AGENTS.md
Instructions for brilliantlabsAR/brilliant_sdk, covering brilliant sdk — agent guide, how an app works (the pattern behind everything), minimal reading paths, verify without hardware and testing.
NeoMind CLAUDE.md
Claude Code instructions for camthink-ai/NeoMind, covering neomind — edge ai platform for iot, development commands, ecosystem repositories, extension package contract (.nep) and device type template contract (json).
zmk-config AGENTS.md
AGENTS.md instructions for urob/zmk-config, covering customization guide, ground rules, how the multi-board layout works, adding a new board and where to change what.
ext-apps CLAUDE.md
Claude Code instructions for modelcontextprotocol/ext-apps, a project described as: Official repo for spec & SDK of MCP Apps protocol - standard for UIs embedded AI chatbots, served by MCP servers.