cadence-code AGENTS.md

cadence-code AGENTS.md is an instructions file for Codex, OpenCode from michael-L-i/cadence-code. It costs 2,720 tokens per session, scanned A, original, MIT.

A project guide for Cadence Code, a local voice companion for coding agents on Apple Silicon Macs. It explains the project structure, important files, commands, and how its speech-to-text and text-to-speech parts work.

In plain words
What is it for?
Use it when developing, debugging, or navigating Cadence Code and its Codex, Claude Code, or Antigravity plugin layout.
Why use it?
It gives an agent the project context needed to work in the repository without guessing where files are or how the local voice system is designed.

Instructions file for CodexOpenCode

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.

agentmods
npx agentmods add instructions/michael-l-i/cadence-code/agents-md
Clone the repo
git clone --depth 1 https://github.com/michael-L-i/cadence-code

Made for: Codex, OpenCode.

Per session 2,720 This file is loaded in full into every session.
When invoked 2,720 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.02720 $0.02720
Opus 5 $0.01360 $0.01360
Sonnet 5 $0.00544 $0.00544
Haiku 4.5 $0.00272 $0.00272

Measured 3d ago against content hash 45382dc6817b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cadence-code AGENTS.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 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.

AGENTS.md · 213 lines

How it starts

The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Guide

Project Overview

cadence-code is a Codex, Claude Code, and Antigravity plugin: a fully local voice companion for Apple Silicon. Its stdio MCP process owns local TTS and STT models directly while a voice conversation is active. There is no HTTP daemon or local summarization model; the host coding agent provides the exact text sent to TTS.

MLX is the speech inference backend, not a second reasoning layer. Speech models run through mlx-audio; some TTS implementations reuse mlx-lm cache and sampling utilities internally, but Cadence Code never loads a local reasoning or summarization model.

There is no passive narration. Users explicitly choose Start Talking with $start-talking or /skills in Codex, /cadence-code:start-talking in Claude Code, or /start-talking in Antigravity:

  • On a new install, the host calls voice_models, shows the fixed first-run orientation, and persists its returned Pocket TTS and Parakeet 110M defaults through voice_configure without pausing for model selection.
  • The host calls voice_start, which preflights audio access and then loads the selected TTS and STT models in the background. The host polls voice_status until ready is true -- so a first-run model download never outlives any host's MCP tool deadline -- then speaks a greeting via voice_speak.
  • The host calls voice_listen to capture the user's reply via the mic, then acts on the transcript with its normal tools -- silently, no play-by-play.
  • After interrupting a host turn with Escape, the user can invoke the explicit interrupt workflow. voice_interrupt silences current audio, opens a fresh capture, and returns added guidance without unloading the models.
  • The host calls voice_speak again with a short spoken-style update, and the loop repeats until the user says something like "stop" or two consecutive voice_listen calls time out.
  • At that point the host calls voice_stop, which drops both providers, clears the MLX cache, and releases the active-session lock. If the host session ends unexpectedly, MCP process exit releases its memory and lock.
  • The explicit $wrap-up or /cadence-code:wrap-up workflow gives the same clean ending on demand, allowing a short goodbye to finish before release.

Read the full file on GitHub · 213 lines

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. 3d ago First seen · 213 lines · 2,720 tokens per session scan A 45382dc6817b

Subscribe to this mod's changes

cadence-code AGENTS.md is an instructions file published in the GitHub repository michael-L-i/cadence-code (2 stars, last pushed 6d ago), licensed MIT. It adds 2,720 tokens to every session, about $0.0136 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 2026-08-31.

Related

Other instructions, from other repositories

Vocello AGENTS.md

Instructions for PowerBeef/Vocello, covering agents.md — vocello (qwenvoice), product and authority, start and resume work, hard invariants and domain routing.

PowerBeef/Vocello · 5,212 tokens

localvoxtral AGENTS.md

Instructions for T0mSIlver/localvoxtral, covering localvoxtral — agent guide, build & test — read this first on a non-mac dev box, proof culture — non-negotiable, test tiers — the short version and ci / shipping.

T0mSIlver/localvoxtral · 2,917 tokens

OpenSuperMLX AGENTS.md

Instructions for axot/OpenSuperMLX, covering agents.md — opensupermlx, agent behavioral guidelines, 1. think before coding, 2. simplicity first and 3. surgical changes.

axot/OpenSuperMLX · 5,957 tokens

claude-mlx-tts CLAUDE.md

Instructions for aperepel/claude-mlx-tts, covering claude.md, project overview, architecture, development commands and install plugin locally for development.

aperepel/claude-mlx-tts · 764 tokens

localvoxtral CLAUDE.md

Instructions for T0mSIlver/localvoxtral, a project described as: Talk to your coding agents by voice. Realtime, fully local macOS dictation that streams words as you speak and grounds LLM polishing in the exact Claude Code session under your cursor — Ghostty, iTerm2, Terminal.app, even a herdr pane. 100% on-device on…

T0mSIlver/localvoxtral · 5 tokens

OpenSuperMLX CLAUDE.md

Instructions for axot/OpenSuperMLX, a project described as: macOS app for real-time audio transcription powered by MLX on Apple Silicon.

axot/OpenSuperMLX · 3 tokens