What is pi-voice AGENTS.md?

Repository instructions for pi-voice, a TypeScript project that adds voice commands, text-to-speech, and automatic spoken responses to Pi.

They provide commands for type checks, linting, unit, event, server, and end-to-end tests, plus rules for model memory, serialized operations, dependencies, and project layout.

They make testing and model handling more predictable, especially when audio, machine-learning models, locks, and hardware-related behaviour are involved.

How S1M0N38/pi-voice configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to S1M0N38/pi-voice. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/S1M0N38/pi-voice/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/S1M0N38/pi-voice

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/s1m0n38/pi-voice/agents-md.svg)](https://agentmods.dev/instructions/s1m0n38/pi-voice/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/s1m0n38/pi-voice/agents-md"><img src="https://agentmods.dev/badge/instructions/s1m0n38/pi-voice/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,708 This file is loaded in full into every session.

When invoked 1,708 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.01708	$0.01708
Opus 5	$0.00854	$0.00854
Sonnet 5	$0.00342	$0.00342
Haiku 4.5	$0.00171	$0.00171

Measured 7d ago against content hash 31f6b91f12df, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

pi-voice 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 7d 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 · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

pi-voice — Agent Context

Quick Reference

What	Command
Type check	`npm run typecheck`
Lint	`npm run lint`
Unit tests	`npm run test:unit` (fast, no model/hardware)
Event tests	`npm run test:events` (mocked pi, plays real audio)
Server tests	`npm test` (unit + integration, ~60s, real kokoro-js q4)
E2E tests	`npm run test:e2e` (needs running server + pilotty)
Start server	`npm run server`
Verify before commit	`npm run typecheck && npm run lint`

Constraints

No build step — pi loads .ts via jiti
2-space indent — enforced by biome
Single model in memory — every model-swap path calls unloadModel() first, which disposes ONNX sessions
Model ops are serialized — load/download/delete chain through withModelLock(); never call the *Impl variants outside the lock
Peer deps use * range — pi packages list @earendil-works/pi-* and typebox as peerDependencies: "*"

Project Layout

extensions/
  index.ts             # Extension: /voice command, tts tool, auto-TTS events
  text.ts              # Pure text helpers (extraction, voice hints, markdown cleanup)
  config.ts            # Config types + load/save (path-injectable)
  audio.ts             # Player detection, WAV playback, serial play queue
  server.ts            # HTTP server: Kokoro ONNX TTS model lifecycle + REST API
  server.test.ts       # Server integration tests (node:test)
  events.test.ts       # Mocked-pi event tests (plays real audio)
  text.test.ts         # Unit tests for text.ts
  config.test.ts       # Unit tests for config.ts
  audio.test.ts        # Unit tests for audio.ts
bin/
  pi-voice.mjs         # CLI launcher (createJiti -> src/cli.ts; works inside node_modules)
src/
  cli.ts               # CLI: pi-voice server/model management
  prepare.js           # npm prepare script (writes default config if missing)
tests/
  helpers.sh           # Shared pilotty test utilities
  run.sh               # E2E test runner (tui, toggle, queue)
  tui.sh               # /voice TUI interaction tests
  toggle.sh            # alt+v toggle tests
  queue.sh             # Playback queue overlap tests
.agents/skills/        # pi-test, pi-init, pi-package skills

Read the full file on GitHub · 142 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.

7d ago First seen · 142 lines · 1,708 tokens per session scan A 31f6b91f12df

Subscribe to this mod's changes

pi-voice AGENTS.md is an instructions file published in the GitHub repository S1M0N38/pi-voice (5 stars, last pushed 11d ago), licensed MIT. It adds 1,708 tokens to every session, about $0.0085 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.

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

pi-voice: Instructions file for Codex