Vocello AGENTS.md

An AGENTS.md project instruction file for Vocello, a local text-to-speech application for Apple devices. It explains the product, its supported platforms, the repository’s source-of-truth files, and the rules agents must follow while developing it.

In plain words
What is it for?
Use it to understand the macOS and iOS apps, the command-line tool, the React website, model downloads, development plans, architecture, and domain rules. It also points to the files that define public product facts and benchmark information.
Why use it?
It gives coding agents the project facts and boundaries they need before making changes. This helps them use the documented architecture, verification scripts, and product claims instead of relying on assumptions.

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/powerbeef/vocello/agents-md
Clone the repo
git clone --depth 1 https://github.com/PowerBeef/Vocello

Made for: Codex, OpenCode.

Per session 5,212 This file is loaded in full into every session.
When invoked 5,212 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 $0.05212 $0.05212
Opus 5 $0.02606 $0.02606
Sonnet 5 $0.01042 $0.01042
Haiku 4.5 $0.00521 $0.00521

Measured 2d ago against content hash 23cbb1e7676c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Vocello 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 2d 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 · 248 lines

How it starts

The opening of the file, as written. The whole thing — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Vocello (QwenVoice)

Durable repository guidance for Codex and other coding agents. Code and machine-readable contracts win over prose. Repository scripts are the gates; optional skills, plugins, MCP servers, devices, and models never are.

Plans: docs/ROADMAP.md · Current narrative: docs/development-progress.md · Architecture: docs/ARCHITECTURE.md · Project map: docs/project-map.html · Domain rules: .agents/rules/

Product and authority

Vocello is a local-first text-to-speech application for Apple Silicon using Qwen3-TTS and MLX with Swift 6. The checkout and Xcode project retain the historical QwenVoice name. The repository ships a macOS app with an XPC engine, an iOS app with an in-process engine, the vocello CLI, deterministic automation, benchmarks, and a React/Vite website. Supported targets are macOS and iOS 26+. No model weights are bundled and no cloud inference is used; approved artifacts download from Hugging Face through the complete production model catalog.

Derive public facts from project.yml, config/public-product-facts.json, and the benchmark catalog. Check them before quoting version, hardware, preset, or speaker counts. Release only on an explicit maintainer request.

Source-of-truth order:

Sources/project.yml → machine-readable config/ contracts → scripts/.github/workflows/AGENTS.md and .agents/rules/ → other prose.

The model/speaker schema is Sources/Resources/qwenvoice_contract.json. The complete fail-closed delivery source for all six Speed/Quality artifacts is Sources/Resources/qwenvoice_production_model_catalog.json; receipts and schema live in config/model-artifact-receipts.json and config/model-catalog-schema-v2.json. If source or a machine-readable contract invalidates documentation, update the documentation in the same change.

Read the full file on GitHub · 248 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. 2d ago First seen · 248 lines · 5,212 tokens per session scan A 23cbb1e7676c

Subscribe to this mod's changes

Vocello AGENTS.md is an instructions file published in the GitHub repository PowerBeef/Vocello (357 stars, last pushed 3d ago), licensed MIT. It adds 5,212 tokens to every session, about $0.0261 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.