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/powerbeef/vocello/agents-mdgit clone --depth 1 https://github.com/PowerBeef/VocelloWhat 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 | $0.05212 | $0.05212 |
| Opus 5 | $0.02606 | $0.02606 |
| Sonnet 5 | $0.01042 | $0.01042 |
| Haiku 4.5 | $0.00521 | $0.00521 |
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.
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.
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.
- 2d ago First seen · 248 lines · 5,212 tokens per session scan A 23cbb1e7676c
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.
Other instructions, from other repositories
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.
OpenSuperMLX CLAUDE.md
Instructions for axot/OpenSuperMLX, a project described as: macOS app for real-time audio transcription powered by MLX on Apple Silicon.
speech-swift AGENTS.md
Instructions for soniqo/speech-swift, covering agent instructions, communication style, workflow, running tests and benchmarks — sequential and memory-aware and git conventions.
Logue CLAUDE.md
Instructions for bitwize-ai/Logue, covering logue — development guidelines, project overview, running the build you just made, where documentation goes and dependencies.
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.
cadence-code AGENTS.md
Instructions for michael-L-i/cadence-code, covering agent guide, project overview, plugin layout, important paths and local commands.