Borrowing it
Nothing to install: this file belongs to abm-dungtq/tqd-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.
curl -O https://raw.githubusercontent.com/abm-dungtq/tqd-voice/main/AGENTS.mdgit clone --depth 1 https://github.com/abm-dungtq/tqd-voiceWrote 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/abm-dungtq/tqd-voice/agents-md)<a href="https://agentmods.dev/instructions/abm-dungtq/tqd-voice/agents-md"><img src="https://agentmods.dev/badge/instructions/abm-dungtq/tqd-voice/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/abm-dungtq/tqd-voice/agents-md"><img src="https://agentmods.dev/badge/instructions/abm-dungtq/tqd-voice/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.01985 | $0.01985 |
| Opus 5 | $0.00992 | $0.00992 |
| Sonnet 5 | $0.00397 | $0.00397 |
| Haiku 4.5 | $0.00198 | $0.00198 |
Grade A, and why
tqd-voice AGENTS.md scanned grade A with 1 finding 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 8d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s http://127.0.0.1:8765/v1/voices?limit=100 -H "X-OmniVoice-Client: webapp" How it starts
The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Set up & run OmniVoice-VI
This file is the setup contract for an AI coding agent (e.g. Google Antigravity). Follow it top to bottom. Every step is non-interactive and idempotent — safe to re-run. The goal: a human can open the Studio web UI and generate Vietnamese speech, and the agent can call TTS through MCP.
What this product is
OmniVoice-VI is a local Vietnamese text-to-speech service:
- A REST API + built-in web UI ("Studio") at
http://127.0.0.1:8765/ui. - An MCP server so an agent can synthesize speech as a tool.
- Runs fully local & loopback-only. No account, no cloud, no secrets to boot.
Prerequisites (check, install only if missing)
- git
- Python 3.10–3.12 on PATH (
python --version/python3 --version). - GPU (optional): an NVIDIA GPU + driver gives real-time speed. Without one, setup falls back to CPU (works, but slow — fine for short demos). Apple Silicon uses the Metal (MPS) backend automatically.
- ~10 GB free disk (the model downloads on first use).
Step 1 — Get the code
git clone <REPO_URL> omnivoice-vi
cd omnivoice-vi
Step 2 — Install (auto-detects the GPU)
The setup script probes the GPU with nvidia-smi, installs the matching PyTorch
wheel (Pascal→cu118, modern NVIDIA→cu121, otherwise CPU), then the service.
Windows (PowerShell):
powershell -ExecutionPolicy Bypass -File scripts\setup-windows.ps1
Linux / macOS:
bash scripts/setup-linux.sh
Expected tail: a line like torch 2.5.1+cu121 | cuda True | NVIDIA GeForce RTX ...
(or cuda False | cpu/mps on a CPU/Mac machine) and Ready.
Step 3 — Run & open the UI
Starts the API, waits until /health is ok, then opens the browser.
Windows:
powershell -ExecutionPolicy Bypass -File scripts\run-windows.ps1
Linux / macOS:
bash scripts/run-linux.sh
Then a human opens http://127.0.0.1:8765/ui, types Vietnamese text, and clicks generate. The first generation downloads the model (~several GB) and can take a few minutes; later runs are fast.
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.
- 8d ago First seen · 175 lines · 1,985 tokens per session scan A f1d3d32013a4
tqd-voice AGENTS.md is an instructions file published in the GitHub repository abm-dungtq/tqd-voice (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,985 tokens to every session, about $0.0099 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.