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/tetsuo-ai/voice_clone_lab/agents-mdgit clone --depth 1 https://github.com/tetsuo-ai/voice_clone_labWrote 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/tetsuo-ai/voice_clone_lab/agents-md)<a href="https://agentmods.dev/instructions/tetsuo-ai/voice_clone_lab/agents-md"><img src="https://agentmods.dev/badge/instructions/tetsuo-ai/voice_clone_lab/agents-md.svg" alt="Measured on agentmods" 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 | $0.00895 | $0.00895 |
| Opus 5 | $0.00447 | $0.00447 |
| Sonnet 5 | $0.00179 | $0.00179 |
| Haiku 4.5 | $0.00089 | $0.00089 |
Grade C, and why
voice_clone_lab AGENTS.md scanned grade C 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 4d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
No unconditional `ffmpeg -y`, no unguarded `rm -rf`/`shutil.rmtree`. The one How it starts
The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for agents working in this repo.
What this is
Voice Clone Lab: an installable pipeline (src/voice_clone_lab/, console script
vcl) for fine-tuning Qwen3-TTS-12Hz-1.7B-Base on a user's own voice and
generating speech. CLI (cli.py) + Gradio UI (ui.py) over shared modules.
Layout
src/voice_clone_lab/— the package.config.py(dataclass config + per-voice path derivation),utils.py(IO + overwrite safety),audio.py,transcribe.py,dataset.py,train.py,generate.py,sources.py(yt-dlp URL downloads),system.py,cli.py,ui.py.config/default.yaml— the ONLY config source. Every key is used; if you add a setting, add it here AND to the dataclasses inconfig.py.patches/sft_12hz.patch— local patch to the vendored training script. See "Vendor rule" below.third_party/Qwen3-TTS/— vendored upstream clone (gitignored, recreated byvcl setup).data/,outputs/,models/,attic/— gitignored runtime dirs.data/andoutputs/contain biometric voice data: never commit, never upload.tests/— pytest, CPU-only (synthetic audio, tmp_path, monkeypatching).
Conventions (keep them when editing)
- Overwrite safety: every step that writes files must refuse to overwrite
unless
force=True, viautils.refuse_overwrite/refuse_any_existing. No unconditionalffmpeg -y, no unguardedrm -rf/shutil.rmtree. The one destructive path (train--force) must stay guarded tooutputs/checkpoints/only. - Relative paths in artifacts: files under
data/that reference audio (chunk metadata, transcripts, dataset rows) store project-relative paths viaconfig.rel_to_root; readers resolve withutils.resolve_artifact_path(accepts legacy absolute paths too). - Config idiom: values come from the
Configdataclasses; function parameters override (None= use config). Noconfig.get(...).get(...)chains, no second YAML reader. - Speaker-derived paths: never hardcode a voice name or a data path; use
cfg.paths_for(speaker). - Lazy heavy imports:
torch,qwen_tts,soundfile, ASR backends,webrtcvad,noisereduceimport inside functions sovclstays fast and CPU-only tests pass. - User-facing errors:
raise SystemExit(clear message), not tracebacks. - Ported behavior is faithful to the original scripts — don't change filter chains, thresholds, or scoring formulas without a reason and a README note.
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.
- 4d ago First seen · 69 lines · 895 tokens per session scan C abc71b57da61
voice_clone_lab AGENTS.md is an instructions file published in the GitHub repository tetsuo-ai/voice_clone_lab (150 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 895 tokens to every session, about $0.0045 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
mcp-voice-soundboard CLAUDE.md
Claude Code instructions for mcp-tool-shop-org/mcp-voice-soundboard, covering mcp voice soundboard — plugin context, tools (5), presets (5), voices (48 across 9 languages) and emotion spans (8 emotions).
talky-talky CLAUDE.md
Claude Code instructions for shawnrushefsky/talky-talky, covering talky talky - development guide, quick reference, project overview, architecture and technology stack.
Vocello AGENTS.md
AGENTS.md instructions for PowerBeef/Vocello, covering agents.md — vocello (qwenvoice), product and authority, start and resume work, hard invariants and domain routing.
VoiceStudio CLAUDE.md
Claude Code instructions for debpalash/VoiceStudio, covering project, constraints, technology stack, conventions and architecture.
VoiceStudio AGENTS.md
AGENTS.md instructions for debpalash/VoiceStudio, covering agent rules — voicestudio, cross-platform parity: behaviour, not performance, merge protocol (hard rules), change rules (see claude.md for full text) and agent skills.
langlearn-tts CLAUDE.md
Claude Code instructions for punt-labs/langlearn-tts, covering claude.md, no "pre-existing" excuse, project overview, build & run and install with dev dependencies.