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.
git clone --depth 1 https://github.com/HariFatherKR/claude-qwen-ttsWrote 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/commands/harifatherkr/claude-qwen-tts/tts-init)<a href="https://agentmods.dev/commands/harifatherkr/claude-qwen-tts/tts-init"><img src="https://agentmods.dev/badge/commands/harifatherkr/claude-qwen-tts/tts-init/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/commands/harifatherkr/claude-qwen-tts/tts-init"><img src="https://agentmods.dev/badge/commands/harifatherkr/claude-qwen-tts/tts-init.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 | $0.00016 | $0.00720 |
| Opus 5 | $0.00008 | $0.00360 |
| Sonnet 5 | $0.00003 | $0.00144 |
| Haiku 4.5 | $0.00002 | $0.00072 |
Grade A, and why
tts-init 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 12d 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TTS-Init - Interactive Configuration
Set up TTS configuration through interactive questions.
Prerequisites
Check if /tts-setup has been run:
test -d ~/.config/claude-qwen-tts/venv && echo "Setup complete" || echo "Setup needed"
If setup needed, inform user: "Please run /tts-setup first."
Interactive Flow
Question 1: Reference Voice Selection
Ask the user using AskUserQuestion:
Question: "Select your reference voice for TTS:"
Options:
- A) Use default sample (Korean male)
- B) Use default sample (Korean female)
- C) Register my own voice file
If Option A or B selected:
Set config based on selection:
- A:
~/.config/claude-qwen-tts/samples/ko_male.wav - B:
~/.config/claude-qwen-tts/samples/ko_female.wav
Read the corresponding text file for reference text.
If Option C selected:
Ask: "Please provide the path to your voice file (5-10 seconds, WAV recommended):"
Then ask: "What is the exact transcript of the audio? (accuracy improves quality)"
Question 2: Default Output Directory
Ask the user:
Question: "Select default output directory:"
Options:
- A) ./output (current project)
- B) ~/Documents/tts-output (home directory)
- C) Enter custom path
Save Configuration
Write to ~/.config/claude-qwen-tts/config.yaml:
reference:
audio: PATH_TO_AUDIO
text: "TRANSCRIPT_TEXT"
output:
default_dir: OUTPUT_DIRECTORY
sample_rate: 24000
environment:
venv_path: ~/.config/claude-qwen-tts/venv
device: auto
cat > ~/.config/claude-qwen-tts/config.yaml << 'EOF'
reference:
audio: "AUDIO_PATH"
text: "REFERENCE_TEXT"
output:
default_dir: "OUTPUT_DIR"
sample_rate: 24000
environment:
venv_path: ~/.config/claude-qwen-tts/venv
device: auto
EOF
Test Configuration
Run a quick test:
source ~/.config/claude-qwen-tts/venv/bin/activate && \
python ~/.config/claude-qwen-tts/scripts/tts_runner.py voice_clone \
--text "설정 테스트입니다" \
--output ~/.config/claude-qwen-tts/test_output.wav \
--config ~/.config/claude-qwen-tts/config.yaml
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.
- 12d ago First seen · 123 lines · 16 tokens per session scan A d9f35b75de3d
tts-init is a command published in the GitHub repository HariFatherKR/claude-qwen-tts (16 stars, last pushed 7mo ago), licensed MIT. It adds 16 tokens to every session and 720 once invoked, about $0.0001 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.