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 skills add THU-SAGE/syll --skill audition-clean-voicegit clone --depth 1 https://github.com/THU-SAGE/syllWrote 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/skills/thu-sage/syll/audition-clean-voice)<a href="https://agentmods.dev/skills/thu-sage/syll/audition-clean-voice"><img src="https://agentmods.dev/badge/skills/thu-sage/syll/audition-clean-voice/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/skills/thu-sage/syll/audition-clean-voice"><img src="https://agentmods.dev/badge/skills/thu-sage/syll/audition-clean-voice.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 | $0.00131 | $0.01306 |
| Opus 5.5 | $0.00052 | $0.00522 |
| Sonnet 5.5 | $0.00026 | $0.00261 |
| Haiku 4.5 | $0.00013 | $0.00131 |
Grade A, and why
audition-clean-voice 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 2mo 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audition Clean Voice
Use the clean_audio_in_audition tool to clean up a voice recording — reducing
hiss, hum, broadband noise, and harsh sibilance. This is not a filter that
runs in this process — it drives the real Adobe Audition application on a
macOS host, opens the clip, applies the cleanup, and exports the result.
When To Reach For This
The user wants a recording to sound cleaner. Recognize the intent from phrases like:
- English: "clean up this audio", "clean up the voice", "remove the hiss", "remove the hum", "get rid of the background noise", "denoise this", "reduce the noise", "de-ess", "too much sibilance", "repair the voice", "fix the recording".
- 中文：「降噪」「去底噪」「去杂音」「去噪音」「帮我清理人声」「清理一下录音」「修复人声」 「去齿音」「去咝声」。
How It Works
- You call
clean_audio_in_auditionwith the path to the source audio file. - The tool launches / focuses Adobe Audition, opens the clip, applies the noise reduction / de-ess chain, and exports the cleaned audio.
- The tool measures the result (noise-floor reduction, whether the voice was preserved vs. only made louder) and returns a verdict.
- The before and after audio render inline automatically — you do not need to attach or describe them yourself.
Confirm Before Control
This tool seizes the mouse and keyboard of the host machine. It MUST NOT take over the screen without the user's explicit permission.
- First call —
confirmed=false. Always make the first call withconfirmed=false. The tool will return a takeover-consent question (it does not touch the mouse/keyboard yet). Surface that question to the user. - Wait for an explicit yes. Only proceed once the user clearly agrees — a "yes", "go ahead", "do it", "确认", "可以" in the conversation counts. Silence, ambiguity, or "maybe" does not count.
- Second call —
confirmed=true. Only then call again withconfirmed=true. This is the call that actually takes over the host.
Never set confirmed=true on the first call, and never assume consent.
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.
- 2mo ago First seen · 104 lines · 131 tokens per session scan A a7d90936e681
audition-clean-voice is a skill published in the GitHub repository THU-SAGE/syll (304 stars, last pushed 5mo ago), licensed MIT. It adds 131 tokens to every session and 1,306 once invoked, about $0.0005 per session on Opus 5.5. 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.
audition-clean-voice compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| audition-clean-voiceTHU-SAGE/syll | Skill | 304 | 5mo ago | MIT | A | 131 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 103 | Claude Code |