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 rohailaltaf/claude-ableton --skill mastering-chaingit clone --depth 1 https://github.com/rohailaltaf/claude-abletonWrote 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/rohailaltaf/claude-ableton/mastering-chain)<a href="https://agentmods.dev/skills/rohailaltaf/claude-ableton/mastering-chain"><img src="https://agentmods.dev/badge/skills/rohailaltaf/claude-ableton/mastering-chain/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/rohailaltaf/claude-ableton/mastering-chain"><img src="https://agentmods.dev/badge/skills/rohailaltaf/claude-ableton/mastering-chain.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 | $0.00076 | $0.01470 |
| Opus 5 | $0.00038 | $0.00735 |
| Sonnet 5 | $0.00015 | $0.00294 |
| Haiku 4.5 | $0.00008 | $0.00147 |
Grade A, and why
mastering-chain 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 9d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mastering chain (Main track)
Build a conservative mastering chain on the Main track. Goal: glue + perceived loudness without audible pumping or clipping. When in doubt, do less.
1. Pre-flight — always do this first
get_master_devices— see what's already on the Main track.- If a Limiter (or Glue Compressor) is already loaded, adjust it instead of stacking a second one. Never end up with two limiters.
get_master_volume— set to ~0.85 (unity / 0 dB) viaset_master_volumeif it's been pushed higher. Loudness must come from the limiter's Input Gain, not the master fader.- If the mix is playing, spot-check the loudest tracks with
get_track_state:output_meter_levelpinned above ~0.95 means the mix itself is too hot — pull those track volumes down before mastering. Mastering cannot fix a clipping mix bus.
2. Choose the devices — don't reflexively reach for stock
Each chain stage is a role (glue compressor, EQ, limiter), not a fixed device. Pick the best available tool for each role before loading:
- Check what the user owns.
list_pluginsfor third-party mastering plugins (FabFilter Pro-L/Pro-C/Pro-Q, iZotope Ozone, Waves, etc.). - Honor an explicit request. If the user named a plugin ("master with
Ozone", "use Pro-L 2"), use it — find it via
list_pluginsand load it withload_browser_item_on_master(node='plugins', path=...). - Otherwise prefer the user's plugins over stock when one clearly fits the role (same principle as preferring packs over stock instruments — it's what keeps results from sounding like default Ableton). A dedicated mastering limiter like Pro-L beats stock Limiter when present.
- Match the genre when choosing between options:
- EDM / pop / anything needing max loudness → transparent brickwall limiter (Pro-L, or stock Limiter pushed).
- Hip-hop / lo-fi / rock → favor character: glue compression and a touch of saturation over clinical transparency.
- Acoustic / jazz / classical → minimal: gentle glue, little to no limiting, preserve dynamics. Consider skipping the limiter.
- When two options are equally valid and the user gave no preference, briefly say which you're choosing and why (one line) rather than silently picking.
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.
- 9d ago First seen · 111 lines · 76 tokens per session scan A 0e55ad13eb12
mastering-chain is a skill published in the GitHub repository rohailaltaf/claude-ableton (2 stars, last pushed 2mo ago), licensed MIT. It adds 76 tokens to every session and 1,470 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
video-perception
Use when the user mentions a video file (.mp4, .mov, .avi, .mkv, .webm), a YouTube URL, asks to watch/analyze/review a video, or references video content in conversation.
wechat_channels
A search skill for WeChat Channels, WeChat's short-video service, using the TikHub service.
screencast-desktop
Drive the Windows desktop with feedback — a screenshot and an element tree come back after every action, like the Playwright plugin does for the browser — plus record what happens into a finished demo video with zoom to clicks, a smooth cursor, and voiceover. Triggers: "click around in the app", "look at what's on the…
using-ig-dl
Use when the user asks to download something from Instagram, archive an Instagram profile, extract an IG reel/story/post, or mentions Instagram URLs. Prefer ig-dl's MCP tools and prompts over ad-hoc curl/yt-dlp invocations.
media
Use whenever someone wants to confirm an image/video is usable for a social post, or asks to "upload", "resize", or "list" media, through the Ayrshare MCP server. The only media tool is mcpayrsharevalidatemedia, which HEAD-checks that a media URL is reachable (it does not upload, store, or resize anything). Trigger on…
screenshot-game-view
Capture a screenshot of the Unity Editor's Game View by reading its internal render texture directly. Image size matches the current Game View resolution; the tool corrects Y-flip on DirectX / Metal so the output is always upright. Requires an open Game View window.