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 skills/guvense/hellyee/mastering-targetsnpx skills add guvense/hellyee --skill mastering-targetsgit clone --depth 1 https://github.com/guvense/hellyeeWrote 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/guvense/hellyee/mastering-targets)<a href="https://agentmods.dev/skills/guvense/hellyee/mastering-targets"><img src="https://agentmods.dev/badge/skills/guvense/hellyee/mastering-targets.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 | $0.00123 | $0.01243 |
| Opus 5 | $0.00062 | $0.00622 |
| Sonnet 5 | $0.00025 | $0.00249 |
| Haiku 4.5 | $0.00012 | $0.00124 |
Grade A, and why
mastering-targets 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 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.
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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mastering Targets
The honest measurement contract
Streaming platforms measure LUFS (integrated loudness) and true peak. hellyee cannot read either — Live's API exposes only the master meter (0–1 scale, 0.85 ≈ 0 dB, ~10 Hz, sustained level not true peak). So:
- Work in meter targets (below), calibrated from real sessions. They are approximations, and say so when reporting.
- If the user has a loudness meter plugin (Youlean, ADPTR) on their master, its readout is invisible to the API — ask the user to read the LUFS number aloud and adjust from that. That combination (their eyes + your control) is the accurate path.
- True-peak overshoot between meter samples is invisible: keep the limiter ceiling conservative (values below) rather than trusting the meter.
Chain and gain staging
Order on the master: EQ Eight → Glue Compressor → Limiter (limiter always last). If the user's set already has a master chain, work with it — never stack a second limiter.
- Trim all track faders proportionally until the loudest section's master peak reads ~0.75 pre-limiter (preserves the mix balance).
- EQ: high-pass ≤25 Hz; fix real problems only (a −1 dB mud cut near 500 Hz, a gentle +1–2 dB high shelf for air). Mastering EQ moves are small.
- Glue: ratio 2:1, slow attack (transients pass), threshold for ~1–3 dB of glue, auto release.
- Limiter: raise Gain stepwise, measuring the loudest 8 bars each step, until the target below is reached.
Targets by destination
| Destination | Industry target | hellyee meter target (drop, ~8 bars) | Limiter ceiling |
|---|---|---|---|
| Spotify | −14 LUFS-I, −1 dBTP | peak ≈ 0.83–0.85, mean ≈ 0.80–0.83 | −1.0 dB |
| Apple Music | −16 LUFS-I, −1 dBTP | peak ≈ 0.81–0.83, mean ≈ 0.78–0.81 | −1.0 dB |
| YouTube | −14 LUFS-I | as Spotify | −1.0 dB |
| SoundCloud / no normalization | loudness wins (−8…−11) | peak ≈ 0.87–0.89 | −0.3 dB |
| Club / DJ WAV | −6…−9 LUFS-I | peak ≈ 0.88–0.91, mean ≈ 0.86+ | −0.3 dB |
| Ambient / dynamic material | −16…−18 | peak ≈ 0.75–0.78 | −1.0 dB |
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 · 87 lines · 123 tokens per session scan A 3c1b5ac431a0
mastering-targets is a skill published in the GitHub repository guvense/hellyee (6 stars, last pushed 13d ago), licensed MIT. It adds 123 tokens to every session and 1,243 once invoked, about $0.0006 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
amazon aurora dsql
Deprecated compatibility redirect for Aurora DSQL guidance. Use when a request concerns DSQL, Aurora DSQL, distributed SQL, DSQL schemas, migrations, queries, authentication, performance, or application development.
surf
Use when the user wants crypto data — token prices, on-chain SQL, prediction-market positions, CEX order books, wallet labels/net-worth, social mindshare, news, or unified search. 83 endpoints across exchange, on-chain, wallet, social, prediction, news and search — one API, flat $0.0085/call in USDC via x402. Settles…
dv-overview
Foundational cross-cutting context for Dataverse / Power Platform work — scope and the skill map, the tool-capability reference, the safety rules, and the safe change lifecycle. Use when the user mentions Dataverse, Dynamics 365, Power Platform, CRM, or ERP; load this first for orientation. Specialist skills…
dv-query
Bulk reads, multi-page iteration, and analytics over Dataverse data. Use when the user wants to read, list, filter, aggregate, group, join, or analyze records — including pandas DataFrame workflows and notebook exploration.
odoo-data-quality-gate
Audit an Odoo database's data quality with evidence before trusting AI answers, importing, or migrating — duplicates, missing required values, orphaned references, format anomalies — and drive remediation through odoo-mcp's gated write workflow. Use when the user asks to "check data quality", "clean up data", "prepare…
add-provider
Add a new storage or service provider to the core package. Use when implementing a new backend for StorageService (e.g., a new database) or a new service provider (e.g., a new LLM backend).