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/melody-craftnpx skills add guvense/hellyee --skill melody-craftgit 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/melody-craft)<a href="https://agentmods.dev/skills/guvense/hellyee/melody-craft"><img src="https://agentmods.dev/badge/skills/guvense/hellyee/melody-craft.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 | $0.00143 | $0.02319 |
| Opus 5 | $0.00072 | $0.01159 |
| Sonnet 5 | $0.00029 | $0.00464 |
| Haiku 4.5 | $0.00014 | $0.00232 |
Grade A, and why
melody-craft 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 5d 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Melody Craft
Turns "give me a melody" into a phrase with motif logic, tension notes, breath,
and dynamics — then refines it through conversation without throwing it away.
emotion-to-notes decides the palette (key, mode, tempo, contour direction);
this skill decides the sentences written with that palette.
Why generated melodies sound simple — the seven traps
A melody sounds "basit" when it has these properties. Never deliver a melody that fails more than one of these checks:
- Grid marching — every note starts on a beat or 8th. Real phrases start off the beat, anticipate the bar, or arrive late.
- Uniform durations — all notes 0.5 or 1.0 beats. A phrase needs at least 3 distinct duration values (e.g. 0.25 ornaments, 1.5 anchors, 3.0 arrivals).
- Scale-walking — stepwise up, stepwise down, repeat. Steps are filler; leaps carry emotion. A leap of a 6th says more than six steps.
- No rests — sound wall-to-wall. Rests are where the listener breathes; a phrase without silence is a paragraph without punctuation.
- Flat velocity — everything 90–100. Velocity range across a phrase should span at least 25–30, shaped toward the climax, not random.
- Chord-tones only — every note "safe". Emotion lives in the notes that don't belong and then resolve (see tension notes below).
- Copy-paste repetition — bar 1 pasted four times. Repetition is good; identical repetition is dead. Repeat the shape, change the detail.
Building a phrase — the craft
Motif first, melody second
Do not write 16 bars of notes. Write a motif: 3–6 notes with one distinctive feature (a leap, a rhythm, a tension-resolution). The melody is that motif developed:
- Sequence — repeat the motif starting a step higher/lower.
- Inversion — mirror its direction (rise becomes fall).
- Augmentation / diminution — same pitches, durations doubled or halved.
- Fragmentation — take only the motif's tail and repeat it, tightening.
- Octave displacement — same note, different octave; instant drama.
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.
- 5d ago First seen · 155 lines · 143 tokens per session scan A 9145d3098c88
melody-craft is a skill published in the GitHub repository guvense/hellyee (6 stars, last pushed 14d ago), licensed MIT. It adds 143 tokens to every session and 2,319 once invoked, about $0.0007 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
mastering-chain
Master the current Ableton Live set — build a Glue Compressor → (EQ Eight) → Limiter chain on the Main track with conservative, streaming-safe settings. Use when the user asks to master the track, finish/polish the mix, "make it louder", add glue/punch to the whole mix, or prepare the song for export or streaming.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
specflow-use
To connect Rosetta with Grid Dynamics SpecFlow MCP; only when SpecFlow is mentioned and the MCP is installed.
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — errors, failed tool calls, latency, regressions, and low online-eval scores — plus Diagnostics issues. Reads live/production traces via the SDK (searchtraces and agentinsights) and works with no MCP; uses the MCP issue entity when connected.…
planning-and-task-breakdown
Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible.
qa-knowledge
To run QA engineering — requirements/gap analysis, scenario & spec design, test implementation, failure triage — over the QA knowledge base.