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 rjdunlap/suno --skill suno-songwritinggit clone --depth 1 https://github.com/rjdunlap/sunoWrote 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/rjdunlap/suno/suno-songwriting)<a href="https://agentmods.dev/skills/rjdunlap/suno/suno-songwriting"><img src="https://agentmods.dev/badge/skills/rjdunlap/suno/suno-songwriting/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/rjdunlap/suno/suno-songwriting"><img src="https://agentmods.dev/badge/skills/rjdunlap/suno/suno-songwriting.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 | $0.00041 | $0.05033 |
| Opus 5 | $0.00020 | $0.02516 |
| Sonnet 5 | $0.00008 | $0.01007 |
| Haiku 4.5 | $0.00004 | $0.00503 |
Grade A, and why
suno-songwriting 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 10d 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 — 345 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Suno Songwriting
Help Robert write songs that are designed to be performed by Suno, not just read. The job is to encode structure, energy, and sonic identity into the prompt so the model has clear instructions for how each section should sound.
Style prompts: production DNA, not artist names
Never name artists in style prompts or in suggestions/offers about what a song could sound like. This applies both to the metatags that go into Suno and to how you describe options to Robert in chat.
Instead of "in the style of [Artist]," describe the production DNA:
- Instruments: e.g., "Rhodes electric piano, upright bass, brushed drums, muted trumpet"
- Vocal style: e.g., "breathy female vocal, intimate close-mic, slight rasp on belted notes"
- Mix character: e.g., "tape saturation, wide reverb, sidechained pads, dry vocal up front"
- Era / production hallmarks: e.g., "late-80s gated reverb drums, glossy DX7 synth bells, 16th-note hi-hat programming"
This produces better Suno output and avoids pinning the song to a specific artist's catalog.
The mindset: songs are performance instructions
Most people write Suno prompts like they're writing lyrics on a page. The way to get great output is to think of every section as a job with a sound, an emotion, and an energy level — and then encode that with metatags.
Three principles drive everything:
- Contrast is what makes a song feel alive. Verse → chorus, low → high, sparse → dense. If everything sounds the same, the song goes flat.
- Repetition + variation, balanced. Repeat enough to stick; vary enough to stay interesting. Verse 2 should follow Verse 1's shape but never be identical.
- The chorus must pay off what the verse builds. If the chorus doesn't feel like release, the song feels unsatisfying — no matter how good the lyrics are.
Mode selection
Before starting, check what kind of track Robert wants. Mode selection overrides all defaults — structure, tempo, vocal use, density, and excluded styles all follow the mode.
What ships with it
17 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/album-construction.md 5.7 KB
- references/driving-mode.md 6.6 KB
- references/focus-work-mode.md 6.9 KB
- references/genre-fusion.md 5.6 KB
- references/gotchas.md 6.7 KB
- references/kids-family-mode.md 9.4 KB
- references/lyric-craft.md 6.2 KB
- references/metatag-library.md 4.3 KB
- references/quality-checklist.md 3.7 KB
- references/song-breakdown-example.md 5.1 KB
- references/sound-healing-mode.md 13 KB
- references/specialty-modes.md 5.0 KB
- references/structure-templates.md 3.8 KB
- references/style-dna.md 5.4 KB
- references/suno-controls.md 5.1 KB
- references/tempo-key.md 6.1 KB
- references/workout-endurance-mode.md 8.7 KB
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.
- 10d ago First seen · 345 lines · 41 tokens per session scan A 8c4c7b40e341
suno-songwriting is a skill published in the GitHub repository rjdunlap/suno (3 stars, last pushed 4mo ago), licensed MIT. It adds 41 tokens to every session and 5,033 once invoked, about $0.0002 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.