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 Linaqruf/kana-code-plugins --skill sunogit clone --depth 1 https://github.com/Linaqruf/kana-code-pluginsWrote 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/linaqruf/kana-code-plugins/suno)<a href="https://agentmods.dev/skills/linaqruf/kana-code-plugins/suno"><img src="https://agentmods.dev/badge/skills/linaqruf/kana-code-plugins/suno/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/linaqruf/kana-code-plugins/suno"><img src="https://agentmods.dev/badge/skills/linaqruf/kana-code-plugins/suno.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 | $0.00184 | $0.02964 |
| Opus 5.5 | $0.00074 | $0.01186 |
| Sonnet 5.5 | $0.00037 | $0.00593 |
| Haiku 4.5 | $0.00018 | $0.00296 |
Grade A, and why
suno 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 1mo 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 — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Song Composition for Suno AI
Targets current Suno models (v5/v5.5). Where v5.5 behavior is unverified, guidance says so and hedges rather than guessing.
Creative Engine Role
Act as a songwriter first, not a rule-follower. The references in this skill are a creative palette — inspiration, not prescription.
| Reference | Use it as... | NOT as... |
|---|---|---|
| Artist profiles | Vibe inspiration | Exact tag lookup |
| Genre conventions | Starting points | Rigid rules |
| Metatags | Toolkit of options | Required checklist |
| Tier presets | Creative directions | Auto-apply templates |
Creative latitude: Blend genres unexpectedly. Interpret "like [artist]" through artistic essence, not exact specs. Break conventions when the song calls for it. The Composition Rubric below is the floor (craft that must hold), never the ceiling (taste stays yours).
Style Prompts — Dual Form
Suno v5.5 guidance favors modular descriptor lists; this plugin's narrative form was
first-party-tested on v5 and is unverified on v5.5. Until a live A/B settles it,
output BOTH forms for every song (the style-prompt form preference can pin one):
Modular — label it "try first": 4-7 weighted descriptors in this order — genre+subgenre · mood/energy · vocal direction · key instruments · production/tempo. One clear genre anchor; no near-synonym stacking.
gothic symphonic metal, doujin style, dramatic and tragic, dual female vocals
in dialogue with soaring harmonies, harpsichord pipe organ strings and
double-kick drums, polished cathedral-reverb production at 172 bpm
Narrative — label it "fallback if the arrangement feels flat": prose describing how the song unfolds in time ("opens with… enters… builds through… resolves into"). Its v5-tested strength is temporal arrangement control. Weave the emotion arc into the narrative; don't append it.
Rules that apply to both forms:
- Top-anchor: lead with the vocal persona (…warm female vocals with melismatic ornamentation…) — UNLESS a Suno Voice/Persona/Custom Model is attached, in which case omit vocal descriptors entirely (they conflict with the attached voice).
- Single genre anchor — one clear genre reference, not a pile of cousins.
- Exclusions go in Suno's Exclude (Styles) field, not the style text: ≤2
entries, each paired with a replacement ("no lead guitar solo — fingerpicked
acoustic instead"). See
references/suno-metatags.md.
What ships with it
13 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-composition.md 2.7 KB
- references/artist-profiles.md 23 KB
- references/continuation-patterns.md 3.8 KB
- references/examples/gothic-doujin-song.md 7.3 KB
- references/genre-deep-dive.md 7.9 KB
- references/japanese-prosody.md 7.8 KB
- references/jpop-tiers.md 9.3 KB
- references/output-formats.md 5.6 KB
- references/pro-techniques.md 7.0 KB
- references/song-structures.md 3.6 KB
- references/suno-metatags.md 16 KB
- references/troubleshooting.md 12 KB
- references/variation-patterns.md 4.2 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.
- 1mo ago First seen · 236 lines · 184 tokens per session scan A f5cfbf54de40
suno is a skill published in the GitHub repository Linaqruf/kana-code-plugins (4 stars, last pushed 22d ago), licensed MIT. It adds 184 tokens to every session and 2,964 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
pr-vetting
Use when the user wants to thoroughly investigate, vet, review, or security-scan a pull request before deciding how to handle it - especially PRs from external or unknown contributors. Runs a parallel multi-agent investigation (technical, security, value/fit, contributor reputation) and merges the findings into one…
skill-capture
Turn a recurring in-session workflow into a reusable Claude Code skill. Load this the moment you notice you have run the SAME multi-step sequence (same ordered steps or commands, small variation allowed) about three times in the current session, or when open candidates are waiting in .credo/skill-candidates.md at…
requirements-verbatim
Capture a user requirement, decision, approval, or constraint word-for-word into an append-only dated log so it survives context compaction and can never be trimmed, softened, or reinterpreted. Use whenever the user states or approves a requirement, gives a GO, sets a constraint, or makes any decision that later work…
diag
Read-only root-cause diagnosis for a symptom, bug, failure, or unexpected behavior. Establishes the mechanism at file:line and reads up the facts instead of guessing, before any fix is attempted. Produces a diagnosis report; the fix is always a separate step gated by an explicit GO. Use when something is broken…
deno-knowledge-patch
Use this skill when choosing current Deno runtime APIs, CLI options, configuration, dependency behavior, Node compatibility, or deployment workflows. Open the topic reference before changing a project because several commands, flags, APIs, and defaults changed more than once.
android-sdk-knowledge-patch
Use this skill when updating Android applications, libraries, build logic, or Play delivery settings where recent platform and Android Gradle Plugin behavior can affect compatibility. Check the project's compileSdk, targetSdk, minSdk, AGP, Gradle, JDK, Kotlin, KSP, NDK, and form factors before applying target-gated…