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 zarlor/suno-band-manager --skill suno-style-prompt-buildergit clone --depth 1 https://github.com/zarlor/suno-band-managerWrote 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/zarlor/suno-band-manager/suno-style-prompt-builder)<a href="https://agentmods.dev/skills/zarlor/suno-band-manager/suno-style-prompt-builder"><img src="https://agentmods.dev/badge/skills/zarlor/suno-band-manager/suno-style-prompt-builder/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/zarlor/suno-band-manager/suno-style-prompt-builder"><img src="https://agentmods.dev/badge/skills/zarlor/suno-band-manager/suno-style-prompt-builder.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 | $0.00054 | $0.01999 |
| Opus 5.5 | $0.00022 | $0.00800 |
| Sonnet 5.5 | $0.00011 | $0.00400 |
| Haiku 4.5 | $0.00005 | $0.00200 |
Grade A, and why
suno-style-prompt-builder 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 22d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Style Prompt Builder
Act as a producer's sound engineer who thinks in sonic textures, frequency ranges and production. The outcome is a complete Suno package — style prompt, Exclude Styles, Controls settings, title and a wild card — for the user's model and tier, blending a band profile's baseline with this song's direction. Its consumer, the user at Suno's Create form or the Band Manager calling headless, pastes it as given, so every field has passed the validator and every judgment call carries its reason.
On Activation
- Resolve customization. Run
uv run {project-root}/_bmad/scripts/resolve_customization.py --skill {skill-root} --project-root {project-root} --key workflow(always run it; never decide it's missing from a directory listing, which may be cut short). If it can't run, usecustomize.toml's defaults and say once that setting up BMad (invoke thebmadskill) restores overrides. Run anyactivation_steps_prepend; loadpersistent_facts. A user changes a value (say, the ledger path) by invoking thebmad-customizeskill naming the key; if it isn't installed, offernpx skills add bmad-code-org/BMAD-METHOD --skill bmad-customize. - Load config. Always run
uv run {project-root}/_bmad/scripts/resolve_config.py --project-root {project-root} --key modules.suno(never judge it missing from a listing) forsuno_tierandband_profiles_folder(default{project-root}/docs/band-profiles); missing values take the defaults. If the resolver is missing, BMad isn't set up here: use the defaults and offerbmad setup suno(thebmadskill) once in your first reply, even when the user opened with a request — in a headless run, as onewarningsentry instead. - Headless (
--headless/-H, any--headless:variant, or clearly non-interactive intent): readreferences/headless-contract.mdfully, run anyactivation_steps_append, and follow the steps below without greeting or asking. Write no text at all until the reply: every tool call goes out with no words beside it (no "Now emitting…", no progress note), and the reply starts with{and ends with}, nothing before or after it. - Interactive: greet the user in their language, run any
activation_steps_append, readreferences/interactive-session.mdfully (intake, presentation, refine loop), then go to Step 1.
What ships with it
20 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.
- bmod.toml 511 B
- customize.toml 1.6 KB
- evals/cases.json 22 KB
- evals/fixtures/band-profiles/iron-bayou.yaml 1.5 KB
- evals/fixtures/band-profiles/porchlight-saints.yaml 1.3 KB
- evals/fixtures/band-profiles/saint-roch-revival.yaml 1.2 KB
- evals/fixtures/band-profiles/willow-creek-assembly.yaml 1.3 KB
- evals/triggers.json 2.1 KB
- references/headless-contract.md 12 KB
- references/interactive-session.md 4.9 KB
- references/model-prompt-strategies.md 88 KB
- references/research-sources.md 25 KB
- references/retired-model-strategies.md 9.4 KB
- references/safety-tables.md 15 KB
- references/v6-build-core.md 8.1 KB
- scripts/_shared/__init__.py 0 B runs code
- scripts/_shared/suno_constants.py 7.3 KB runs code
- scripts/tests/__init__.py 0 B runs code
- scripts/tests/test_validate_prompt.py 49 KB runs code
- scripts/validate-prompt.py 49 KB runs code
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.
- 22d ago Changed · -38 lines · +15 tokens per session 01cdd1dc69df
- 1mo ago Changed · -154 lines ba84e92f7803
- 1mo ago Changed · +8 lines 17820bca05d4
- 1mo ago Changed · +5 lines 112ad197921a
- 2mo ago First seen · 248 lines · 39 tokens per session scan A b23a34823907
suno-style-prompt-builder is a skill published in the GitHub repository zarlor/suno-band-manager (14 stars, last pushed 2d ago), licensed MIT. It adds 54 tokens to every session and 1,999 once invoked, about $0.0002 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 2026-08-30.
suno-style-prompt-builder compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| suno-style-prompt-builderzarlor/suno-band-manager | Skill | 14 | 2d ago | MIT | A | 54 | Claude Code |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | today | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | today | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 314k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |