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-feedback-elicitorgit 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-feedback-elicitor)<a href="https://agentmods.dev/skills/zarlor/suno-band-manager/suno-feedback-elicitor"><img src="https://agentmods.dev/badge/skills/zarlor/suno-band-manager/suno-feedback-elicitor/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-feedback-elicitor"><img src="https://agentmods.dev/badge/skills/zarlor/suno-band-manager/suno-feedback-elicitor.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 | $0.01877 |
| Opus 5.5 | $0.00022 | $0.00751 |
| Sonnet 5.5 | $0.00011 | $0.00375 |
| Haiku 4.5 | $0.00005 | $0.00188 |
Grade A, and why
suno-feedback-elicitor 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feedback Elicitor
Act as the user's A&R collaborator: they heard the take, you can't, so you draw out what they felt and translate it. The outcome is concrete adjustments (style prompt, Exclude Styles, sliders, lyrics, or a regeneration or editor path) that the Style Prompt Builder, Lyric Transformer or a headless Band Manager applies without this conversation, so each names its dimension, direction and reason. Speak plainly with the technical term in parentheses, and mirror the user's own words ("crunchy" stays "crunchy"; renaming it breaks the bridge). Plain questions ("too busy or too empty?") beat rating scales.
Rules for every mode
- Creative feedback: prompt changes before regeneration. Technical artifacts: no prompt edit until the artifact persists — repair a keeper take's bad span first (Replace Section), otherwise regenerate the unchanged prompt a few times; an artifact is usually one generation's, and a prompt edit for it can break what works.
map-adjustments.pyholds artifact edits apart underif_artifact_persists. - Preserve what works: name the keepers and risk none of them. A keeper's own words and part stay untouched: no remove, exclude, add or reorder item rewrites it (an add like "palm-muted riff" changes the riff). Mix-space moves around it are fine and often the fix — "leave midrange room for the vocal", "guitars a step behind the voice" — as long as the keeper's description itself doesn't change.
- Instrumental track: no vocal or lyric questions or recommendations, and no question spent confirming there are no vocals.
- Mixed feedback: clear and technical issues first; solving them often clarifies the vague ones.
- Vague feedback narrows before it maps: one question at a time toward one anchor, no proposed changes until a dimension and direction are confirmed. No convergence after 3–4 questions: offer 2–3 contrasting variants plus a wild card, turning elicitation into selection.
- Dual-path issues ("robotic vocals"): map the prompt-fixable part alongside the technical fix.
- Tier gates every path (
{suno_tier}; ask only when unset): Replace Section at Pro and Premier, Studio at Premier, regeneration on Free. - Interactive recommendations go through the
suno-style-prompt-builderskill before you show them; a hand-edited prompt skips its artist-name, character-budget and exclusion checks.
What ships with it
52 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 611 B
- customize.toml 1.4 KB
- evals/cases.json 12 KB
- evals/triggers.json 2.0 KB
- references/audio-analysis-scripts.md 6.9 KB
- references/controls.md 5.7 KB
- references/durable-writes.md 4.2 KB
- references/feedback-triage-guide.md 7.3 KB
- references/gemini-audio-analysis.md 8.9 KB
- references/headless-contract.md 9.7 KB
- references/map-arrangement.md 3.6 KB
- references/map-energy-structure.md 6.0 KB
- references/map-production-mood.md 2.6 KB
- references/map-vocals.md 6.1 KB
- references/output-template.md 3.6 KB
- references/research-sources.md 5.7 KB
- references/retired-models.md 1.8 KB
- references/technical-resolution.md 16 KB
- scripts/_shared/__init__.py 0 B runs code
- scripts/_shared/audio_deps.py 1.8 KB runs code
- scripts/_shared/beat_grid.py 13 KB runs code
- scripts/_shared/bmad_config.py 2.9 KB runs code
- scripts/_shared/companion_writer.py 7.2 KB runs code
- scripts/_shared/json_archiver.py 4.5 KB runs code
- scripts/_shared/loudness.py 6.0 KB runs code
- scripts/_shared/suno_constants.py 7.3 KB runs code
- scripts/_shared/tempo_source.py 13 KB runs code
- scripts/analyze-audio.py 16 KB runs code
- scripts/audio-deep-analysis.py 12 KB runs code
- scripts/audio-files-manifest.py 7.0 KB runs code
- scripts/beat-grid.py 731 B runs code
- scripts/chord-progression.py 13 KB runs code
- scripts/feedback-log.py 11 KB runs code
- scripts/map-adjustments.py 35 KB runs code
- scripts/parse-feedback.py 15 KB runs code
- scripts/section-map.py 51 KB runs code
- scripts/tempo-detail.py 11 KB runs code
- scripts/tests/__init__.py 0 B runs code
- scripts/tests/test_analyze_audio.py 6.4 KB runs code
- scripts/tests/test_audio_deep_analysis.py 1.8 KB runs code
- scripts/tests/test_audio_files_manifest.py 3.3 KB runs code
- scripts/tests/test_beat_grid.py 5.7 KB runs code
- scripts/tests/test_chord_progression.py 991 B runs code
- scripts/tests/test_feedback_log.py 8.3 KB runs code
- scripts/tests/test_map_adjustments.py 22 KB runs code
- scripts/tests/test_parse_feedback.py 11 KB runs code
- scripts/tests/test_section_map.py 23 KB runs code
- scripts/tests/test_tempo_detail.py 976 B runs code
- scripts/tests/test_verify_audio_files.py 6.8 KB runs code
- scripts/tests/test_vocal_placement.py 2.3 KB runs code
- scripts/verify-audio-files.py 18 KB runs code
- scripts/vocal-placement.py 11 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 · -68 lines · +8 tokens per session c49ce68d1160
- 1mo ago Changed · -144 lines d224ecc88ce0
- 1mo ago Changed · +5 lines 710b195c350a
- 1mo ago Changed · +5 lines 77533d777ca9
- 2mo ago First seen · 253 lines · 46 tokens per session scan A 98a06a73d50e
suno-feedback-elicitor 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 1,877 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-feedback-elicitor compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| suno-feedback-elicitorzarlor/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 |