lyric-refiner

lyric-refiner is a skill for Claude Code from bitwize-music-studio/claude-ai-music-skills. It costs 36 tokens per session (3,480 once invoked), scanned A, original, CC0-1.0.

A multi-step lyric editing procedure for tightening songs and making tracks fit together as an album.

In plain words
What is it for?
Refining one track or every track in an album, choosing the number of editing passes, and checking whether a track is instrumental before editing.
Why use it?
Repeated editing passes can improve clarity and consistency after lyrics have been written, while instrumental tracks are left alone.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter.

Part of the bitwize-music plugin — 52 skills, 1 hook, 1 MCP server shipped together

Good fit Refining one track or every track in an album, choosing the number of editing passes, and checking whether a track is instrumental before editing.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bitwize-music-studio/claude-ai-music-skills/lyric-refiner
Install

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.

Any agent
npx skills add bitwize-music-studio/claude-ai-music-skills --skill lyric-refiner
Clone the repo
git clone --depth 1 https://github.com/bitwize-music-studio/claude-ai-music-skills

Made for: Claude Code.

Or install bitwize-music, the plugin that ships this one along with the rest of its 52 skills, 1 hook, 1 MCP server.

Wrote 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.

agentmods badge for lyric-refiner

README.md
[![agentmods](https://agentmods.dev/badge/skills/bitwize-music-studio/claude-ai-music-skills/lyric-refiner/github.svg)](https://agentmods.dev/skills/bitwize-music-studio/claude-ai-music-skills/lyric-refiner)
Your own site
<a href="https://agentmods.dev/skills/bitwize-music-studio/claude-ai-music-skills/lyric-refiner"><img src="https://agentmods.dev/badge/skills/bitwize-music-studio/claude-ai-music-skills/lyric-refiner/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.

agentmods 80×15 button for lyric-refiner

Your own site · 80×15
<a href="https://agentmods.dev/skills/bitwize-music-studio/claude-ai-music-skills/lyric-refiner"><img src="https://agentmods.dev/badge/skills/bitwize-music-studio/claude-ai-music-skills/lyric-refiner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,480 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 5
    Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.
    Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00036 $0.03480
Opus 5.5 $0.00014 $0.01392
Sonnet 5.5 $0.00007 $0.00696
Haiku 4.5 $0.00004 $0.00348

Measured 2mo ago against content hash 84edf578b061, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

lyric-refiner 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 2mo 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.

skills/lyric-refiner/SKILL.md · 310 lines

How it starts

The opening of the file, as written. The whole thing — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Your Task

Input: $ARGUMENTS

Parse Arguments

  1. Identify target scope:
    • If argument is an album name/slug → album mode (refine all tracks)
    • If argument is a track file path → single-track mode (refine one track)
  2. Parse pass count: Look for --passes N (default: 3, minimum: 1, maximum: 5)
    • If --passes > 5, warn: "Diminishing returns beyond 5 passes — capping at 5."

Instrumental Guard

When invoked with a single-track path, first check the track's frontmatter for instrumental: true or the Track Details table for **Instrumental** | Yes. If the track is instrumental:

  • STOP and report: "This is an instrumental track — no lyrics to refine. Use /bitwize-music:suno-engineer for Style Box work."
  • Do NOT attempt to refine instrumental tracks.

In album mode, instrumental tracks are silently skipped with a one-line note (not blocking) — see the triage in "Resolve Album & Tracks" below. A mix of instrumental and vocal tracks on the same album is the normal case, not an error.

Resolve Album & Tracks

  1. Use find_album(name) MCP tool to locate the album
  2. Use list_tracks(album_slug) to get all tracks
  3. Triage every track into one of three buckets — the refiner only operates on the third:
    • Instrumental — frontmatter instrumental: true or Track Details **Instrumental** | Yes → skip, emit Skipping {track} — instrumental
    • Not ready — status Not Started / Sources Pending, OR no Lyrics Box content → skip, emit Skipping {track} — no lyrics yet ({status})
    • Refineable — vocal track with lyrics written → include in the refinement pass set
  4. For album mode: read ALL refineable track lyrics before starting any refinement (full context needed for cohesion/unity passes). Instrumental and not-ready tracks do not need to be read.
  5. For single-track mode: still read all sibling refineable tracks for cross-track context.

Pre-flight Exits

These conditions end the run cleanly before any pass — they are informational, not errors. Report and exit; do not treat as a guard-clause failure.

Read the full file on GitHub · 310 lines

Changes

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.

  1. 2mo ago First seen · 310 lines · 36 tokens per session scan A 84edf578b061

Subscribe to this mod's changes

lyric-refiner is a skill published in the GitHub repository bitwize-music-studio/claude-ai-music-skills (631 stars, last pushed 2d ago), licensed CC0-1.0. It adds 36 tokens to every session and 3,480 once invoked, about $0.0001 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.

Related

lyric-refiner compared with skills from other repositories

lyric-refiner next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
lyric-refinerbitwize-music-studio/claude-ai-music-skillsSkill6312d agoCC0-1.0A36Claude Code
api-testingsecondsky/claude-skillsSkill2456d agoMITA39Claude Code
bun-http-serversecondsky/claude-skillsSkill2456d agoMITA31Claude Code
bun-jest-migrationsecondsky/claude-skillsSkill2456d agoMITA25Claude Code
cloudflare-workers-migrationsecondsky/claude-skillsSkill2456d agoMITA49Claude Code
bun-test-coveragesecondsky/claude-skillsSkill2456d agoMITA26Claude Code
api-gateway-configurationsecondsky/claude-skillsSkill2456d agoMITA49Claude Code