Borrowing it
Nothing to install: this file belongs to regiellis/suno-songwriter-agent-skill. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/regiellis/suno-songwriter-agent-skill/main/CLAUDE.mdgit clone --depth 1 https://github.com/regiellis/suno-songwriter-agent-skillWrote 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/instructions/regiellis/suno-songwriter-agent-skill/claude-md)<a href="https://agentmods.dev/instructions/regiellis/suno-songwriter-agent-skill/claude-md"><img src="https://agentmods.dev/badge/instructions/regiellis/suno-songwriter-agent-skill/claude-md/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/instructions/regiellis/suno-songwriter-agent-skill/claude-md"><img src="https://agentmods.dev/badge/instructions/regiellis/suno-songwriter-agent-skill/claude-md.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 | $0.01886 | $0.01886 |
| Opus 5 | $0.00943 | $0.00943 |
| Sonnet 5 | $0.00377 | $0.00377 |
| Haiku 4.5 | $0.00189 | $0.00189 |
Grade C, and why
suno-songwriter-agent-skill CLAUDE.md scanned grade C with 1 finding 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 11d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf /Users/rellis/.agents/skills/suno-songwriter/references How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Suno Model Version
Target model: Suno v5.5 (released 2026-03-26; Voices, Custom Models, My Taste): still current, no v6 released; checked 2026-07-31. When this stamp goes stale, re-verify and overwrite it in place, and keep it in sync with the "current as of" stamp near the top of SKILL.md.
What This Repo Is
This is an agent skill (no application code, no build system). It packages instructions and reference material that teach an agent harness how to produce Suno v5.5-ready song packages: hook-first vocal lyrics, instrumental prompts/arrangements, vocal Style/Excluded Styles prompts, vocal/custom slider suggestions, and multilingual adaptations. The skill is harness-agnostic: anything that can read SKILL.md and selectively load references/ can use it.
The git repo is named suno-songwriter-agent-skill; the working directory and skill name are both suno-songwriter. The skill name in SKILL.md's frontmatter is canonical.
Architecture
Progressive disclosure is the core design constraint:
SKILL.md: the always-loaded entry point. Contains the YAML frontmatter (name,description) used for trigger matching, the core workflow, the output contract, and a routing table pointing toreferences/. Keep this file concise; deeper guidance belongs in a reference file.references/templates.md: the routing index. Every other reference file must be listed here. When you add a reference file, update bothtemplates.mdand the routing list near the top ofSKILL.md.references/*.md: focused, independently-loadable topic files (output skeletons, Suno controls, Suno meta-tags, Suno sounds/samples, cover art/animated covers, studio/iteration, songwriting craft, song structure, rule-of-3, 80/20, instrumental, screen music, multilingual, style selection, genre palettes, genre fusion/multi-genre, remix/style-match, personas, albums, evals). A harness loads only the ones relevant to a request. Prefer adding a new narrow file over growing an existing one. Note:personas.mdandalbums.mdinstruct the agent to write spec.mdfiles into the user's working directory (personas/<slug>.md,albums/<slug>.md), not into this repo.docs/: GitHub Pages documentation site, a single self-containeddocs/index.html(hash-routed SPA, no build step) plus.nojekyll, served frommain/docsat https://regiellis.github.io/suno-songwriter-agent-skill/. It summarizesSKILL.mdandreferences/; it is not a second source of truth. When the output contract, a mode, or Suno controls change, update the matching page section. Design tokens follow the workspaceKARA.mdfamily (Fraunces/Source Serif 4, warm paper,#8A3B12accent); no em-dashes in prose.agents/openai.yaml: harness-specific metadata only. Portable behavior stays inSKILL.md/references/; product-specific config stays underagents/. Other harnesses get their own file (agents/claude.yaml, etc.); do not put harness-specific behavior inSKILL.md.
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.
- 11d ago First seen · 80 lines · 1,886 tokens per session scan C d46ffbd020fc
suno-songwriter-agent-skill CLAUDE.md is an instructions file published in the GitHub repository regiellis/suno-songwriter-agent-skill (6 stars, last pushed 1mo ago), licensed MIT. It adds 1,886 tokens to every session, about $0.0094 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).