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 LoranaAurelia/CloudmusicMCP --skill netease-music-curatorgit clone --depth 1 https://github.com/LoranaAurelia/CloudmusicMCPWrote 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/loranaaurelia/cloudmusicmcp/netease-music-curator)<a href="https://agentmods.dev/skills/loranaaurelia/cloudmusicmcp/netease-music-curator"><img src="https://agentmods.dev/badge/skills/loranaaurelia/cloudmusicmcp/netease-music-curator/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/loranaaurelia/cloudmusicmcp/netease-music-curator"><img src="https://agentmods.dev/badge/skills/loranaaurelia/cloudmusicmcp/netease-music-curator.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 | $0.00062 | $0.00546 |
| Opus 5 | $0.00031 | $0.00273 |
| Sonnet 5 | $0.00012 | $0.00109 |
| Haiku 4.5 | $0.00006 | $0.00055 |
Grade A, and why
netease-music-curator 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 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.
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 — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NetEase Music Curator
Rules
- Run only from an explicit current-chat recommendation request.
- Read
config/recommender.example.jsonanddata/recommender-config.jsonwhen present. Current-request constraints override saved preferences. - Use
get_recommendation_contextonce at startup instead of separate login, likes and playlist-list calls. - Treat liked tracks as deduplication/prior evidence, not proof that every similar track is wanted.
- Search with
search_songs; resolve finalists in batches withget_track_details. - Verify requested style at track or release level using public sources. Platform tags and comments are discovery signals, not sufficient evidence.
- Do not claim to have heard audio unless an actual audio-analysis tool was used.
- Reject unavailable, ambiguous, duplicate and insufficiently verified candidates. Return fewer tracks rather than lower standards.
- After selection is validated, use
create_managed_playlistonce with a stablerequestId; do not repeat create/add calls after it succeeds. - Preserve the intended ordered song IDs before any write. Require
orderVerified=truefromcreate_managed_playlist; if it is false, read the complete playlist, repair only that managed playlist withreorder_playlist_tracks, and verify again before reporting success. - Never delete playlists, remove tracks, cancel likes or change unrelated playlists.
Workflow
- Parse count, style, mood, vocal, structure, included/excluded artists and version policy from the current message.
- Call
get_recommendation_contextand stop with a re-login instruction on authentication failure. - Build a varied candidate pool from exact searches, liked-track credits, album expansion, similar tracks and followed artists when supplied by the user.
- Batch-resolve candidate IDs with
get_track_details; remove liked, unavailable and duplicate recordings unless the request permits them. - Open public sources for each finalist and record specific evidence supporting the requested style.
- Select a diverse set with no unexplained artist/album concentration.
- Call
create_managed_playlistwithrequestId,direction, optionallabel, summary and ordered song IDs. - Report playlist ID, actual added tracks, verification sources, uncertainties and any partial failure.
What ships with it
1 file 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.
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 · 34 lines · 62 tokens per session scan A e2a8d738f918
netease-music-curator is a skill published in the GitHub repository LoranaAurelia/CloudmusicMCP (0 stars, last pushed 2mo ago), licensed MIT. It adds 62 tokens to every session and 546 once invoked, about $0.0003 per session on Opus 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…