Borrowing it
Nothing to install: this file belongs to umsachde/re-com. 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/umsachde/re-com/main/.claude/skills/recom-playlist-handoff/SKILL.mdgit clone --depth 1 https://github.com/umsachde/re-comWrote 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/umsachde/re-com/recom-playlist-handoff)<a href="https://agentmods.dev/skills/umsachde/re-com/recom-playlist-handoff"><img src="https://agentmods.dev/badge/skills/umsachde/re-com/recom-playlist-handoff/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/umsachde/re-com/recom-playlist-handoff"><img src="https://agentmods.dev/badge/skills/umsachde/re-com/recom-playlist-handoff.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 | $0.00055 | $0.00705 |
| Opus 5.5 | $0.00022 | $0.00282 |
| Sonnet 5 | $0.00011 | $0.00141 |
| Haiku 4.5 | $0.00006 | $0.00071 |
Grade A, and why
recom-playlist-handoff 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 9d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
re-com is deliberately read-only (see PLAN.md §4.9) — it never creates a
playlist or adds a track anywhere, so "recommend me songs and make it a
playlist" is always three separate steps, in this exact order. Skipping the
third step is the footgun: the cached library-exclusion set stays stale for up
to RECOM_CACHE_TTL (default 6 hours), so a later recommendation call can hand
back a song you just saved as if it were still "new".
The three steps
-
Get the songs from re-com, not from a bare
ytmusic/spotifysearch:recommend_from_song,recommend_from_playlist,songs_by_artist,recommend_for_mood, orrecommend_from_playlist_for_mood.- Never hand-pick candidates from the raw
ytmusic/spotifyMCP search tools instead — that bypasses re-com's library-exclusion guarantee entirely, and a search result's own "already in library" flag is not reliable.
-
Create/add via the playlist-management MCP server for that backend —
ytmusic(create_playlist/add_to_playlist) or the equivalent Spotify tools — using the ids (videoIdfor YouTube, track id for Spotify) that re-com's response returned. re-com has no playlist-write tool of its own; don't look for one. -
Call
refresh_library(video_ids=[...])on the same re-com instance immediately after, passing exactly the ids you just added. It adds them to the exclusion cache instantly, with no ~20s rebuild. This is not optional cleanup: re-com keeps a song it handed out excluded forRECOM_SERVED_TTL(default 2 hours), but once that passes, a saved song can come back until the cache is refreshed. Call it once per batch of adds, right after the add call succeeds, not at the end of an unrelated later turn. Barerefresh_library()(a full rebuild) is only for library changes you can't list by id.
Which re-com instance to refresh
There are two separate re-com registrations, one per backend
(re-com for YouTube Music, re-com-spotify for Spotify), each with its own
store and library cache (PLAN.md §4.10). Call refresh_library() on the
same instance whose backend you just wrote to — refreshing the other one
does nothing for the cache that matters.
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.
- 9d ago Changed · +8 lines daf0164b6650
- 10d ago First seen · 48 lines · 55 tokens per session scan A afbea91ca604
recom-playlist-handoff is a skill published in the GitHub repository umsachde/re-com (0 stars, last pushed 2d ago), licensed MIT. It adds 55 tokens to every session and 705 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 2026-09-14.
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…