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 imkohenauser/mtp --skill mtp-playlistgit clone --depth 1 https://github.com/imkohenauser/mtpWrote 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/imkohenauser/mtp/mtp-playlist)<a href="https://agentmods.dev/skills/imkohenauser/mtp/mtp-playlist"><img src="https://agentmods.dev/badge/skills/imkohenauser/mtp/mtp-playlist/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/imkohenauser/mtp/mtp-playlist"><img src="https://agentmods.dev/badge/skills/imkohenauser/mtp/mtp-playlist.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 | $0.00085 | $0.04219 |
| Opus 5.5 | $0.00034 | $0.01688 |
| Sonnet 5.5 | $0.00017 | $0.00844 |
| Haiku 4.5 | $0.00009 | $0.00422 |
Grade A, and why
mtp-playlist 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.
How it starts
The opening of the file, as written. The whole thing — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MTP Playlist
MTP Playlist creates a music sequence using the Mapping the Prompt (MTP) framework.
It can map songs, recordings, compositions, performances, sound works, or musical moments.
Take your time with the curation. This is not a quick list to dash off — you are composing roughly an hour of someone's life. Treat the listener's hour as precious, and spend real effort researching, digging, and verifying so the finished sequence earns it.
Request types
Theme-only
The default. The user names a theme; you choose all 20 tracks to fit the theme and each node's function.
Examples:
/mtp-playlist Mozart for Spring
/mtp-playlist Strings at Work
Theme with node placements
The user may anchor one or more specific tracks to named MTP nodes. Treat the remainder as a theme-only request: fill unassigned nodes with tracks that honor the theme and each node's function.
Node names may appear as MTP labels (Start, Helix, Fade, etc.) or as numbers 1–20.
Examples:
/mtp-playlist Ravel with Boléro at Helix
/mtp-playlist Orchestral crescendo with Boléro at Helix
/mtp-playlist The Beatles starting with Hello, Goodbye at Start
Ravel with Boléro at Helix— theme: Ravel; anchor "Boléro" at #6HelixOrchestral crescendo with Boléro at Helix— theme: orchestral crescendo; anchor "Boléro" at #6HelixThe Beatles starting with Hello, Goodbye at Start— theme: The Beatles; anchor "Hello, Goodbye" at #1Start
Placement rules:
- Apply every user-specified anchor before choosing any other track.
- Do not move, swap, or override anchored tracks unless the user asks.
- Anchors reshape the surrounding sequence. When a track is fixed at a node, treat that placement as a constraint that changes which tracks best fit the remaining nodes — not as an isolated decision. A strong anchor at
Helix, for example, shifts whatOpen,Grow, andEnterneed to do in relation to it. - Anchored tracks must still perform their node's function as far as possible; state any tension honestly in
Reason. An unexpected anchor can be productive: a familiar song placed early, late, in the middle, or as a deliberate dissonance reveals a different facet of it. - If a placement is ambiguous (wrong track title, unclear node, or conflicting anchors), ask briefly before generating.
What ships with it
2 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.
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.
- 2mo ago First seen · 231 lines · 85 tokens per session scan A 483b1e025714
mtp-playlist is a skill published in the GitHub repository imkohenauser/mtp (5 stars, last pushed 4mo ago), licensed MIT. It adds 85 tokens to every session and 4,219 once invoked, about $0.0003 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 2026-08-31.
mtp-playlist compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mtp-playlistimkohenauser/mtp | Skill | 5 | 4mo ago | MIT | A | 85 | Claude Code |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 4d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |