Borrowing it
Nothing to install: this file belongs to jeremyruppel/claude-collider. 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/jeremyruppel/claude-collider/main/.claude/skills/play-tape/SKILL.mdgit clone --depth 1 https://github.com/jeremyruppel/claude-colliderWrote 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/jeremyruppel/claude-collider/play-tape)<a href="https://agentmods.dev/skills/jeremyruppel/claude-collider/play-tape"><img src="https://agentmods.dev/badge/skills/jeremyruppel/claude-collider/play-tape/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/jeremyruppel/claude-collider/play-tape"><img src="https://agentmods.dev/badge/skills/jeremyruppel/claude-collider/play-tape.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
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 64 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00023 | $0.00596 |
| Opus 5.5 | $0.00009 | $0.00238 |
| Sonnet 5.5 | $0.00005 | $0.00119 |
| Haiku 4.5 | $0.00002 | $0.00060 |
Grade A, and why
play-tape 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 1mo 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Play Tape
This skill plays a tape — loading its patterns, effects, and routing in the correct order.
When to use
When the user says play @tapes/<name>.scd or asks you to play a tape.
Process
Step 1: Read the tape files
- Read the tape's
.scdfile to understand all the Pdef/Ndef definitions, effects, and sidechains. - Check for an arrangement file at
tapes/<name>-arrangement.scd.
Step 2: Ask the user how they want to play
Always ask:
- Jam — Play all parts at once (add
.playto each Pdef/Ndef) - Arrangement — Play using the CCArrangement (only available if an arrangement file exists)
If no arrangement file exists, offer to create one with /arrange-tape as an alternative.
Step 3: Clear and set tempo
~cc.clear;
~cc.tempo(<bpm>);
Step 4: Load patterns WITHOUT playing them
CRITICAL: Do NOT call .play on any Pdef or Ndef yet. Load all pattern definitions first.
Execute all Pdef(\name, Pbind(...)) and Ndef(\name, {...}) definitions exactly as written in the tape — they define the patterns but do not start them.
Step 5: Load effects, routing, and sidechains
Execute all ~cc.fx.load(...), ~cc.fx.set(...), ~cc.fx.route(...), ~cc.fx.connect(...), ~cc.fx.sidechain(...), and ~cc.fx.routeTrigger(...) calls from the tape.
Step 6: Play
If the user chose Jam:
Play all Pdefs and Ndefs at once by calling .play on each one.
If the user chose Arrangement:
Execute the CCArrangement([...]).play code from the arrangement file.
Optional: MIDI clock sync
If the user wants to sync external gear, enable MIDI clock before playing:
~cc.midi.connect("My Device", \out);
CCMIDIClock.enable(~cc.midi.output);
CCArrangement automatically sends MIDI clock start/stop/ticks when enabled. No extra steps needed during playback.
Key rules
- Always ask jam vs arrangement before playing.
- Never add
.playto patterns when playing an arrangement — the arrangement handles start/stop timing. - Execute the tape code in chunks: tempo, then patterns, then effects, then play.
- Keep the SC code faithful to the tape file — don't rewrite or modify patterns.
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.
- 1mo ago First seen · 72 lines · 23 tokens per session scan A fa191eaa71b5
play-tape is a skill published in the GitHub repository jeremyruppel/claude-collider (59 stars, last pushed 12d ago), licensed MIT. It adds 23 tokens to every session and 596 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.
Other skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…