Subwave is an internet radio station where an AI DJ selects music and speaks between tracks for every listener at once. Listeners can request music in plain language, while operators manage the queue, schedule, DJ personas, and station activity. Its catalogue entries define skills and workflows for operating the station.
Borrowing it
Nothing to install: this file belongs to perminder-klair/subwave. 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/perminder-klair/subwave/develop/.claude/skills/subwave-control/SKILL.mdgit clone --depth 1 https://github.com/perminder-klair/subwaveWrote 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/perminder-klair/subwave/subwave-control)<a href="https://agentmods.dev/skills/perminder-klair/subwave/subwave-control"><img src="https://agentmods.dev/badge/skills/perminder-klair/subwave/subwave-control/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/perminder-klair/subwave/subwave-control"><img src="https://agentmods.dev/badge/skills/perminder-klair/subwave/subwave-control.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
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 →
- high Privilege Escalation · line 124 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium Excessive Agency · line 112 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 | $0.00205 | $0.01781 |
| Opus 5.5 | $0.00082 | $0.00712 |
| Sonnet 5.5 | $0.00041 | $0.00356 |
| Haiku 4.5 | $0.00020 | $0.00178 |
Grade A, and why
subwave-control scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sf http://localhost:7701/health # dev — controller exposed directly How it starts
The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SUB/WAVE control
Bring the SUB/WAVE stack up or down. Nothing more. No builds, no pulls, no setup — if any of those are needed, hand off to the subwave-deploy skill.
This skill is checked into the SUB/WAVE repo. The repo root is the git repository that contains this skill — derive it once, don't hardcode it:
REPO=$(git -C "<this skill's base directory>" rev-parse --show-toplevel)
<this skill's base directory> is the absolute path shown as "Base directory
for this skill" when the skill loads. All docker compose invocations run from
docker/ inside $REPO. Shell state does not persist between commands, so
re-derive $REPO (or substitute its value) in each command block below.
The three things you need to know
-
Two compose files = two modes.
- Dev —
docker-compose.dev.yml: Icecast + Liquidsoap + Controller only. Web runs separately asnpm run devon the host (port7700). - Prod —
docker-compose.yml: addsweb(built image) andcaddy(edge router). Only Caddy binds a host port. State defaults to<repo>/state(override with theSTATE_DIRenv).
- Dev —
-
Service ports (post-renumber): Web
7700, Controller7701, Icecast7702. The controller's/healthendpoint returns{"status":"on-air"}once Liquidsoap is connected to Icecast — that's the canonical "is it up?" check. -
Web dev is hot-reloaded but must be launched separately in dev mode.
npm run devinweb/is a long-running foreground process; in this skill, always run it as a background task. The Next.js port7700collides with macOS AirPlay Receiver in some setups — if you getEADDRINUSEon:7700, checklsof -nP -iTCP:7700 -sTCP:LISTENand surface the conflict to the user rather than guessing.
Workflow
Step 0 — Detect what's running
cd "$REPO"
RUNNING_DEV=$(docker compose -f docker-compose.dev.yml ps -q 2>/dev/null)
RUNNING_PROD=$(docker compose -f docker-compose.yml ps -q 2>/dev/null)
WEB_DEV_PID=$(lsof -nP -iTCP:7700 -sTCP:LISTEN -t 2>/dev/null | head -1)
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 · 135 lines · 205 tokens per session scan A 3465301b92df
subwave-control is a skill published in the GitHub repository perminder-klair/subwave (1,568 stars, last pushed today), licensed MIT. It adds 205 tokens to every session and 1,781 once invoked, about $0.0008 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). 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…