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-worktree-dev/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-worktree-dev)<a href="https://agentmods.dev/skills/perminder-klair/subwave/subwave-worktree-dev"><img src="https://agentmods.dev/badge/skills/perminder-klair/subwave/subwave-worktree-dev/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-worktree-dev"><img src="https://agentmods.dev/badge/skills/perminder-klair/subwave/subwave-worktree-dev.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 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 35 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.
- high Privilege Escalation · line 52 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 Data Exfiltration · line 135 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Excessive Agency · line 151 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 | $0.00196 | $0.02465 |
| Opus 5.5 | $0.00078 | $0.00986 |
| Sonnet 5.5 | $0.00039 | $0.00493 |
| Haiku 4.5 | $0.00020 | $0.00247 |
Grade A, and why
subwave-worktree-dev 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 22d 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 # expect {"status":"on-air"} How it starts
The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SUB/WAVE worktree dev setup
Get the SUB/WAVE dev stack running from inside a git worktree so branch changes can be tested without touching the main checkout.
Why a worktree needs prep
A worktree checks out every tracked file, so all source is already there. But the dev stack also depends on gitignored files that do not travel with a worktree checkout:
| File | Why the stack needs it |
|---|---|
.env |
Root .env — the controller's only env_file in dev compose (./.env), and compose's substitution source. ADMIN_USER / ADMIN_PASS / SITE_URL, plus NAVIDROME_* and LLM/TTS keys. Compose refuses to start without it. |
controller/.env |
Legacy — nothing reads it. Older checkouts still keep NAVIDROME_* and API keys here; the script folds any key it has into the worktree's root .env (root wins, ICECAST_* skipped). Without that, the station boots with needsSetup: true and "could not reach http://navidrome:4533". |
web/.env.local |
Dev API/stream URL overrides (NEXT_PUBLIC_API_URL etc.). Without it the web UI defaults to same-origin /api and cannot reach the controller. Copied from main if present, otherwise written against $SUBWAVE_DEV_HOST (default localhost). |
docker/.env |
Compose variable substitution (legacy — harmless to copy). |
state/setup-config.json |
Navidrome creds the wizard saved on main. Without this the controller reports needsSetup: true and the player redirects to /onboarding on every load. |
state/secrets.env |
Cloud LLM / TTS API keys (if main has any). Sourced into the controller's process.env on boot. |
state/settings.json |
Operator's full config — LLM provider/model, personas, shows, TTS. Without it the controller boots with default settings (llm.model = ''), every LLM call returns "fetch failed", and the new skills cannot run. |
state/moods.json |
Library mood tagging produced by npm run tag (LLM walk over the whole library — expensive to redo per branch). |
state/sfx.json + sfx/ |
Sound-effects catalogue metadata + rendered WAVs the admin UI lists and liquidsoap mixes in. |
state/jingles.json + jingles.m3u + jingles/ |
Pre-rendered station idents. Liquidsoap reads the M3U with reload_mode="watch". |
state/recent-plays.json |
24h play log — the picker and the library-deep-cut skill key off it for dedup. |
state/sessions/ |
Archived DJ sessions (the live one is regenerated on boot). |
state/voice/ |
Persona TTS reference voices (Chatterbox cloning refs, if any). |
web/node_modules |
Needed by npm run dev. |
state/ |
Bind-mounted into the containers. A worktree's state/ is empty. |
What ships with it
3 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.
- 22d ago Changed · +11 lines cbd5ec8a5314
- 2mo ago First seen · 171 lines · 196 tokens per session scan A c7da0e63322b
subwave-worktree-dev is a skill published in the GitHub repository perminder-klair/subwave (1,578 stars, last pushed today), licensed MIT. It adds 196 tokens to every session and 2,465 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
merge-batch
Prepare and merge an owner-selected PR batch with contributor credit and exact-candidate admission. Use for a pasted PR list; combined focused validation is diagnostic, and every actual landing still requires its applicable checks and authorization.
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
gh-auth-isolation
Safely manage multiple GitHub identities (EMU + personal) in agent workflows.
comet-github
A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.
github-skill
Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.
release-helper
Ensures configuration and code changes are released correctly. Use PROACTIVELY whenever you edit config.json, change any setting, or fix a configuration bug in this project, so the change reaches production.