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/verify/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/verify)<a href="https://agentmods.dev/skills/perminder-klair/subwave/verify"><img src="https://agentmods.dev/badge/skills/perminder-klair/subwave/verify/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/verify"><img src="https://agentmods.dev/badge/skills/perminder-klair/subwave/verify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 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 Tool Misuse · line 24 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Tool Misuse · line 16 Tool defaults are unsafe or overly permissive (e.g. disabled TLS verification, no authentication, world-writable permissions). Unsafe defaults widen the attack surface.Fix: Override unsafe defaults with secure settings (verify=True, auth required, restrictive permissions). Review and harden all tool configurations.
- medium MCP Rug Pull · line 18 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00045 | $0.00462 |
| Opus 5.5 | $0.00018 | $0.00185 |
| Sonnet 5.5 | $0.00009 | $0.00092 |
| Haiku 4.5 | $0.00005 | $0.00046 |
Grade A, and why
verify scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Drive `/settings` etc. with `curl -u test:test http://localhost:7791/...`. What it actually says
Verifying controller + admin-UI changes in isolation
The operator's real station is usually running (docker sub-wave-* containers). Never restart or
point tests at it. Boot your own stack from the worktree instead:
Isolated controller (API surface)
cd <worktree>/controller
STATE_DIR=$CLAUDE_JOB_DIR/tmp/state PORT=7791 ADMIN_USER=test ADMIN_PASS=test \
NODE_ENV=development \
NAVIDROME_URL=http://localhost:9999 NAVIDROME_USER=x NAVIDROME_PASS=x \
npx tsx src/server.ts
- A fresh
STATE_DIRboots clean (seeds sfx/jingles, writessettings.jsonon first save). - The fake
NAVIDROME_*env matters: without itneedsSetupis true and the admin shell redirects every page to/onboarding, so UI tests never find their controls. - Drive
/settingsetc. withcurl -u test:test http://localhost:7791/.... - To test load-time migrations: stop the server, hand-edit
settings.json, restart, GET. - Kill by port (
fuser -k 7791/tcp) — apkill -f "tsx src/server.ts"matches the Bash tool's own wrapper cmdline and kills your shell (exit 144).
Worktree web dev server (UI surface)
cd <worktree>/web
NEXT_PUBLIC_API_URL=http://localhost:7791 npm run dev -- -p 7793
Then Playwright (headless chromium, sync API):
- Pre-seed auth before load:
ctx.add_init_script("localStorage.setItem('subwave_admin_auth', '<base64 user:pass>')"). - Assert state through the controller API after clicking Save, not through sonner toasts.
- Admin modals portal into
.admin-root; scope input lookups with[role="dialog"].
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 · 41 lines · 45 tokens per session scan A 7d18ebc94bc1
verify is a skill published in the GitHub repository perminder-klair/subwave (1,568 stars, last pushed today), licensed MIT. It adds 45 tokens to every session and 462 once invoked, about $0.0002 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
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
test-master
Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation…
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
test-warp-ui
Guides testing Warp UI features and changes using the computer use tool. Use this skill only when computer-use testing was requested (explicit request or accepted offer) and the computeruse tool is available to the agent. Covers launching Warp and verifying UI behavior.