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-log-analysis/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-log-analysis)<a href="https://agentmods.dev/skills/perminder-klair/subwave/subwave-log-analysis"><img src="https://agentmods.dev/badge/skills/perminder-klair/subwave/subwave-log-analysis/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-log-analysis"><img src="https://agentmods.dev/badge/skills/perminder-klair/subwave/subwave-log-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00228 | $0.02787 |
| Opus 5.5 | $0.00091 | $0.01115 |
| Sonnet 5.5 | $0.00046 | $0.00557 |
| Haiku 4.5 | $0.00023 | $0.00279 |
Grade A, and why
subwave-log-analysis 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 16d 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.
internal/Tailscale address. Liquidsoap works around this with a `curl`-based How it starts
The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SUB/WAVE log analysis
What this is
The SUB/WAVE controller writes a unified, append-only event log to
state/logs/events-YYYY-MM-DD.jsonl — one JSON object per line. It is the
station's flight recorder: every LLM call, every agent tool call, every
Navidrome/Subsonic API call, plus track plays and session boundaries. Events
made inside one DJ decision share a traceId, so a decision and the calls it
triggered read back as a single trace.
This skill turns that raw stream into a written diagnostic report for the operator, covering three lenses: Navidrome usage, picker/DJ quality, and health & anomalies. The job is to diagnose and recommend — describe what the logs show, then suggest concrete changes with reasoning.
A bundled script does the aggregation; your job is interpretation. Do not re-derive numbers by hand or eyeball the JSONL — run the script and reason about its output.
Step 1 — Run the analysis script
python3 scripts/analyze_events.py [--state-dir DIR] [--since 24h] [--day YYYY-MM-DD]
--state-dir— path to the SUB/WAVEstate/directory. Omit it and the script auto-detects./stateor../state, so from the subwave repo root it usually needs no argument. Pass it explicitly if the repo is elsewhere.--since— narrow to a recent window:6h,24h,3d,1w. Use this when the user asks about "today", "the last few hours", "this week". Omit it to analyse everything on disk.--day— pin to a single day's file.
The script prints a sectioned digest. Read all of it before writing anything.
If the script reports no events files: the unified log is written by the
controller, and it is a recent addition — it only exists once the controller
has been rebuilt with observability/events.js and has run. A controller
restart is not enough; its source is baked in at build time. Tell the
operator this rather than guessing. If the file exists but is nearly empty, the
station simply hasn't been on air long — say so and analyse what little there is.
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.
- 16d ago Changed · +2 lines 5c63b4f19e2d
- 23d ago Changed · +12 lines 0039ab89e025
- 2mo ago First seen · 187 lines · 228 tokens per session scan A d9c890b08da7
subwave-log-analysis is a skill published in the GitHub repository perminder-klair/subwave (1,568 stars, last pushed today), licensed MIT. It adds 228 tokens to every session and 2,787 once invoked, about $0.0009 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
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
cwv-optimizer
Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…
ci-fixer
CI failures - read error, minimal fix, verify.
incident-response-incident-response
Coordinate production incident triage, mitigation, investigation, recovery, and follow-up. Use when responding to outages or other incidents that require structured operational coordination.
diagnosing-missing-recordings
Diagnoses why a session recording is missing or was not captured. Use when a user asks why a session has no replay, why recordings aren't appearing, or wants to troubleshoot session replay capture issues for a specific session ID or across their project. Covers SDK diagnostic signals, project settings, sampling…