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-release-pr/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-release-pr)<a href="https://agentmods.dev/skills/perminder-klair/subwave/subwave-release-pr"><img src="https://agentmods.dev/badge/skills/perminder-klair/subwave/subwave-release-pr.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00200 | $0.03837 |
| Opus 5 | $0.00100 | $0.01919 |
| Sonnet 5 | $0.00040 | $0.00767 |
| Haiku 4.5 | $0.00020 | $0.00384 |
Grade A, and why
subwave-release-pr 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 7d 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 — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SUB/WAVE release PR
Open a pull request from develop → main. Everything after that — version bump, CHANGELOG, tag, GitHub release, image publishing — is handled by the release-please and publish-images workflows once the PR merges. This skill's job is just to surface a clean PR with a useful summary.
Why this skill exists
A release PR for SUB/WAVE is mechanical but easy to get wrong by hand: forgetting to fetch first, listing merge commits in the body, picking up commits that are actually already on main via a back-merge. The skill encodes the right git plumbing and the body format that matches the project's recent PR history.
It also keeps develop from drifting behind main. After every release, release-please pushes a chore(main): release X.Y.Z version bump (and CHANGELOG entry) directly to main, and that commit — plus the merge-commit bubble from the release PR — never flows back to develop on its own. Left alone, develop steadily falls "N commits behind main" even though it carries every line of real source. This skill detects that gap up front and closes it with a back-merge after the release lands (Step 8).
Workflow
Step 0 — Sanity checks
Run these from the repo root (/home/klair/Projects/subwave). They're cheap, surface state, and let you decide whether to proceed:
git rev-parse --show-toplevel # confirm we're in subwave (or any git repo)
git status --short # any uncommitted work?
git rev-parse --abbrev-ref HEAD # current branch (informational — we work via remote refs)
git fetch origin main develop # MUST run before computing the diff, otherwise stale
git rev-list --left-right --count origin/develop...origin/main # "<ahead> <behind>" — develop relative to main
What to do with the output:
- If
git status --shortshows uncommitted changes, surface them to the user and ask whether to proceed (the PR is built fromorigin/develop, so local edits won't be in it — but the user might want to commit them first). - If
git fetchfails (no network, no remote), stop and tell the user. Don't fall back to local refs — the PR base isorigin/mainand the head isorigin/develop, so the comparison must be against fresh remotes. - If the second number ("behind") is > 0, develop is behind main. Inspect those commits with
git log --oneline origin/develop..origin/mainbefore reacting. Almost always they're pure release bookkeeping —chore(main): release …version bumps + merge-commit bubbles from prior release PRs — in which case develop is not missing any real source and the release PR is unaffected (a merge commit does a 3-way merge, so main's version bump and CHANGELOG survive). Note the gap to the user, proceed with the PR, and plan to close it with the Step 8 back-merge once this release lands. Only stop and flag it as a real problem if those "behind" commits includefeat:/fix:/refactor:work that isn't already on develop — that means a hotfix landed straight on main and should be back-merged into develop before you cut the release, so the release PR doesn't reintroduce or conflict with it.
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.
- 7d ago First seen · 227 lines · 200 tokens per session scan A 8d3a10745585
subwave-release-pr is a skill published in the GitHub repository perminder-klair/subwave (1,303 stars, last pushed today), licensed MIT. It adds 200 tokens to every session and 3,837 once invoked, about $0.0010 per session on Opus 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
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.
agent-release-swarm
Agent skill for release-swarm - invoke with $agent-release-swarm.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
pack-submit
Package one of this agent's own skills as a standalone community pack and submit it to the aeon registry as a PR.
updater_guide
Guidance for checking for and installing Row-Bot updates.