Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/christosk92/waveemusic/waveenpx skills add christosk92/WaveeMusic --skill waveegit clone --depth 1 https://github.com/christosk92/WaveeMusicWrote 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/christosk92/waveemusic/wavee)<a href="https://agentmods.dev/skills/christosk92/waveemusic/wavee"><img src="https://agentmods.dev/badge/skills/christosk92/waveemusic/wavee.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 | $0.00050 | $0.01821 |
| Opus 5 | $0.00025 | $0.00911 |
| Sonnet 5 | $0.00010 | $0.00364 |
| Haiku 4.5 | $0.00005 | $0.00182 |
Grade A, and why
wavee 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 4d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wavee app
Scope: src/apps/Wavee/**, src/apps/Wavee.Core/**, src/apps/Wavee.Tests/** only.
⛔ HARD RULES for subagents (agents dispatched by an orchestrator). (1) Never
git stash— or any other git state change (no commit/checkout/reset/restore/stash pop): the working tree is shared and a stash wipes every parallel agent's in-progress edits. (2) Never run builds or test suites — nodotnet build,dotnet test, VerticalSlice, or check-canon: parallel builds on the sharedobj/bincollide and exhaust the machine. Write code + tests only; the orchestrator runs the full verification once after the whole batch. (Working solo, i.e. not as a dispatched subagent? Then the Build & verify commands below are yours to run.)
Build & verify
dotnet build src/apps/Wavee/Wavee.csproj
dotnet test src/apps/Wavee.Tests/Wavee.Tests.csproj
Architecture hub
docs/plans/wavee/ — and within it architecture.md is the seam canon: the ports (ICatalogSource,
IEntityHydrator, IOnlineCatalog, the playback/remote/session/lyrics/mutation ports), the SourceRegistry /
AggregateCatalog federation, the ACL rule (no GraphQL/proto type crosses a port), the §9 status matrix and the
§10 file map. Start there for "where does this belong?".
Two pointers that used to conflict, now reconciled:
docs/plans/wavee-native-backend-architecture.mdis a different doc — the live Spotify backend (transport, dealer, session, audio). It does not supersedearchitecture.md; read it for wire/session questions.- Production comments across
Wavee.Core/Sources/**,App/**andFeatures/**citedocs/architecture.md, which does not exist. They meandocs/plans/wavee/architecture.md; the §-numbers still line up.
Hydration (every catalog metadata fetch in the app goes through one façade):
hydration.md is the how-to. Canon: docs/plans/wavee/hydration-facade-design.md (shapes),
hydration-facade-plan.md (phases + status), metadata-entry-points-inventory.md (what it replaced),
xm-kind-probe-overview.md + xm-playcount-handoff.md (which extension kind carries what).
What ships with it
13 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.
- audio-handoff.md 6.3 KB
- bridges.md 5.6 KB
- deep-linking.md 3.4 KB
- focus-pitfalls.md 2.2 KB
- home-layout.md 5.1 KB
- hydration.md 18 KB
- notifications.md 11 KB
- palette-shortcuts.md 4.5 KB
- playback-modules.md 6.7 KB
- receipts.md 2.5 KB
- session-restore.md 9.9 KB
- wavee-playlist-mutations/SKILL.md 29 KB
- wiring-discipline.md 1.9 KB
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.
- 4d ago First seen · 92 lines · 50 tokens per session scan A 2372e4805475
wavee is a skill published in the GitHub repository christosk92/WaveeMusic (50 stars, last pushed yesterday), licensed MIT. It adds 50 tokens to every session and 1,821 once invoked, about $0.0003 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
nunit-testing
Use when writing or modifying tests in NUnit's own test projects, or when making a behavioral change to production code that needs test coverage. Covers test structure, attribute choice, helper visibility, platform guards, and which test projects are real.
nunit-code-style
Use when writing or modifying C# method bodies, type declarations, or non-trivial logic in NUnit source. Covers NUnit's taste-and-judgment conventions — exception construction, simplification, naming intent, StringComparison, non-null check form, and var usage — that aren't already caught at build time.
opentelemetry-net-instrumentation
Provides guidance for implementing OpenTelemetry instrumentation in .NET codebases, covering tracing (Activities/Spans), metrics, logs, naming conventions, error handling, performance, SDK setup, resources, context propagation, and API design best practices.
community-research-insight
Extract structured insight briefs from community research transcripts or notes. Produces pain points, stakeholder needs, opportunity maps, risks, and follow-up questions. Requires human review before publication.
add-slice
Scaffold a slice in this Vertical Slice Architecture template — one use case in its own folder, with its FastEndpoints endpoint, request, response, validator, and summary, plus the Feature and Group if they don't exist yet, plus tests. Use when the user says "add a slice", "add a use case", "add an endpoint", "add a…
pr-independent-review
実装セッションと完全に独立したセッションでPRをレビューする手動発火スキル。PR URLまたは番号を受け取り、 レビュー専用worktreeにcheckoutして moores-code-review（report-only）＋新規性ゲートL1を実行し、 実コード抜粋入りのインフォグラフィックHTMLダイジェスト（verdict/裁定カード/suppressed）と シャドー台帳を出力する。ダイジェストの閲覧は裁定サイト（https://review.moores.tech/pr/ ）が担う。 実装セッションの自己申告contextは一切受け取らない。…