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 skills add P47Phoenix/Claude-Plugins --skill adaptergit clone --depth 1 https://github.com/P47Phoenix/Claude-PluginsWrote 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/p47phoenix/claude-plugins/adapter)<a href="https://agentmods.dev/skills/p47phoenix/claude-plugins/adapter"><img src="https://agentmods.dev/badge/skills/p47phoenix/claude-plugins/adapter/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/p47phoenix/claude-plugins/adapter"><img src="https://agentmods.dev/badge/skills/p47phoenix/claude-plugins/adapter.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00159 | $0.03136 |
| Opus 5.5 | $0.00064 | $0.01254 |
| Sonnet 5.5 | $0.00032 | $0.00627 |
| Haiku 4.5 | $0.00016 | $0.00314 |
Grade A, and why
adapter 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 2d 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 — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.
adapter
Design Principle: Two Genres, One Role
Adapting a song needs the source genre and the target genre in context at the same time, which no
other music-team role needs. This skill keeps adaptation craft out of the main context: it detects
the role, reads only the matched manifest, one output contract, both genre profiles and at most two
techniques, then spawns one sub-agent per role. The main context receives the finished artifact and a
one-sentence summary. Craft lives in references/, never here.
The adapter keeps what makes the song itself (hook, title, melody contour, lyric meaning, point of
view, key images) and remaps what makes it sound like a genre (feel, tempo band, harmony, form,
instrumentation, diction register). It never adds new meaning and never imports a line from any
existing song. Originality policy clauses 1, 2, 4 and 5 apply
(music-team/references/shared/originality-policy.md).
Phase 1: Detection
Detection is cheap pattern work; run it on phase_1_detector_model (haiku) when delegated.
1. Roles from what the user supplied
| Supplied input | Role(s) | Order |
|---|---|---|
| Lyric only | lyric-adapter |
single call |
| Chords and/or melody only (no lyric) | music-adapter |
single call |
| Lyric and chords/melody | lyric-adapter, then music-adapter |
two sequential Agent calls, one role each |
| Arrangement or production notes only | music-adapter (task arrangement-adapt) |
single call |
| "what would change if this were " | the role the input matches, task adaptation-report only; write nothing else |
single call |
One role is one Agent call; never put two ROLE: lines in one prompt. When ambiguous, ask once.
2. Genres
source_genre: from the brief, the request, or the input itself. If absent or unclear, ask. Do not guess.target_genre: must resolve to a profile inmusic-team/references/shared/genres/<slug>.mdthrough itsgenre:oraliases:front-matter (for example "bossa" and "bossa nova" resolve tobossa-nova).- A target that is a named artist, band or song, "in the style of ", "to the tune of", or an entry in
blocked-targets.txt: refuse with exactly the sentence under "PARODY_ADAPT refusal" inmusic-team/references/shared/song-types.md. Create nothing. - A genre with no profile: say which profiles exist and ask the user to pick the nearest one. Do not improvise a profile.
What ships with it
10 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.
- references/contracts/adaptation-report.md 3.1 KB
- references/contracts/arrangement-adapt-output.md 2.5 KB
- references/contracts/cross-role-tasks.md 3.0 KB
- references/contracts/lyric-adapt-output.md 2.5 KB
- references/contracts/music-adapt-output.md 2.7 KB
- references/roles/lyric-adapter.md 4.0 KB
- references/roles/music-adapter.md 4.6 KB
- references/techniques/feel-conversion.md 2.9 KB
- references/techniques/lyric-refit.md 3.4 KB
- references/techniques/reharmonization-moves.md 3.6 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.
- 2d ago First seen · 276 lines · 159 tokens per session scan A 06e665d95717
adapter is a skill published in the GitHub repository P47Phoenix/Claude-Plugins (2 stars, last pushed 2d ago), licensed MIT. It adds 159 tokens to every session and 3,136 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-10-26.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…