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 GuitarAlchemist/ga --skill voicing-searchgit clone --depth 1 https://github.com/GuitarAlchemist/gaWrote 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/guitaralchemist/ga/voicing-search)<a href="https://agentmods.dev/skills/guitaralchemist/ga/voicing-search"><img src="https://agentmods.dev/badge/skills/guitaralchemist/ga/voicing-search/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/guitaralchemist/ga/voicing-search"><img src="https://agentmods.dev/badge/skills/guitaralchemist/ga/voicing-search.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 | $0.00101 | $0.01814 |
| Opus 5 | $0.00051 | $0.00907 |
| Sonnet 5 | $0.00020 | $0.00363 |
| Haiku 4.5 | $0.00010 | $0.00181 |
Grade A, and why
voicing-search 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 9d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OPTIC-K Voicing Search
Retrieval over a 313,000-voicing corpus using musical geometry, not text embeddings. The index is a pre-built 112-dim OPTK v4 mmap file; similarity is weighted partition cosine across STRUCTURE (pitch-class invariants), MORPHOLOGY (fretboard geometry), CONTEXT (harmonic function), SYMBOLIC (technique/style tags), and MODAL (mode flavor) partitions.
When to Use
- User names a chord and wants playable fingerings: "show me Cmaj7 voicings", "drop-2 Dm7", "rootless G7 shapes".
- User asks for voicings in a mode or style: "Lydian on guitar", "jazz voicings", "shell voicings".
- User wants similar-sounding alternatives: "voicings with a similar quality to F#m7b5".
When NOT to Use
- Pure music theory questions ("what's a Lydian mode?") — use
TheoryAgentor theGaScaleByNametool. - Chord progression analysis ("what key is C-F-G?") — use
GaKeyFromProgression. - Purely descriptive queries without any chord/mode/tag ("something warm and dreamy"). The typed extractor returns empty; search yields arbitrary results. Ask the user to name a chord or style first.
How to Call
Before the first search this session, call ga_voicing_vocabulary once — it returns the canonical lists of modes, chord-quality suffixes, roots, and style/technique tags that the search tool understands. Cache the result for the rest of the session. When the user's query uses descriptive language ("warm", "jazzy", "moody") or non-canonical phrasing, map their words to the returned tags client-side before calling search. That keeps retrieval fully deterministic — the search tool has zero LLM dependency.
Example flow:
- User: "something jazzy in F minor for a ballad"
- You call
ga_voicing_vocabularyonce (if not yet cached). See "jazz" is a canonical tag. - You formulate
ga_search_voicings { query: "Fm jazz" }— canonical tokens only. - Retrieval returns Fm voicings ranked by OPTIC-K musical geometry + jazz-tag boost.
Canonical-form gotchas found in live testing (2026-04-18):
drop2does NOT match — usedrop-2-voicings(dashes, plural). Same fordrop-3-voicings.shellDOES substring-matchshell-voicing— partial match works on this one.rootlessis its own canonical tag (notrootless-voicing).- Register hints like
register:high,register:mid,register:lowexist and are useful for "voicings that sit high on the neck" type queries. - Many mood words ARE canonical:
dreamy,melancholy,bright,soulful,aggressive,tense,resonant,stable,sad. Callga_voicing_vocabularyonce to see the full list before guessing. - Famous-chord names are indexed:
hendrix-chord,mystic-chord,petrushka-chord,james-bond-chord,blackbird-chord,tristan-chord, etc.
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.
- 9d ago First seen · 111 lines · 101 tokens per session scan A 3e21e72709e1
voicing-search is a skill published in the GitHub repository GuitarAlchemist/ga (2 stars, last pushed today), licensed MIT. It adds 101 tokens to every session and 1,814 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…