A command-line tool for running Guitar Alchemist’s music-theory language against its domain services. It can explore operations called closures and return results such as parsed chords or diatonic triads.

Use it to list available operations, parse and transpose chords, find the triads in a major or minor key, transpose progressions, and run language scripts.

It lets developers test music-theory operations interactively without building separate code or starting the full server stack.

GA Eval — Skill for Claude Code and Codex by GuitarAlchemist: A command-line tool for running Guitar Alchemist’s music-theory language…

Install

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.

agentmods

npx agentmods add skills/guitaralchemist/ga/eval

Any agent

npx skills add GuitarAlchemist/ga --skill eval

Clone the repo

git clone --depth 1 https://github.com/GuitarAlchemist/ga

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/guitaralchemist/ga/eval.svg)](https://agentmods.dev/skills/guitaralchemist/ga/eval)

Your own site

<a href="https://agentmods.dev/skills/guitaralchemist/ga/eval"><img src="https://agentmods.dev/badge/skills/guitaralchemist/ga/eval.svg" alt="Measured on agentmods" height="20"></a>

Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 960 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 2 findings. Scan, not verified.

Origin 94% copy Near-identical to another mod in the catalogue.

Token cost

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	$0.00041	$0.00960
Opus 5	$0.00020	$0.00480
Sonnet 5	$0.00008	$0.00192
Haiku 4.5	$0.00004	$0.00096

Measured 4d ago against content hash 63df78012302, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

GA Eval scanned grade B with 2 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.

Unrestricted tool accessmediumExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

# Run any command

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s -X POST http://localhost:5232/api/ga/eval \

Origin

This is a copy

94% identical to GA Language Evaluator — 6 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.agent/skills/ga/eval/SKILL.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/ga eval — GA Language Evaluator

Use this sub-command when the user asks to run a GAL script, test a closure, or explore the GA DSL interactively.

When to Use

"What does domain.diatonicChords return for E minor?"
"List all available closures"
"Run this closure and show me the result"
"Test whether this chord symbol parses correctly"

CLI (primary — no server needed for domain closures)

The GaCli project (Apps/GaCli) calls domain closures directly in-process. No Aspire stack required.

# From repo root — build once, then use the binary directly
dotnet build Apps/GaCli/GaCli.fsproj -c Debug -v q

# Run any command
dotnet run --project Apps/GaCli/GaCli.fsproj -- <command>

Commands

ga closures [domain|pipeline|agent|io]   List closures (optionally filtered by category)
ga chord <symbol>                         Parse a chord symbol → JSON structure
ga transpose <symbol> <semitones>         Transpose a chord by N semitones
ga diatonic <root> [major|minor]          Get the 7 diatonic triads for a key
ga progression <sym...> --by <n>          Transpose every chord in a progression
ga ask <question>                         Ask the GA chatbot (requires server running)

Examples

dotnet run --project Apps/GaCli/GaCli.fsproj -- closures
dotnet run --project Apps/GaCli/GaCli.fsproj -- chord Am7
dotnet run --project Apps/GaCli/GaCli.fsproj -- transpose Cmaj9 5
dotnet run --project Apps/GaCli/GaCli.fsproj -- diatonic G major
dotnet run --project Apps/GaCli/GaCli.fsproj -- progression Am F C G --by 7

Available Closures (quick reference)

Name	Inputs	Output
`domain.parseChord`	`symbol: string`	JSON chord structure
`domain.transposeChord`	`symbol: string`, `semitones: int`	transposed chord symbol
`domain.diatonicChords`	`root: string`, `scale: string`	string[] of 7 triads
`agent.theoryAgent`	`question: string`	GA chatbot answer
`agent.tabAgent`	`request: string`	tab or VexTab string
`agent.criticAgent`	`progression: string`	harmonic critique
`agent.fanOut`	`question: string`, `agentNames: string[]`	Map of answers
`io.readFile`	`path: string`	file contents
`io.writeFile`	`path: string`, `content: string`	unit
`io.httpGet`	`url: string`	response body
`io.httpPost`	`url: string`, `body: string`	response body

Read the full file on GitHub · 84 lines

Changes

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 · 84 lines · 41 tokens per session scan B 63df78012302

Subscribe to this mod's changes

GA Eval is a skill published in the GitHub repository GuitarAlchemist/ga (2 stars, last pushed today), licensed MIT. It adds 41 tokens to every session and 960 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 2 findings (unrestricted tool access, makes network calls). It is 94% identical to GA Language Evaluator, differing in 6 lines, and is treated as a copy.

Creative and media Testing

general-video

Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…

heygen-com/hyperframes · 92 tokens

GA Eval