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.
git clone --depth 1 https://github.com/solanabr/solana-ai-kitWrote 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/commands/solanabr/solana-ai-kit/build-unity)<a href="https://agentmods.dev/commands/solanabr/solana-ai-kit/build-unity"><img src="https://agentmods.dev/badge/commands/solanabr/solana-ai-kit/build-unity/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/commands/solanabr/solana-ai-kit/build-unity"><img src="https://agentmods.dev/badge/commands/solanabr/solana-ai-kit/build-unity.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 | $0.00017 | $0.00697 |
| Opus 5.5 | $0.00007 | $0.00279 |
| Sonnet 5.5 | $0.00003 | $0.00139 |
| Haiku 4.5 | $0.00002 | $0.00070 |
Grade A, and why
build-unity 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 25d 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 — 23 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build the Unity project for the target in $ARGUMENTS: webgl (default), win64, osx, android or psg1. References: solana-game SKILL.md, unity-sdk.md (wallet login per platform), playsolana.md (PSG1 build configuration).
Steps
- Find the editor for the version in
ProjectSettings/ProjectVersion.txt: macOS/Applications/Unity/Hub/Editor/<version>/Unity.app/Contents/MacOS/Unity, WindowsC:\Program Files\Unity\Hub\Editor\<version>\Editor\Unity.exe, Linux~/Unity/Hub/Editor/<version>/Editor/Unity. Theunity-editorcommand exists only in GameCI images. - Check that
Packages/manifest.jsonlistscom.solana.unity-sdk(pluscom.playsolana.sdkfor PSG1) and that the target's platform module (WebGL or Android Build Support) is installed. - Use
Assets/Editor/BuildScript.csif it exists. Otherwise create it with one static method per target that builds the enabled scenes fromEditorBuildSettings.scenesintoBuild/<Platform>/and callsEditorApplication.Exit(1)whenreport.summary.result != BuildResult.Succeeded. Without that call, batchmode exits 0 on a failed build. - Run
<Unity> -quit -batchmode -nographics -projectPath . -buildTarget <target> -executeMethod BuildScript.<Method> -logFile build.log(-logFile -streams to stdout). CLI target names areWebGL,Win64,OSXUniversal,Linux64andAndroid, unlike the C# enum (BuildTarget.StandaloneWindows64,BuildTarget.StandaloneOSX). On failure, searchbuild.logforerror CSand the build report errors. - PSG1 builds for Android: ARM64 only (which requires the IL2CPP backend), minimum API level 30, portrait orientation (1080x1240), Vulkan plus GLES3, package ID
com.playsolana.games.<game>, and thePLAYSOLANA_PSG1scripting define. Set these in the build method; playsolana.md has the settings snippet. Add PSG1 code paths only when the user targets PSG1.
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.
- 25d ago Changed · -354 lines · +4 tokens per session 77c8124f4595
- 1mo ago First seen · 377 lines · 13 tokens per session scan A a8a535379a0f
build-unity is a command published in the GitHub repository solanabr/solana-ai-kit (104 stars, last pushed 26d ago), licensed MIT. It adds 17 tokens to every session and 697 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
apex
APEX Methodology - The systematic Analyze-Plan-Execute-eLicit-eXamine approach for intelligent development. Reduces hallucination and defect risk through mandatory parallel research, self-review, and validation gates.
explain-architecture
Analyze and explain software architecture with ASCII diagrams and pattern detection. Creates visual representations of system design.
db-migrate
You are a database migration expert specializing in zero-downtime deployments, data integrity, and multi-database environments. Create comprehensive migration scripts with rollback strategies, validation checks, and performance optimization.
plan-feature
Production-grade feature planning with dual-AI validation (Claude + Antigravity/Gemini 3 via agy).
generate-tests
Begin by outputting: [ Manta — Generate Tests ].
pre-push-review
Begin by outputting: [ Manta — Pre-Push Review ].