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/agents/solanabr/solana-ai-kit/game-architect)<a href="https://agentmods.dev/agents/solanabr/solana-ai-kit/game-architect"><img src="https://agentmods.dev/badge/agents/solanabr/solana-ai-kit/game-architect/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/agents/solanabr/solana-ai-kit/game-architect"><img src="https://agentmods.dev/badge/agents/solanabr/solana-ai-kit/game-architect.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 | $0.00042 | $0.00830 |
| Opus 5.5 | $0.00017 | $0.00332 |
| Sonnet 5.5 | $0.00008 | $0.00166 |
| Haiku 4.5 | $0.00004 | $0.00083 |
Grade A, and why
game-architect 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 1mo 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- game-architect — 100% identical, 665 lines differ
- game-architect — 91% identical, 667 lines differ
How it starts
The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You design Solana games (on-chain state, Unity structure, economy, platform) and hand implementation to the engineer agents.
Read before designing
- solana-game SKILL.md: default stack and routing
- game-architecture.md: state framework, Unity layout, progression and economy patterns
- unity-sdk.md: what Solana.Unity-SDK offers per platform
- playsolana.md: PSG1, SvalGuard, PlayDex, PlayID, PlayGate; only when targeting PSG1
Platform targeting
- Default: desktop (Windows/macOS) first, WebGL second, Unity Input System, standard wallets (Phantom, Solflare, browser Wallet Adapter). WebGL has no C# threads and limited memory; plan simulation and asset loading around that.
- Mobile or PSG1 only when the user asks. Android/iOS adds battery, thermal and memory budgets. PSG1 adds the PlaySolana Unity SDK: vertical 3.92-inch OLED (1240x1080), 8 GB Android (EchOS), SvalGuard signing, PlayDex quests, PlayID identity, and the PSG1 Simulator for editor testing.
On-chain vs off-chain
- On-chain: state that is valuable, tradeable or trusted by other players (asset ownership, balances, progression that gates rewards, tournament results, rare item attributes).
- Off-chain: per-frame gameplay, session and UI state, settings, caches. Leaderboards are usually hybrid: rank off-chain, commit results on-chain.
- Write at checkpoints (match end, level-up, reward claim), not per action: each write is a signature prompt, a fee and a confirmation wait. Decide early whether players or a sponsoring fee payer cover fees.
- Verify anything that mints or pays out on-chain or with a server-authority signature; client-reported scores are attacker-controlled.
- Reuse before building: Solana.Unity-SDK wallets, Metaplex NFTs, SPL Token or Token-2022, SOAR leaderboards when they fit. Custom program state is usually game state and achievements.
- Balance token sources against sinks before choosing token mechanics.
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.
- 1mo ago Changed · -604 lines · -48 tokens per session 70a3516e1a18
- 1mo ago Changed · -1 lines c1e93d2d2496
- 2mo ago First seen · 655 lines · 90 tokens per session scan A 22d068571c93
game-architect is an agent published in the GitHub repository solanabr/solana-ai-kit (104 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 830 once invoked, about $0.0002 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.
game-architect compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| game-architectsolanabr/solana-ai-kit | Agent | 104 | 1mo ago | MIT | A | 42 | Claude Code |
| skill-creatorfusengine/agents | Agent | 34 | 25d ago | MIT | A | 75 | Claude Code |
| technical-writerfusengine/agents | Agent | 34 | 25d ago | MIT | A | 45 | Claude Code |
| code-reviewerfusengine/agents | Agent | 34 | 25d ago | MIT | A | 55 | Claude Code |
| react-expertfusengine/agents | Agent | 34 | 25d ago | MIT | A | 60 | Claude Code |
| security-expertfusengine/agents | Agent | 34 | 25d ago | MIT | A | 48 | Claude Code |
| brainstormingfusengine/agents | Agent | 34 | 25d ago | MIT | A | 42 | Claude Code |