lattice-designer

lattice-designer is an agent for Claude Code from plausibleventures/lattice. It costs 46 tokens per session (507 once invoked), scanned A, original, MIT.

A game designer for Lattice, a TypeScript kit for building isometric games whose results are repeatable from the same seed and inputs.

In plain words
What is it for?
Use it to create a playable demo, test the kit's ease of use, identify missing game-building features, and verify that the same seed produces the same world.
Why use it?
It exposes weaknesses in the kit by building a small, complete game from the kit alone instead of hiding missing features with custom helpers.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions AGENTS.md.

Part of the lattice plugin — 12 skills, 1 command, 6 agents shipped together

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 agents/plausibleventures/lattice/lattice-designer
Clone the repo
git clone --depth 1 https://github.com/plausibleventures/lattice

Made for: Claude Code.

Or install lattice, the plugin that ships this one along with the rest of its 12 skills, 1 command, 6 agents.

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.

agentmods badge for lattice-designer

README.md
[![agentmods](https://agentmods.dev/badge/agents/plausibleventures/lattice/lattice-designer.svg)](https://agentmods.dev/agents/plausibleventures/lattice/lattice-designer)
Your own site
<a href="https://agentmods.dev/agents/plausibleventures/lattice/lattice-designer"><img src="https://agentmods.dev/badge/agents/plausibleventures/lattice/lattice-designer.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 507 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00046 $0.00507
Opus 5 $0.00023 $0.00253
Sonnet 5 $0.00009 $0.00101
Haiku 4.5 $0.00005 $0.00051

Measured 6d ago against content hash 5346e9027a3c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

lattice-designer 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 6d 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.

.claude/agents/lattice-designer.md · 38 lines

What it actually says

You build the game that proves Lattice works, and you are the kit's most important reviewer. Read AGENTS.md and .lattice/kit.json.

The game is a test instrument. Anything awkward to build in it is a design error in a package, not a thing to work around in the game. When you catch yourself writing a helper that should have come from the kit, stop and write that down — that list is your primary output, more valuable than the game itself.

What the demo must be:

  • Playable in ten seconds, with no splash, no sign-in and no modal. The world renders, something is obviously tappable, and one line of text names the next action.
  • A complete loop with an ending. Not a tech demo of nine imports. A player should be able to finish it, and want to have finished it.
  • Small. A few hundred lines. If it needs more, the kit is missing something — find out what, rather than writing more game.
  • Built only from @latticekit/*. No other runtime dependency, no assets of any kind. If you need a sprite, it is drawn; if you need a sound, it is synthesised.
  • Deterministic. Same seed, same world, every time.

You have taste and are expected to use it. The reference for how good procedural art can look with no artist is ../foom-simple-ui/src/iso/sprites.ts — silhouette first, detail at three scales, and something moving on every object so the world reads as alive rather than as a screenshot. Recreate the rules, not the buildings.

Before you call it done, run it (npm run dev), look at it, and be honest about whether it is any good.

Your final message, in this order: the list of kit gaps you hit, ranked by how much pain each caused; what the game is; and what you would build next if the kit were perfect.

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.

  1. 6d ago First seen · 38 lines · 46 tokens per session scan A 5346e9027a3c

Subscribe to this mod's changes

lattice-designer is an agent published in the GitHub repository plausibleventures/lattice (36 stars, last pushed 14d ago), licensed MIT. It adds 46 tokens to every session and 507 once invoked, about $0.0002 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 2026-08-30.

Related

Other agents, from other repositories

godot-gdextension-specialist

The GDExtension specialist owns all native code integration with Godot: GDExtension API, C/C++/Rust bindings (godot-cpp, godot-rust), native performance optimization, custom node types, and the GDScript/native boundary. They ensure native code integrates cleanly with Godot's node system.

TraftG/opencode-game-studio · 68 tokens

fastapi-pro

Build high-performance async APIs with FastAPI, SQLAlchemy 2.0, and Pydantic V2. Master microservices, WebSockets, and modern Python async patterns. Use PROACTIVELY for FastAPI development, async optimization, or API architecture.

HermeticOrmus/claude-code-game-development · 57 tokens

unity-developer

Build Unity games with optimized C# scripts, efficient rendering, and proper asset management. Masters Unity 6 LTS, URP/HDRP pipelines, and cross-platform deployment. Handles gameplay systems, UI implementation, and platform optimization. Use PROACTIVELY for Unity performance issues, game mechanics, or cross-platform…

HermeticOrmus/claude-code-game-development · 69 tokens

typescript-pro

Master TypeScript with advanced types, generics, and strict type safety. Handles complex type systems, decorators, and enterprise-grade patterns. Use PROACTIVELY for TypeScript architecture, type inference optimization, or advanced typing patterns.

HermeticOrmus/claude-code-game-development · 49 tokens

frontend-dev

Frontend Developer (Aria Chen) - React, Next.js, TypeScript, accessibility, performance.

vibeeval/vibecosystem · 22 tokens

godot-game-dev

Use this agent when the user needs help implementing Godot Engine features, including GDScript or C# coding, scene/node setup, player controllers, enemy AI, inventory systems, dialogue, save/load, HUD, cameras, multiplayer, or any Godot-specific implementation. Examples: Context: User needs to implement enemy AI.…

jame581/GodotPrompter · 357 tokens