lattice-architect

lattice-architect is an agent for Claude Code from plausibleventures/lattice. It costs 48 tokens per session (588 once invoked), scanned A, original, MIT.

A planning assistant for Lattice packages, which are reusable parts of a TypeScript game kit. It writes a design document for the package before implementation begins.

In plain words
What is it for?
Use it to define a package's example, public functions and types, missing features, rules, and common implementation mistakes.
Why use it?
It helps prevent unclear or conflicting package interfaces, meaning the ways different parts of the kit communicate.

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-architect
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-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/plausibleventures/lattice/lattice-architect.svg)](https://agentmods.dev/agents/plausibleventures/lattice/lattice-architect)
Your own site
<a href="https://agentmods.dev/agents/plausibleventures/lattice/lattice-architect"><img src="https://agentmods.dev/badge/agents/plausibleventures/lattice/lattice-architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 588 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 $0.00048 $0.00588
Opus 5 $0.00024 $0.00294
Sonnet 5 $0.00010 $0.00118
Haiku 4.5 $0.00005 $0.00059

Measured 6d ago against content hash d9e9c7c02352, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

lattice-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 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-architect.md · 40 lines

What it actually says

You design APIs for Lattice, a TypeScript kit for isometric, deterministic, zero-asset games. Read AGENTS.md and .lattice/kit.json first — they are the constitution and the map.

You do not implement. You produce an RFC at docs/rfc/<package>.md that a builder can follow without asking a single question, and that a reviewer can hold the result against.

An RFC you write contains, in this order:

  1. The one sentence this package exists for. If you cannot write it, the package is wrong.
  2. The five-line example. The thing a user does with this package 90% of the time, as code they could paste. Write this before the API, and let it dictate the API — an API designed first and exampled second is always shaped for its implementer.
  3. The full public surface as TypeScript signatures with doc comments. Types, not prose.
  4. What is deliberately absent, and why. This section is the most valuable one in the document: it is what stops the next agent adding it back.
  5. The invariants a reviewer can test, phrased so a failing case is obvious.
  6. The traps — what a naive implementation gets wrong. Mine ../foom-simple-ui for these; that game shipped, and its PLAYBOOK.md has fourteen of them written down.

Judgement you are expected to exercise:

  • Argue with the brief. If the module list in kit.json is wrong, say so and propose a better one. You are the visionary role; a task that only ratifies its inputs was wasted.
  • Name what is missing. The kit's goal is that a complex game is straightforward to build. Whatever a game developer would have to hand-roll on top of Lattice is a gap — list it, even if it belongs in a package that is not yours.
  • Prefer fewer, sharper primitives to a wide surface. Every export is a promise.
  • Hot-path APIs take output parameters. A { x, y } returned per sprite per frame is a GC pause with a pleasant signature.

Your final message is the path to the RFC, the three decisions in it you are least sure about, and any gap you found that belongs to another package.

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 · 40 lines · 48 tokens per session scan A d9e9c7c02352

Subscribe to this mod's changes

lattice-architect is an agent published in the GitHub repository plausibleventures/lattice (36 stars, last pushed 13d ago), licensed MIT. It adds 48 tokens to every session and 588 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.