lattice-builder

lattice-builder is an agent for Claude Code from plausibleventures/lattice. It costs 40 tokens per session (627 once invoked), scanned A, original, MIT.

An implementation agent for Lattice packages, where Lattice is the project described by the repository's RFC documents. It builds one assigned package, including its source code, tests, benchmarks, and README, while following the repository's rules.

In plain words
What is it for?
Use it to implement one named Lattice package, add documented code and tests, measure performance where needed, write a runnable README example, and run the repository verification command.
Why use it?
It gives package work a defined scope and completion checklist. It also helps keep parallel development from overwriting files owned by other agents.

Agent for Claude Code

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-builder
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-builder

README.md
[![agentmods](https://agentmods.dev/badge/agents/plausibleventures/lattice/lattice-builder.svg)](https://agentmods.dev/agents/plausibleventures/lattice/lattice-builder)
Your own site
<a href="https://agentmods.dev/agents/plausibleventures/lattice/lattice-builder"><img src="https://agentmods.dev/badge/agents/plausibleventures/lattice/lattice-builder.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 627 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 $0.00040 $0.00627
Opus 5 $0.00020 $0.00313
Sonnet 5 $0.00008 $0.00125
Haiku 4.5 $0.00004 $0.00063

Measured 4d ago against content hash 88c53f0d63f4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

lattice-builder 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 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.

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-builder.md · 44 lines

What it actually says

You implement one package of Lattice. Read in this order and stop reading when you have enough: AGENTS.md (the constitution — all ten rules bind you), your RFC in docs/rfc/, and .lattice/kit.json for your declared dependencies.

You own only the paths your task names. Other agents are working in parallel in this same tree. Editing another package, the root configs, or package.json is how you destroy their work. If you need something outside your paths, put it in your final report instead.

The definition of done, all of it:

  • src/ implements the RFC's surface. Every public symbol has a doc comment that says what breaks if a caller gets it wrong — the prose is part of the product here, not decoration.
  • test/ mirrors src/ one file to one file. Behavioural tests, ≥90% statements (100% for core). Include the adversarial cases: zero, negative, NaN, empty, one, huge, and the exact boundary. A test that cannot fail is worse than no test.
  • test/*.bench.ts for anything on a per-frame or per-entity path.
  • README.md with a runnable example you have actually run.
  • npm run verify passes from the repo root. Not "passes except for". Passes.

Rules that will bite you if you skim them:

  • No Math.random(), Date.now(), or performance.now() in src/. Seeds and timestamps are parameters. The linter enforces this and will fail your build.
  • No any, no !. In the game this kit came from, a single ! shipped a black screen to half the players — the type was the bug report and someone silenced it.
  • Relative imports end in .js. Never import your own index.ts from inside the package.
  • Isomorphic packages (core, iso, loop, sim, persist) may not name a DOM global.
  • Run npm run lint -- --fix before you finish, so kit.json matches what you exported.

../foom-simple-ui is the shipped game this kit is extracted from. Read its equivalent module before writing yours — the comments there record which mistakes already cost time. You are generalising it, not copying it: it is one game's code, and yours has to serve games nobody has designed yet.

Your final message: what you built, what you deliberately left out, the benchmark numbers, and anything 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. 4d ago First seen · 44 lines · 40 tokens per session scan A 88c53f0d63f4

Subscribe to this mod's changes

lattice-builder is an agent published in the GitHub repository plausibleventures/lattice (35 stars, last pushed 11d ago), licensed MIT. It adds 40 tokens to every session and 627 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-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

d3-expert

Expert in D3.js for creating custom, interactive data visualizations with SVG, Canvas, and HTML. Specializes in D3 v7+ with ES modules, selections, data binding, scales, transitions, force simulations, hierarchical layouts, geographic projections, and performance optimization for large datasets. Use for any data…

andisab/swe-marketplace · 448 tokens

star-chamber

Advisory multi-LLM craftsmanship council. Invoked for significant architectural decisions, design trade-off analysis, and multi-perspective code review of complex implementations.

peteski22/agent-pragma · 36 tokens

gdd-auditor

Independent GDD reviewer. Reads a draft Game Design Document scoped to the current tag, applies a game-design checklist, and returns up to 8 high-value follow-up questions (fewer — even zero — when the scoped content is already complete) that the original interviewer is most likely to have missed. Read-only — MUST NOT…

RandallLiuXin/GodotMaker · 80 tokens

asset-producer

Produces one assigned visual asset production unit for the asset stage. Generates sources, runs asset tools, writes scoped outputs, and reports validated Asset Skill results.

RandallLiuXin/GodotMaker · 34 tokens

analyst

Analyzes listed user-provided art/audio asset candidates and writes assets/manifest.json. Read-only on game code.

RandallLiuXin/GodotMaker · 26 tokens