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.
npx agentmods add instructions/icecreamyou/three.terrain/agents-mdgit clone --depth 1 https://github.com/IceCreamYou/THREE.TerrainWrote 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/instructions/icecreamyou/three.terrain/agents-md)<a href="https://agentmods.dev/instructions/icecreamyou/three.terrain/agents-md"><img src="https://agentmods.dev/badge/instructions/icecreamyou/three.terrain/agents-md.svg" alt="Measured on agentmods" 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 | $0.00551 | $0.00551 |
| Opus 5 | $0.00275 | $0.00275 |
| Sonnet 5 | $0.00110 | $0.00110 |
| Haiku 4.5 | $0.00055 | $0.00055 |
Grade A, and why
THREE.Terrain AGENTS.md 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 5d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Process
This file defines the process for changes in this repository. It does not document library functions. Read llms.txt for library usage and API information.
Repository areas
src/contains the library source.demo/contains the interactive terrain demo and its local assets.scripts/contains build, vendor, and screenshot tools.vendor/contains browser files required by static hosting.dist/contains generated library bundles.README.md,llms.txt, andSKILL.mdcontain documentation.
Do not hand-edit files in dist/.
Run npm run build to generate library bundles.
Treat files in vendor/ as imported or generated files; do not change them manually.
Run npm run vendor after a dependency update.
Run npm run build:eztree after a change to the vendored eztree source.
Preserve the license files for all vendored dependencies.
Keep API descriptions and usage examples in llms.txt and the README.
Keep agent workflow instructions in this file.
Keep those three files up to date when relevant changes are made.
Randomness
Use the seeded randomness utilities rather than Math.random.
Generate a random seed on each run if no seed is supplied.
Use an explicit seed when you need to reproduce a demo result.
Demo changes
Start the demo with npm start for manual checks.
Use a URL with a seed when you compare terrain or decoration changes.
Use scripts/capture-readme-screenshots.mjs to update README images after substantial changes to the demo.
Do not add test controls, debug overlays, or test-only URL behavior to the shipped demo.
For visual changes, inspect the result at the camera positions that the change affects. Check the result after a window resize.
Codex has a known bug where it fails to start Chrome in its sandbox. If this affects you, use Playwright instead.
Validation
Run these commands after source, demo, or build changes:
npm run build
git diff --check
Run npm run screenshots -- --output-dir /tmp/three-terrain-screenshots after screenshot or camera changes.
Inspect every generated image before you replace a README image.
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.
- 5d ago First seen · 66 lines · 551 tokens per session scan A 5b27d2501d79
THREE.Terrain AGENTS.md is an instructions file published in the GitHub repository IceCreamYou/THREE.Terrain (892 stars, last pushed 8d ago), licensed MIT. It adds 551 tokens to every session, about $0.0028 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.
Other instructions, from other repositories
appwrite AGENTS.md
AGENTS.md instructions for appwrite/appwrite, covering appwrite, commands, stack, layout and libraries.
qiankun AGENTS.md
Instructions for umijs/qiankun, covering qiankun project knowledge base, structure, architecture (big picture), commands and build (vite 8 → package javascript; tsc → declarations).
joint CLAUDE.md
Claude Code instructions for clientIO/joint, covering claude.md, project overview, common commands, install dependencies and build distribution files (runs grunt).
qiankun CLAUDE.md
Instructions for umijs/qiankun: This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
ai AGENTS.md
AGENTS.md instructions for vercel/ai, covering agents.md, project overview, repository structure, key directories and core package dependencies.
Claw3D AGENTS.md
Instructions for iamlukethedev/Claw3D, covering agent instructions, cursor cloud specific instructions, service overview, running the app and lint, typecheck, and tests.