agentmods.dev

chisel AGENTS.md

A set of contributor instructions for Chisel, a server that lets AI agents create, edit, render, and export 3D models.

In plain words
What is it for?
Use it when working on Chisel’s 3D scene graph, modeling operations, rendering, file export, MCP server, or browser playground.
Why use it?
It gives developers the project’s file locations, conventions, and commands so changes fit the existing code and model behavior.

Instructions file for CodexOpenCode

6 2mo ago A scan 399 tokens original MIT
View the source file EYamanS/chisel
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 instructions/eyamans/chisel/agents-md
Clone the repo
git clone --depth 1 https://github.com/EYamanS/chisel

Made for: Codex, OpenCode.

Per session 399 This file is loaded in full into every session.
When invoked 399 The same file — it is already loaded in full.
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 $0.00399 $0.00399
Opus 5 $0.00199 $0.00199
Sonnet 5 $0.00080 $0.00080
Haiku 4.5 $0.00040 $0.00040

Measured 2d ago against content hash 8286b7d8d71c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

chisel 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 2d 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.

AGENTS.md · 32 lines

What it actually says

Chisel — contributor guide

Chisel is an MCP server (plus an optional Next.js web playground) that lets AI agents build, edit, render, and export 3D models from primitives and boolean CSG.

Where things live

  • src/lib/scene/ — the scene graph (types.ts), the deterministic op reducer (operations.ts), and the shared modeling tool schemas (tools.ts).
  • src/lib/three/build.ts — turns the scene graph into Three.js meshes, evaluating CSG booleans with three-bvh-csg. Pure CPU; no GPU needed.
  • src/lib/render/ — the headless software rasterizer (raster.ts), glTF/OBJ export (export.ts), a zero-dependency PNG encoder (png.ts), and a bitmap label font.
  • src/mcp/ — the MCP server (server.ts) and its in-memory session store (engine.ts).
  • src/lib/agent/, src/components/, src/app/ — the browser playground (WebGL viewport
    • OpenAI-driven agent loop).

Conventions

  • Geometry is Y-up, right-handed. Rotations are stored in degrees.
  • The renderer and exporters must stay headless (no window, no WebGL) — they run in Node for the MCP server.
  • The same src/lib/scene/tools.ts schemas feed both the MCP server and the web agent; keep them in sync.

Commands

  • npm run mcp — run the MCP server from source (tsx).
  • npm run build:mcp — bundle the standalone binary to dist/server.js.
  • npm run dev — web playground at http://localhost:3000.
  • npx tsc --noEmit — typecheck the whole project.
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. 2d ago First seen · 32 lines · 399 tokens per session scan A 8286b7d8d71c

Subscribe to this mod's changes

chisel AGENTS.md is an instructions file published in the GitHub repository EYamanS/chisel (6 stars, last pushed 2mo ago), licensed MIT. It adds 399 tokens to every session, about $0.0020 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 2026-08-31.

3d3d-graphics3d-modeling3d-modelsBrowser automationai-agentclaude
Related

Other instructions, from other repositories

eye AGENTS.md

Instructions for suvadityamuk/eye, covering agents.md — ai agent reference for eye, architecture, key files, src/js/app.js and src/js/scene-manager.js.

suvadityamuk/eye · 1,501 tokens

Browser4 CLAUDE.md

Instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.

platonai/Browser4 · 1,205 tokens

sceneview AGENTS.md

Instructions for sceneview/sceneview, covering agents.md — conventions for delegated coding agents, your role, git — you do not own it, secrets and hard technical rules.

sceneview/sceneview · 1,086 tokens

Paperlab AGENTS.md

Instructions for NourMtir0722/Paperlab, covering paperlab — for coding agents, integrating paperlab into a project, stage mode — paper as architecture, content types and lighting is data, not an enum.

NourMtir0722/Paperlab · 7,216 tokens

cad-cae-copilot copilot-instructions.md

Instructions for armpro24-blip/cad-cae-copilot, covering github copilot — aieng workspace and essentials.

armpro24-blip/cad-cae-copilot · 323 tokens

deepseekCLI CLAUDE.md

Instructions for cynchro/deepseekCLI, covering tarea actual, progreso, decisiones clave, próximos pasos and contexto importante.

cynchro/deepseekCLI · 1,728 tokens