cad-cae-copilot: Instructions file for Codex

AGENTS.md

cad-cae-copilot AGENTS.md is an instructions file for Codex, OpenCode from armpro24-blip/cad-cae-copilot. It costs 40,391 tokens per session, scanned A, original, MIT.

A set of instructions for the aieng workbench, a tool for creating and inspecting computer-aided design and engineering geometry. It explains the approved tools, project workflow, and fallback options for agents.

In plain words
What is it for?
It helps agents start work, load project guidance and context, create geometry with build123d, import STEP files, and follow the workspace's modeling workflow.
Why use it?
It prevents agents from learning the system from an outdated stub and helps them use the live workbench or the documented fallback when its tools are unavailable.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions CLAUDE.md; names the AskUserQuestion tool; mentions Claude Code.

This is armpro24-blip/cad-cae-copilot's own configuration. It tells Codex and OpenCode how to work on cad-cae-copilot itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything cad-cae-copilot configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is python agent_import_project.py ../../output/result.step \.

Reuse

Borrowing it

Nothing to install: this file belongs to armpro24-blip/cad-cae-copilot. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/armpro24-blip/cad-cae-copilot/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/armpro24-blip/cad-cae-copilot

Made for: Codex, OpenCode.

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 cad-cae-copilot AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/armpro24-blip/cad-cae-copilot/agents-md.svg)](https://agentmods.dev/instructions/armpro24-blip/cad-cae-copilot/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/armpro24-blip/cad-cae-copilot/agents-md"><img src="https://agentmods.dev/badge/instructions/armpro24-blip/cad-cae-copilot/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 40,391 This file is loaded in full into every session.
When invoked 40,391 The same file — it is already loaded in full.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.40391 $0.40391
Opus 5 $0.20196 $0.20196
Sonnet 5 $0.08078 $0.08078
Haiku 4.5 $0.04039 $0.04039

Measured today against content hash db3b39e31fb8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

cad-cae-copilot AGENTS.md scanned grade A with 1 finding 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 today.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -X POST http://localhost:8000/api/agent/invoke-tool \
AGENTS.md · 2,535 lines

How it starts

The opening of the file, as written. The whole thing — 2,535 lines — stays where its author put it; the contents beside it link to each section on GitHub.

aieng Workbench — Agent Guide

Canonical detailed guide for any AI agent (Claude Code, GitHub Copilot, OpenAI Codex, Cursor, Cline, …) working in this workspace. This is the single source of truth for detailed guidance — CLAUDE.md and .github/copilot-instructions.md point here. The MCP tool aieng.agent_readme returns a compact operational quickstart by default; aieng.guide {topic} extracts detailed sections from this file, and aieng.agent_readme {detail: "full"} returns the complete document.


STOP — read this first

Do NOT browse aieng/src/ to understand what this system can do. That is a legacy library with a FakeBackend stub that produces no real geometry.

The workbench is driven primarily through the aieng-workbench MCP server tools. If you see aieng.* / cad.* / cae.* tools in your tool list, use them — they provide live UI events, topology feedback, and incremental modeling.

If you do NOT have these MCP tools (e.g. Kimi Code CLI without MCP configuration), you are in fallback mode. You can still produce geometry by:

  1. Writing build123d scripts and running them through the provided runner script.
  2. Importing the resulting STEP file into the workbench with the provided importer script so it appears in the UI. See the Fallback mode section below for the exact commands.

If the aieng-workbench MCP server is not in your tool list, it is configured in this repo (.mcp.json for Claude Code, .vscode/mcp.json for VS Code/Copilot, see MCP_SETUP for Codex, and see Kimi Code CLI notes in the Fallback section).


First three calls every session

1. aieng.agent_readme                   → compact operational quickstart
2. aieng.list_projects                  → discover available project IDs
3. aieng.agent_context { project_id }   → geometry state, pointers, next steps

Call these before reading files or running code. aieng.agent_context gives you the current geometry state, stale-artifact warnings, and the pointer IDs you need to construct valid tool calls. Call aieng.guide {topic} only when the current task needs detailed guidance; use aieng.agent_readme {detail: "full"} only when the complete canonical guide is genuinely required.

Read the full file on GitHub · 2,535 lines

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. today Changed · +270 lines · +4,859 tokens per session db3b39e31fb8
  2. yesterday Changed · +45 tokens per session b3fcd17e92e1
  3. 4d ago Changed · +110 lines · +2,037 tokens per session e43ad6e4d8f5
  4. 8d ago First seen · 2,155 lines · 33,450 tokens per session scan A f1e4359c4d32

Subscribe to this mod's changes

cad-cae-copilot AGENTS.md is an instructions file published in the GitHub repository armpro24-blip/cad-cae-copilot (57 stars, last pushed today), licensed MIT. It adds 40,391 tokens to every session, about $0.2020 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens