What is CADCLAW AGENTS.md?

Instructions for CADCLAW, a tool that assembles and validates STEP files, which are standard 3D computer-aided-design models, along with bills of materials. They define what an AI agent may create or edit in CAD work.

Use them before changing CADCLAW geometry or assembly files. They guide assembly creation, validation, inventory and bill-of-material checks, and the required repository workflow.

They prevent the agent from inventing unauthorised geometry and require project-specific Git procedures before editing. This helps keep assemblies traceable and consistent with authored parts.

How sunnyday-technologies/CADCLAW configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to sunnyday-technologies/CADCLAW. 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/sunnyday-technologies/CADCLAW/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/sunnyday-technologies/CADCLAW

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/sunnyday-technologies/cadclaw/agents-md/github.svg)](https://agentmods.dev/instructions/sunnyday-technologies/cadclaw/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/sunnyday-technologies/cadclaw/agents-md"><img src="https://agentmods.dev/badge/instructions/sunnyday-technologies/cadclaw/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/sunnyday-technologies/cadclaw/agents-md"><img src="https://agentmods.dev/badge/instructions/sunnyday-technologies/cadclaw/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,753 This file is loaded in full into every session.

When invoked 1,753 The same file — it is already loaded in full.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5.1	$0.01753	$0.01753
Opus 5.5	$0.00701	$0.00701
Sonnet 5.5	$0.00351	$0.00351
Haiku 4.5	$0.00175	$0.00175

Measured 2mo ago against content hash 5b983912c1bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

CADCLAW 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 2mo 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 · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — guidance for AI assistants using CADCLAW

You are an AI assistant working inside (or on behalf of) a project that uses CADCLAW. This file is the load-bearing policy for how you should behave when adding or editing CAD geometry. Read it before any geometry-touching work.

Before editing this repository at all, read AGENTS_GIT_PROTOCOL.md. More than one agent works here from more than one clone. GitHub is the shared memory; your working copy is not. Fetch first, commit what you validate, never force-push.

What CADCLAW is, and what it is not

CADCLAW is an assembly and validation tool for STEP assemblies and BOMs. Two halves, both first-class:

Assemble. cadclaw assemble compiles a declarative assembly spec into a STEP file. It resolves authored STEP sources, seats each part by connector frames and datum chains (place_relative_to), and writes the assembly plus a design inventory, a model-derived BOM, review renders, and step-by-step build sequences.
Validate. It loads a STEP file and reports findings against rules in cadclaw.yaml: inventory, interference, adjacency, dimensions, orientation, floating, color, structural, tolerance, BOM-vs-CAD parity, claim-audit, publish-audit.

CADCLAW is not a CAD authoring system. It does not draw parts. It does not own bolt-circle constants, hole-drilling helpers, or NEMA mounting templates.

Hold this distinction precisely: assembling is in scope, authoring is not. Placing a part the user drew is CADCLAW's job. Creating that part's geometry is not. Do not describe CADCLAW as "only a validator" (it builds assemblies) or as a "CAD generator" (it never creates geometry).

The core rule: place authored parts, don't generate them

Default to placement, not generation. The user authors complex geometry in a native CAD package and exports a STEP. CADCLAW's own assembly compiler (cadclaw/assembly_compiler.py, driven by an assembly_spec.v0.1 YAML) then places copies of those authored parts into the assembly, and CADCLAW verifies the placement. An external CadQuery script still works, but the spec-driven compiler is the supported path.

Read the full file on GitHub · 170 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.

2mo ago First seen · 170 lines · 1,753 tokens per session scan A 5b983912c1bb

Subscribe to this mod's changes

CADCLAW AGENTS.md is an instructions file published in the GitHub repository sunnyday-technologies/CADCLAW (21 stars, last pushed 2d ago), licensed MIT. It adds 1,753 tokens to every session, about $0.0070 per session on Opus 5.5. 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.

3d-printing Design and UX cad cadquery interference-detection mcp-server mechanical-engineering

CADCLAW AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
CADCLAW AGENTS.mdsunnyday-technologies/CADCLAW	Instructions file	21	2d ago	MIT	A	1,753	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

CADCLAW: Instructions file for Codex