techdrawai-drafting

techdrawai-drafting is a skill for Claude Code, Codex from MeltFlexDevs/techdrawai-skills. It costs 87 tokens per session (1,473 once invoked), scanned A, original, MIT.

A skill that turns a photograph of a physical object into a dimensioned 2D technical drawing. Such drawings show measured views and details used for engineering, production, or repair.

In plain words
What is it for?
Use it to create engineering, shop, assembly, patent, orthographic, as-built, or dimensioned part drawings.
Why use it?
It provides a structured working drawing from a photo, with space for real measurements or estimated dimensions.

Skill for Claude CodeCodex

Part of the techdrawai plugin — 2 skills, 1 MCP server 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 skills/meltflexdevs/techdrawai-skills/techdrawai-drafting
Any agent
npx skills add MeltFlexDevs/techdrawai-skills --skill techdrawai-drafting
Clone the repo
git clone --depth 1 https://github.com/MeltFlexDevs/techdrawai-skills

Made for: Claude Code, Codex.

Or install techdrawai, the plugin that ships this one along with the rest of its 2 skills, 1 MCP server.

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 techdrawai-drafting

README.md
[![agentmods](https://agentmods.dev/badge/skills/meltflexdevs/techdrawai-skills/techdrawai-drafting.svg)](https://agentmods.dev/skills/meltflexdevs/techdrawai-skills/techdrawai-drafting)
Your own site
<a href="https://agentmods.dev/skills/meltflexdevs/techdrawai-skills/techdrawai-drafting"><img src="https://agentmods.dev/badge/skills/meltflexdevs/techdrawai-skills/techdrawai-drafting.svg" alt="Measured on agentmods" height="20"></a>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,473 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 $0.00087 $0.01473
Opus 5 $0.00044 $0.00737
Sonnet 5 $0.00017 $0.00295
Haiku 4.5 $0.00009 $0.00147

Measured 4d ago against content hash 7166ab08ecd4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

techdrawai-drafting 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.

skills/techdrawai-drafting/SKILL.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TechDraw AI: drafting from a photograph

Turns a photograph of a physical object into a dimensioned, standards-compliant 2D technical drawing. For DXF and DWG export, 3D reconstruction and product renders, use the techdrawai-cad skill on whatever this one writes.

Setup (once)

npx -y techdrawai-mcp auth login      # browser sign-in, no key to copy

Requires an active Studio plan. If a tool reports a plan error, say so plainly and point at https://techdrawai.com/app?view=subscription rather than retrying. Keys can also be created in Settings and passed as TECHDRAWAI_API_KEY.

Tools

generate_technical_drawing

Photo to dimensioned technical drawing. 3 credits.

  • image (required): the photo, as a local file path, an http(s) URL or a data URL.
  • product_name: what the object is. Improves the title block and, when dimensions are estimated, the estimates themselves. Run identify_product first if you do not know.
  • measurements: dimensions the user actually measured, each { value, unit?, orientation?, position? }. The single biggest quality lever. See below.
  • estimate_dimensions: let the model infer sizes. Defaults to true when no measurements are given.
  • units: mm (default), cm, m, in.
  • standard: ISO (default) or ANSI.
  • paper_size: A4 to A0 for ISO (default A3), ANSI A to ANSI E for ANSI (default ANSI B).
  • projection: first-angle (default, ISO and Europe) or third-angle (ANSI and North America).
  • drawing_type: working (default, fully dimensioned production drawing), assembly (numbered balloons plus a parts list), as-fitted (a record of the item as built), patent (numbered figure, no dimensions).
  • views: any of front, top, side, isometric. Defaults to front, top and side.
  • notes: material, finish, tolerances, anything else to state on the sheet.
  • output_path: defaults to ./techdrawai-output/drawing-<timestamp>.png.

identify_product

Names the main object in a photo in two or three words. Free. Cheap groundwork: an agent that knows it is looking at a "cast-iron wall bracket" writes a much better title block and estimates far better dimensions than one working from "product".

Read the full file on GitHub · 80 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. 4d ago First seen · 80 lines · 87 tokens per session scan A 7166ab08ecd4

Subscribe to this mod's changes

techdrawai-drafting is a skill published in the GitHub repository MeltFlexDevs/techdrawai-skills (1 stars, last pushed 1mo ago), licensed MIT. It adds 87 tokens to every session and 1,473 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

qcad

Use when editing DXF files with a professional open-source 2D CAD application — CAM output, part libraries, isometric projection. QCAD: open-source 2D CAD with DXF as native format, scriptable via ECMAScript.

znlgis/opengis-skills · 53 tokens

solvespace

Use when doing lightweight parametric 2D/3D CAD with constraint-based sketching — linkages, section analysis, STL export for 3D printing. SolveSpace: ultra-light parametric constraint solver CAD with real-time solving.

znlgis/opengis-skills · 52 tokens

basic-part

Create a simple, fully dimensioned solid part using parameters, common features, inspect, preview, and export an authoritative CAD artefact.

halsyourpal422/Battenmark · 0 tokens

kompas-mcp-operator

Operate KOMPAS-3D MCP for 2D drawings, 3D parts, CAD-as-Code scripts, screenshots, exports, runtime memory, remote/local recovery, and Graph Brain diagnostics. Use when Codex needs to create, edit, inspect, validate, or debug geometry through mcpkompas3d, especially for sketch-feature chains, reusable scenarios…

dwnmf/KOMPAS-3D-MCP-bin · 95 tokens

cad

Create, modify, inspect, and validate STEP-first parametric CAD parts and assemblies. Use for natural-language CAD specs, reference images, 2D technical drawings, STEP/STP generation or direct inspection, Python CAD source, source-level joints, selector references, geometry facts, measurements, mating deltas…

earthtojake/text-to-cad · 79 tokens

dxf

Generate, regenerate, and validate 2D DXF drawings from Python ezdxf sources. Use for DXF files, .dxf.py generators, gendxf() sources, 2D profiles, outlines, templates, gaskets, panels, flat patterns, laser/plasma/waterjet cut layouts, and 2D drawing exports of CAD geometry.

earthtojake/text-to-cad · 77 tokens