A local image-generation connection for Draw Things, an image app that runs on your own Mac or Linux computer. It supports creating images from text, changing existing images, enlarging images, and restoring faces through Draw Things' local gRPC interface.

Creating artwork or scenes from prompts, editing an existing image, upscaling images, and restoring faces on supported hardware.

It lets an agent use a local image generator without sending the image request to a hosted image service. Draw Things must be running with its API server enabled.

drawthings — Skill for Claude Code and Codex by ianscrivener

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.

Any agent

npx skills add ianscrivener/drawthings-agent-skills --skill drawthings-agent-skills

Clone the repo

git clone --depth 1 https://github.com/ianscrivener/drawthings-agent-skills

Made for: Claude Code, Codex.

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/skills/ianscrivener/drawthings-agent-skills/drawthings-agent-skills/github.svg)](https://agentmods.dev/skills/ianscrivener/drawthings-agent-skills/drawthings-agent-skills)

Your own site

<a href="https://agentmods.dev/skills/ianscrivener/drawthings-agent-skills/drawthings-agent-skills"><img src="https://agentmods.dev/badge/skills/ianscrivener/drawthings-agent-skills/drawthings-agent-skills/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/skills/ianscrivener/drawthings-agent-skills/drawthings-agent-skills"><img src="https://agentmods.dev/badge/skills/ianscrivener/drawthings-agent-skills/drawthings-agent-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,170 The whole file, excluding the scripts and references it only reads on demand.

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	$0.00098	$0.02170
Opus 5.5	$0.00039	$0.00868
Sonnet 5.5	$0.00020	$0.00434
Haiku 4.5	$0.00010	$0.00217

Measured 2mo ago against content hash d96d83c7f36e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

drawthings 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.

The scan reads SKILL.md. This mod also ships 1 executable file (assets/gen_code.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

SKILL.md · 185 lines

How it starts

The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DrawThings Image Generation Skill

Generates images via the DrawThings gRPC API running locally on macOS (or Linux). Supports text-to-image, image-to-image, upscaling, face restoration and DrawThingsserver introspection.

Prerequisites - IMPORTANT!!!

This skill will only work on a MacOS with M Series silicon or a Linux with a modern GPU
Be sure to follow the setup prerequisites and process exactly. Do not vary or ignore to read the configuration properly.
The user needs to enable the GRPC server on DrawThings for this skill to work.
DrawThings must be running on macOS with the gRPC server enabled (default port 7859). Enable it in Draw Things → Settings → API Server.

Environment Setup (agent-managed)- IMPORTANT!!!

Follow the instructions exactly. Don't be arrogant and think you know better and try to do your own thing. If there are problems with rendering - just state the facts accurately - do not speculate as to the cause.

Step 1: Check environment - IMPORTANT!!!

python src/drawthings/check_env.py --host localhost:7859

This is uses your the system Python to check the UV Python and curler install that there is a Python virtual environment and that the UV Python environment is has downloaded all the models.

Returns JSON with ready: true/false, a checks object, missing list, and venv_python path. If ready is true, skip to Step #3.

Step 2: Setup (only if check in Step #1 reports not ready) - IMPORTANT!!!

python src/drawthings/setup_env.py

Creates the .venv, installs all dependencies via uv sync, and verifies the package is importable. Returns JSON with success: true/false and the venv_python path. This is idempotent — safe to run repeatedly.

Step 3: Run skill scripts

Use the venv_python path from check/setup (typically .venv/bin/python) to run scripts:

./.venv/bin/python src/drawthings/generate.py --prompt "..."
./.venv/bin/python src/drawthings/list_assets.py --tls true --compression false
./.venv/bin/python src/drawthings/img2img.py --input /path/to/image.png --prompt "..."

Read the full file on GitHub · 185 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 185 lines · 98 tokens per session scan A d96d83c7f36e

Subscribe to this mod's changes

drawthings is a skill published in the GitHub repository ianscrivener/drawthings-agent-skills (2 stars, last pushed 6mo ago), licensed CC0-1.0. It adds 98 tokens to every session and 2,170 once invoked, about $0.0004 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 2026-08-31.

Creative and media

drawthings next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
drawthingsianscrivener/drawthings-agent-skills	Skill	2	6mo ago	CC0-1.0	A	98	Claude Code, Codex
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code