What is drawthings-agent-skills AGENTS.md?

Project instructions for a Python client that connects to Draw Things, a macOS image-generation server, using gRPC, a communication method between programs.

Following project guidelines, checking whether the environment is ready, and understanding how image-generation requests and responses move through the code.

It gives an agent the project’s architecture, coding rules, build and test steps, and environment checks in one place.

How ianscrivener/drawthings-agent-skills configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to ianscrivener/drawthings-agent-skills. 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/ianscrivener/drawthings-agent-skills/main/AGENTS.md

Clone the repo

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

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

Your own site

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

Per session 1,370 This file is loaded in full into every session.

When invoked 1,370 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	$0.01370	$0.01370
Opus 5.5	$0.00548	$0.00548
Sonnet 5.5	$0.00274	$0.00274
Haiku 4.5	$0.00137	$0.00137

Measured 2mo ago against content hash 9a8074adee76, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

drawthings-agent-skills 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 · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Guidelines — drawthings-agent-skill

Overview

Python gRPC client and agent skill for the Draw Things image generation server on macOS. Wraps the gRPC + FlatBuffers + DTTensor image format into a simple Python API with CLI scripts that output JSON.

This project is a Python port of dt-grpc-ts, a TypeScript gRPC client library for Draw Things by Kelly Jerrell. The proto/fbs schemas, wire format, tensor encoding, and FlatBuffer config structure are all derived from that reference implementation.

Architecture

DTService (service.py)
  ├── build_config_buffer (config.py)  → FlatBuffer-encoded GenerationConfiguration
  ├── image_helpers.py                 → DTTensor ↔ PIL Image conversion
  ├── cred.py                          → TLS credentials (Draw Things root CA)
  └── generated/                       → Auto-generated protobuf + FlatBuffer code

Request flow:

Config dict → build_config_buffer() → FlatBuffer bytes
Source image (if img2img) → convert_image_for_request() → DTTensor bytes, SHA-256 hashed
Protobuf ImageGenerationRequest assembled with config, prompt, image hash, contents
gRPC streaming response → convert_response_image() → PIL Image

DTTensor wire format (shared with the TypeScript library):

68-byte header: 17 × uint32 (metadata flags at indices 0–5, height at 6, width at 7, channels at 8)
Payload: float16 pixel data (width × height × channels × 2 bytes)
Response decode: clamp((f16 + 1) × 127, 0, 255) → uint8
Request encode: (uint8 / 127) − 1 → float16
Images are content-addressed: SHA-256 hash as reference, raw bytes in contents[]

Code Style

Python 3.10+, plain Python — no TypeScript, no frameworks
snake_case for all Python identifiers and config dict keys
Config keys map to FlatBuffer schema fields: hires_fix_strength, guidance_scale, seed_mode, etc.
Generated code in src/drawthings/generated/ — do not edit manually; regenerate with assets/gen_code.sh
Imports from generated code use full package paths: from drawthings.generated import imageService_pb2

Read the full file on GitHub · 104 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 · 104 lines · 1,370 tokens per session scan A 9a8074adee76

Subscribe to this mod's changes

drawthings-agent-skills AGENTS.md is an instructions file published in the GitHub repository ianscrivener/drawthings-agent-skills (2 stars, last pushed 6mo ago), licensed CC0-1.0. It adds 1,370 tokens to every session, about $0.0055 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.

Backend and APIs Creative and media

drawthings-agent-skills AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
drawthings-agent-skills AGENTS.mdianscrivener/drawthings-agent-skills	Instructions file	2	6mo ago	CC0-1.0	A	1,370	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	yesterday	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

drawthings-agent-skills: Instructions file for Codex