dalle

dalle is a skill for Claude Code, Codex from vinsonconsulting/limner. It costs 56 tokens per session (938 once invoked), scanned A, original, Apache-2.0.

A guide for using Limner's DALL·E pipeline, which creates or edits images through OpenAI's gpt-image-1 image model. It explains how to write prompts and choose image size, quality, format, and background settings.

In plain words
What is it for?
Use it to create new images, edit an existing source image, request transparent backgrounds, select output dimensions and quality, or place short text in an image.
Why use it?
It turns a visual idea into clearer generation instructions and helps choose settings suited to icons, scenes, transparent graphics, or text in images.

Skill for Claude CodeCodex

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/vinsonconsulting/limner/dalle
Any agent
npx skills add vinsonconsulting/limner --skill dalle
Clone the repo
git clone --depth 1 https://github.com/vinsonconsulting/limner

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.

agentmods badge for dalle

README.md
[![agentmods](https://agentmods.dev/badge/skills/vinsonconsulting/limner/dalle.svg)](https://agentmods.dev/skills/vinsonconsulting/limner/dalle)
Your own site
<a href="https://agentmods.dev/skills/vinsonconsulting/limner/dalle"><img src="https://agentmods.dev/badge/skills/vinsonconsulting/limner/dalle.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 938 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 5.1 $0.00056 $0.00938
Opus 5 $0.00028 $0.00469
Sonnet 5 $0.00011 $0.00188
Haiku 4.5 $0.00006 $0.00094

Measured 5d ago against content hash b99c14a95326, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

dalle 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 5d 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.

packages/limner-agent/skills/dalle/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DALL·E prompt builder

Limner is an independent third-party project built on Anthropic's CMA platform; it is not an Anthropic or Claude product.

Limner's DALL·E pipeline calls OpenAI's Images API on the gpt-image-1 family. It follows detailed instructions well, so the prompt carries most of the weight while the knobs handle format and background. This skill is the procedure; the recipe at the end lists the knobs and their values.

Procedure

  1. Write a descriptive prompt: name the subject, composition, lighting, and style in plain language. gpt-image-1 rewards specificity.
  2. Choose size and quality for the use: square for icons, portrait or landscape for scenes; higher quality trades latency and cost for detail.
  3. For a logo or UI mark that must drop onto any surface, request a transparent background and a format that keeps alpha.
  4. To render text in the image, quote the exact words and where they go, keep the text short, and verify spelling in the result.
  5. To restyle an existing image rather than start over, pass it as a source image URL; the edit preserves the subject while applying the prompt.

Knob reference

The recipe below is generated from the Limner guidance core (@limner/core), the same source the MCP dalle-builder prompt serves, so this skill and that prompt cannot drift. Do not edit the generated region by hand; run pnpm --filter @limner/limner-agent gen:skills instead.

DALL·E prompt recipe

Limner is an independent third-party project built on Anthropic's CMA platform; it is not an Anthropic or Claude product.

Limner’s DALL·E pipeline calls OpenAI’s Images API, defaulting to the gpt-image-1 model. Write a descriptive prompt: gpt-image-1 follows detailed instructions closely and renders legible text in the image far better than earlier models. Then set the knobs below. Note that OpenAI’s 2025/2026 consolidation retired DALL·E 2/3 and removed the legacy style and response_format parameters; Limner does not send them.

Read the full file on GitHub · 69 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. 5d ago First seen · 69 lines · 56 tokens per session scan A b99c14a95326

Subscribe to this mod's changes

dalle is a skill published in the GitHub repository vinsonconsulting/limner (1 stars, last pushed 24d ago), licensed Apache-2.0. It adds 56 tokens to every session and 938 once invoked, about $0.0003 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.