image-studio

image-studio is a skill for Claude Code, Codex from SpaceZephyr/cowrite. It costs 83 tokens per session (925 once invoked), scanned A, original, MIT.

A skill for creating raster images such as article illustrations, Xiaohongshu posts, presentation visuals, covers, and diagrams with the built-in image-generation tool. It includes guidance for choosing image types, proportions, and visual styles.

In plain words
What is it for?
Use it to create article graphics, social-media images, presentation visuals, covers, and structured diagrams.
Why use it?
It provides a defined process for turning content into image assets while keeping the layout and style consistent. It also makes required text and generation choices explicit.

Skill for Claude CodeCodex

Part of the cowrite plugin — 8 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/spacezephyr/cowrite/image-studio
Any agent
npx skills add SpaceZephyr/cowrite --skill image-studio
Clone the repo
git clone --depth 1 https://github.com/SpaceZephyr/cowrite

Made for: Claude Code, Codex.

Or install cowrite, the plugin that ships this one along with the rest of its 8 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 image-studio

README.md
[![agentmods](https://agentmods.dev/badge/skills/spacezephyr/cowrite/image-studio.svg)](https://agentmods.dev/skills/spacezephyr/cowrite/image-studio)
Your own site
<a href="https://agentmods.dev/skills/spacezephyr/cowrite/image-studio"><img src="https://agentmods.dev/badge/skills/spacezephyr/cowrite/image-studio.svg" alt="Measured on agentmods" height="20"></a>
Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 925 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 $0.00083 $0.00925
Opus 5 $0.00042 $0.00463
Sonnet 5 $0.00017 $0.00185
Haiku 4.5 $0.00008 $0.00093

Measured 5d ago against content hash db3d4d57e188, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

image-studio 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.

skills/image-studio/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Image Studio

Create polished raster images with Codex's built-in image_gen tool. Never call LabNana, Gemini, OpenAI API/CLI, a local generation script, or any other external image provider. Do not require or request an API key.

If the runtime does not expose the built-in image_gen tool, stop and explain that image generation requires Codex with built-in image generation. Do not silently downgrade or insert a placeholder.

Image types

Type Default ratio Reference
Xiaohongshu cover or series 3:4 references/types/xhs-cover.md
Presentation visual 16:9 references/types/ppt-illustration.md
Structured chart or diagram adaptive references/types/chart.md
Article logic illustration 16:9 references/types/article-logic.md

Read the matching type reference before prompting. For style, select one file from references/styles/ and keep its palette, typography, spacing, and visual language intact.

Confirmation rules

Confirm these four decisions before generation:

  1. image type and aspect ratio;
  2. complete content and required exact text;
  3. one visual style;
  4. automatic generation or prompt review first.

Treat a Cowrite command that explicitly lists these confirmed values as confirmation already completed. Do not ask again.

Prompt assembly

Read references/prompt-templates/base.md. Build a concise production prompt containing:

  • use case and intended placement;
  • exact aspect ratio and composition;
  • selected style with complete palette and visual identity;
  • one core idea and no more than 3-6 essential concepts;
  • exact visible text, kept short and primarily Simplified Chinese;
  • no logo, watermark, signature, page number, fake UI text, or decorative filler.

For a multi-image set, repeat the complete shared visual identity in every prompt. Do not assume the image model remembers an earlier call.

Built-in generation workflow

  1. Call Codex's built-in image_gen tool directly. For a brand-new image, do not pass reference-image parameters.
  2. Generate one distinct asset per tool call. A batch request means repeated built-in calls, not an API or CLI batch script.
  3. For later images that must match an earlier generated image, use the first accepted image as a style reference only when the built-in tool and current context support it. Still repeat the full visual identity in the prompt.
  4. Inspect every result for composition, text accuracy, palette, watermark, cropping, and consistency. Retry once with one targeted correction when necessary.
  5. For a project-bound image, use the tool's saved output path or output hint, then copy or move the accepted image from Codex's generated-images area into a writable project directory. Never leave a referenced project asset only under the default Codex output directory.
  6. Never overwrite an existing asset unless explicitly requested. Use stable numbered filenames or a version suffix.

Read the full file on GitHub · 78 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 · 78 lines · 83 tokens per session scan A db3d4d57e188

Subscribe to this mod's changes

image-studio is a skill published in the GitHub repository SpaceZephyr/cowrite (91 stars, last pushed 1mo ago), licensed MIT. It adds 83 tokens to every session and 925 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens