image-generation

A guide for generating images from structured prompts, with optional reference images. It covers character designs, scenes, product visuals, and other visual content.

In plain words
What is it for?
It is for creating characters, scenes, product visualizations, and other images with specified subjects, styles, moods, and compositions.
Why use it?
It turns a visual idea into a more detailed generation request and can use references to guide style or composition.

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/comisai/comis/image-generation
Any agent
npx skills add comisai/comis --skill image-generation
Clone the repo
git clone --depth 1 https://github.com/comisai/comis

Made for: Claude Code, Codex.

Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,091 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 $0.00072 $0.01091
Opus 5 $0.00036 $0.00545
Sonnet 5 $0.00014 $0.00218
Haiku 4.5 $0.00007 $0.00109

Measured 2d ago against content hash 0ca8a0be9fba, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

image-generation 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 2d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/generate.py), 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.

packages/daemon/bundled-skills/image-generation/SKILL.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Image Generation

Generate high-quality images using structured JSON prompts and a bundled Python script. Supports reference images for style and composition guidance.

All script paths below are relative to this skill's directory. Resolve them against the directory containing the manifest file shown in <location> (e.g., if <location> is ~/.comis/skills/image-generation/SKILL.md, then scripts/generate.py means ~/.comis/skills/image-generation/scripts/generate.py). Invoke the resolved script by its absolute path while keeping the tool working directory inside the execution workspace. Never set cwd to the skill directory; it is outside workspace bounds. In command examples below, replace each relative scripts/... path with its resolved absolute path.

Write prompt files and generated outputs to your workspace directory (shown in the "Workspace" section of your system prompt).

The bundled script requires requests and Pillow Python packages (pip install requests Pillow).

Workflow

Step 1: Understand requirements

Identify from the user's request:

  • Subject/content: What should be in the image
  • Style preferences: Art style, mood, color palette
  • Technical specs: Aspect ratio, composition, lighting
  • Reference images: Any images to guide generation

Step 2: Create structured prompt

Write a JSON prompt file to your workspace directory with a descriptive filename like {subject-name}.json.

Step 3: Execute generation

python3 scripts/generate.py \
  --prompt-file ~/.comis/workspace/prompt-file.json \
  --output-file ~/.comis/workspace/generated-image.jpg \
  --aspect-ratio 16:9

With reference images:

python3 scripts/generate.py \
  --prompt-file ~/.comis/workspace/prompt-file.json \
  --reference-images /path/to/ref1.jpg /path/to/ref2.png \
  --output-file ~/.comis/workspace/generated-image.jpg \
  --aspect-ratio 2:3

Parameters:

  • --prompt-file: Path to JSON prompt file (required)
  • --reference-images: Paths to reference images (optional, space-separated)
  • --output-file: Path to output image file (required)
  • --aspect-ratio: Aspect ratio (optional, default: 16:9)

Read the full file on GitHub · 123 lines

Files

What ships with it

2 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.

  1. 2d ago First seen · 123 lines · 72 tokens per session scan A 0ca8a0be9fba

Subscribe to this mod's changes

image-generation is a skill published in the GitHub repository comisai/comis (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 72 tokens to every session and 1,091 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

org-sync

Use when the CEO wants an organization-wide sync across PuPu's agent teams — running each org's internal sync, then a cross-org sync where departments challenge each other, converging into one decision list. Triggers: "跑一次 org sync", "全局同步", "组织盘点", "/org-sync", "各部门现在什么情况", "有什么要我拍板的".

haoxiang-xu/PuPu · 82 tokens

release-feature-audit

Use when a new PuPu feature finishes implementation and needs its consistency audit before its ticket is marked done — "audit #123", "审计这个功能", "这个 feature 过一遍检查" — or when release-close-sprint roll-call finds a new feature that was never audited. Also covers standalone i18n checks ("漏翻了吗", "检查 i18n"), which used to be…

haoxiang-xu/PuPu · 94 tokens

gitnexus-impact-analysis

Use when the user wants to know what will break if they change something, or needs safety analysis before editing code. Examples: "Is it safe to change X?", "What depends on this?", "What will break?".

haoxiang-xu/PuPu · 50 tokens

growth-analyst

Use when analyzing PuPu's open-source growth or health for the founder — GitHub traffic, downloads/installs, releases, community, or contributor activity — or when producing a growth report or weekly COO report. Repo is haoxiang-xu/PuPu. Triggers: "how is PuPu growing?", "are people installing PuPu?", "which release…

haoxiang-xu/PuPu · 102 tokens

test-api

Use when running QA / regression tests against PuPu, when verifying a code change actually works in the running app, or when reading PuPu UI/state without screenshotting manually. Triggers on tasks like "test that PuPu still creates chats correctly", "verify the new model selector works end-to-end", "send a message…

haoxiang-xu/PuPu · 110 tokens

org-court

Use when any org-change proposal needs adjudication - adding/removing/redesigning agents or teams, changing org rules, or evaluating org granularity. Runs PuPu's HR court: a proposal is heard by four dimension assessors (comm efficiency / context cleanliness / signal ratio / routing cost), the judge verifies evidence…

haoxiang-xu/PuPu · 136 tokens