image-prompt-designer

image-prompt-designer is an agent for Claude Code from XuanRanL/loamwright-SEO-Skill. It costs 76 tokens per session (5,636 once invoked), scanned A, original, Apache-2.0.

An image-prompt design agent for planning consistent illustrations and cover images for articles before image generation.

In plain words
What is it for?
Use it to decide image slots and create prompts for covers and section illustrations that another image-generation step will use.
Why use it?
It turns an article outline, brief, research, and brand guidance into a structured set of prompts while keeping a shared visual direction across images.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the xuanran-seo-blog-writer plugin — 68 skills, 34 agents, 4 hooks shipped together

Good fit Use it to decide image slots and create prompts for covers and section illustrations that another image-generation step will use.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/xuanranl/loamwright-seo-skill/image-prompt-designer
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.

Clone the repo
git clone --depth 1 https://github.com/XuanRanL/loamwright-SEO-Skill

Made for: Claude Code.

Or install xuanran-seo-blog-writer, the plugin that ships this one along with the rest of its 68 skills, 34 agents, 4 hooks.

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-prompt-designer

README.md
[![agentmods](https://agentmods.dev/badge/agents/xuanranl/loamwright-seo-skill/image-prompt-designer/github.svg)](https://agentmods.dev/agents/xuanranl/loamwright-seo-skill/image-prompt-designer)
Your own site
<a href="https://agentmods.dev/agents/xuanranl/loamwright-seo-skill/image-prompt-designer"><img src="https://agentmods.dev/badge/agents/xuanranl/loamwright-seo-skill/image-prompt-designer/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.

agentmods 80×15 button for image-prompt-designer

Your own site · 80×15
<a href="https://agentmods.dev/agents/xuanranl/loamwright-seo-skill/image-prompt-designer"><img src="https://agentmods.dev/badge/agents/xuanranl/loamwright-seo-skill/image-prompt-designer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 76 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,636 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00076 $0.05636
Opus 5 $0.00038 $0.02818
Sonnet 5 $0.00015 $0.01127
Haiku 4.5 $0.00008 $0.00564

Measured 12d ago against content hash 51900b55b3c1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

image-prompt-designer 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 12d 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/image-prompt-designer.md · 369 lines

How it starts

The opening of the file, as written. The whole thing — 369 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Image Prompt Designer

Designs the article's image-prompt set — slot count comes from outline.json's image_slot flags (= brief.image_count, default 6: 1 cover + 5 sections; scripts/_core/image_policy.py is the single source, raised from 4 on 2026-08-17). The shared Art Direction Prefix is the key innovation that ensures visual consistency across all images while still allowing per-image variation.

When invoked

  • After outline-architect completes (Stage: outline-architected)
  • Before image-slot-allocator invokes openai-image-generator
  • L2 phase-build dispatches this agent during image pipeline

Inputs

  • memory/workspace/{task_id}/outline.json (section breakdown)
  • memory/workspace/{task_id}/brief.json (topic, brand voice)
  • memory/workspace/{task_id}/research-brief.json (entities to depict)
  • projects/{slug}/brand-guideline.yaml (visual brand defaults if set)
  • references/image/style-presets.md (12 visual styles)
  • references/image/format-style-mapping.md (per-format style hints)
  • references/image/negative-prompts.md (per-style exclusions)

Tool whitelist

  • Read — load context + references
  • Write — produce image-prompts.json

Forbidden: Bash, Edit, Task, WebFetch. Pure design role, no API calls.

First: classify every slot — photo or chart?

Set kind: "photo" or kind: "chart" on EVERY slot. This decides whether the slot is generated by the AI photo model (photos) or rendered locally as a real labeled chart by scripts/build/render_data_charts.py (data/diagrams).

  • kind: "chart" when the slot's outline kind=="chart" OR its purpose/description is data/diagram-bearing: a comparison, yield/uplift figures, PPFD/DLI/CFM/efficacy numbers, a coverage map, a checklist, a verdict matrix, a spectrum, or any "chart/ table/graph/diagram" intent. WHY: AI image models garble or omit axis labels, numbers, and legends — that is exactly the "textless dull bar chart" failure. A programmatic renderer draws perfect text, so data belongs in a rendered chart, not a photo prompt.
  • kind: "photo" for scenes (rooms, plants, equipment, hero shots).
  • The COVER / featured slot is ALWAYS kind: "photo" — a charted hero breaks the social card and theme hero.

Read the full file on GitHub · 369 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. 12d ago First seen · 369 lines · 76 tokens per session scan A 51900b55b3c1

Subscribe to this mod's changes

image-prompt-designer is an agent published in the GitHub repository XuanRanL/loamwright-SEO-Skill (49 stars, last pushed 25d ago), licensed Apache-2.0. It adds 76 tokens to every session and 5,636 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 agents, from other repositories

schema-generator

Structured-data specialist. Use proactively during an audit to validate existing JSON-LD and PROPOSE complete Tier-1 schema blocks (plus e-commerce/local schema and agentic-commerce readiness when those verticals are active). It proposes diffs only and does NOT write files.

Hainrixz/claude-seo-ai · 56 tokens

seo-fixer-writer

The ONLY agent allowed to write files. Used exclusively by the fix skill (the /claude-seo-ai:fix command) AFTER the user has confirmed the changes. Applies confirmed AUTO-class fixes (and PROPOSED ones the user accepted) through Edit/Write for local diffs and the ticketed adapter CLIs for remote targets, backs up…

Hainrixz/claude-seo-ai · 93 tokens

geo-schema

Schema markup specialist detecting, validating, and generating structured data (JSON-LD preferred). Focuses on schemas that improve AI discoverability including Organization, Person, Article, sameAs, and speakable properties.

Cognitic-Labs/geoskills · 44 tokens

geo-citability

AI citability scoring and optimization specialist. Analyzes how likely AI systems are to cite, quote, or reference content from a website. Evaluates answer block quality, self-containment, statistical density, structural clarity, and expertise signals.

Cognitic-Labs/geoskills · 53 tokens

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens