What is image-curator?

An image-curation agent intended to prepare article images for WordPress by improving alternative text, adding captions, replacing image placeholders, and adding image metadata for search engines.

Its documented role is the final image-preparation step before publishing an article, but it should not be treated as an active add-on.

It is marked as superseded and unwired, so no workflow currently calls it; other scripts now handle some of its intended jobs.

image-curator — Agent for Claude Code by XuanRanL

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/xuanranl/loamwright-seo-skill/image-curator/github.svg)](https://agentmods.dev/agents/xuanranl/loamwright-seo-skill/image-curator)

Your own site

<a href="https://agentmods.dev/agents/xuanranl/loamwright-seo-skill/image-curator"><img src="https://agentmods.dev/badge/agents/xuanranl/loamwright-seo-skill/image-curator/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/agents/xuanranl/loamwright-seo-skill/image-curator"><img src="https://agentmods.dev/badge/agents/xuanranl/loamwright-seo-skill/image-curator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 61 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,354 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.

Model	Per session	Once invoked
Fable 5.1	$0.00061	$0.01354
Opus 5	$0.00030	$0.00677
Sonnet 5	$0.00012	$0.00271
Haiku 4.5	$0.00006	$0.00135

Measured 10d ago against content hash 22684e5d2232, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

image-curator 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 10d 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-curator.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Image Curator

⚠️ SUPERSEDED — NOT WIRED (2026-08-12 wiring audit). No Stage() dispatches this agent; "Stage 27f" exists only in REFERENCE-ONLY prose in skills/phase-publish/SKILL.md. Its jobs were absorbed: [IMAGE-SLOT-N] replacement by assemble.py + wp_publisher._replace_image_placeholders(); the 4 WP media fields by openai_image_pipeline.py's heuristic caption/description derivation. Known gaps that absorption left open (real, unowned): scripts/image/alt_text_polisher.py has zero callers despite its docstring naming this agent, and nothing writes image_metadata.json (the contract subskills/image/image-curator/SKILL.md still describes). Treat both as unwired until a Stage() names them (Rule 6).

The final image step before publish. Takes raw images + their metadata and turns them into properly attributed, alt-tagged, captioned, schema-marked WordPress-ready content.

Inputs

memory/workspace/{task_id}/image_prompts.json (alt_text_seed + filename_seed per slot)
projects/{slug}/assets/images/{article-slug}/{custom_id}.webp × 4 (+ srcset variants)
projects/{slug}/assets/images/{article-slug}/*.meta.json (per-image metadata)
memory/workspace/{task_id}/draft.md (with [IMAGE-SLOT-N] placeholders)
memory/workspace/{task_id}/meta.json (article title + primary keyword)
references/image/seo-image-best-practices.md

Tool whitelist

Read — load draft, prompts, meta
Write — write image metadata files
Edit — replace placeholders in draft.md
Bash — call image_seo_filename / alt polisher scripts

Workflow

Step 1: Polish alt text per image

For each image (cover + the section images):

Read alt_text_seed from image_prompts.json
Refine to:
- 60-125 chars
- Descriptive (what's in the image, not what it represents)
- Contains primary keyword naturally (if relevant)
- Does NOT start with "Image of..." or "Picture showing..."
- One unique alt per image (no duplicates)

Example refinement:

Seed: "Expert angler demonstrating proper fly fishing technique at golden hour"
Polished: "Angler casting G.Loomis NRX+ rod at sunset on the Deschutes River" (more specific, contains "rod" hint of primary keyword)

Read the full file on GitHub · 139 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.

10d ago First seen · 139 lines · 61 tokens per session scan A 22684e5d2232

Subscribe to this mod's changes

image-curator is an agent published in the GitHub repository XuanRanL/loamwright-SEO-Skill (47 stars, last pushed 23d ago), licensed Apache-2.0. It adds 61 tokens to every session and 1,354 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 2026-08-30.

Claude Code Creative and media Marketing and SEO ai-search blog-automation chatgpt claude-plugin content-marketing

design-producer

Agent visual & production — asset list, brief anh/carousel/video, brand guideline, design review, HTML email/landing.

minhnv0807/ai-business-skills · 28 tokens

hdr

Handles HDR color workflows end-to-end — HDR10 static metadata, HDR10+ dynamic metadata, Dolby Vision profiles, PQ↔HLG conversion, SDR↔HDR tone mapping, and ACES/OCIO color management. Use when the user mentions Dolby Vision, HDR10, HDR10+, HLG, PQ, tone mapping, or anything about color pipelines that must survive…

damionrashford/media-os · 80 tokens

architect

Designs end-to-end media pipelines before a single command runs. Use when the user describes an unfamiliar workflow ("how do I deliver a Dolby Vision MP4 for Apple TV", "stream 4K HDR to HLS + DASH with DRM") and needs a plan that picks the right skills and ordering. Produces a staged recipe with exact tools, not just…

damionrashford/media-os · 76 tokens

image-curator