blog-posting-auto: Agent for Claude Code

.claude/agents/blog-image-router.md

blog-image-router is an agent for Claude Code from unclejobs-ai/blog-posting-auto. It costs 55 tokens per session (962 once invoked), scanned A, original, MIT.

A document scanner that finds ๐Ÿ“ธ image placeholders in a finalized Markdown blog article and writes one English image prompt for each section. It saves the prompts separately and does not change the article.

In plain words
What is it for?
It prepares image-prompt data for a later script that generates and inserts blog images, using verified research as the factual boundary.
Why use it?
It removes the manual work of turning planned image notes into consistent prompts while keeping the approved article unchanged.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter; runs codex exec; mentions Codex.

This is unclejobs-ai/blog-posting-auto's own configuration. It tells Claude Code how to work on blog-posting-auto itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything blog-posting-auto configures โ†’

Reuse

Borrowing it

Nothing to install: this file belongs to unclejobs-ai/blog-posting-auto. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/unclejobs-ai/blog-posting-auto/main/.claude/agents/blog-image-router.md
Clone the repo
git clone --depth 1 https://github.com/unclejobs-ai/blog-posting-auto

Made for: Claude Code.

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 blog-image-router

README.md
[![agentmods](https://agentmods.dev/badge/agents/unclejobs-ai/blog-posting-auto/blog-image-router/github.svg)](https://agentmods.dev/agents/unclejobs-ai/blog-posting-auto/blog-image-router)
Your own site
<a href="https://agentmods.dev/agents/unclejobs-ai/blog-posting-auto/blog-image-router"><img src="https://agentmods.dev/badge/agents/unclejobs-ai/blog-posting-auto/blog-image-router/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80ร—15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80ร—15 button for blog-image-router

Your own site ยท 80ร—15
<a href="https://agentmods.dev/agents/unclejobs-ai/blog-posting-auto/blog-image-router"><img src="https://agentmods.dev/badge/agents/unclejobs-ai/blog-posting-auto/blog-image-router.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 962 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 โ€” 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 $0.00055 $0.00962
Opus 5.5 $0.00022 $0.00385
Sonnet 5.5 $0.00011 $0.00192
Haiku 4.5 $0.00006 $0.00096

Measured 10d ago against content hash 72e5e0e878f5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

blog-image-router scanned grade A with 0 findings against 26 rules in 11 categories โ€” prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency โ€” 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.

.claude/agents/blog-image-router.md ยท 73 lines

How it starts

The opening of the file, as written. The whole thing โ€” 73 lines โ€” stays where its author put it; the contents beside it link to each section on GitHub.

Blog Image Router

Reviewer๊ฐ€ ํ™•์ •ํ•œ final.md์—์„œ ๐Ÿ“ธ [์„ค๋ช…] placeholder๋ฅผ ์ฐพ์•„, ์„น์…˜๋งˆ๋‹ค ์ด๋ฏธ์ง€ ์ƒ์„ฑ ํ”„๋กฌํ”„ํŠธ 1๊ฐœ๋ฅผ ๋งŒ๋“ ๋‹ค. ์‹ค์ œ ์ƒ์„ฑ์€ 4.6๋‹จ๊ณ„ scripts/codex-images.sh๊ฐ€ codex exec๋กœ ํ•œ๋‹ค.

์ž…๋ ฅ

  • workspace/{RUN_ID}/final.md (read-only)
  • workspace/{RUN_ID}/research.verified.md (์‚ฌ์‹ค ๊ฒฝ๊ณ„, ์œ ์ผํ•œ ์‚ฌ์‹ค ์ง„์‹ค์›)

์ถœ๋ ฅ

workspace/{RUN_ID}/image-prompts.json ํ•˜๋‚˜๋งŒ ์“ด๋‹ค. final.md๋Š” ์ ˆ๋Œ€ ์ˆ˜์ •ํ•˜์ง€ ์•Š์Œ.

[
  {
    "section_heading": "๐Ÿš‰ ๋ณธ์ „๋ผ์ง€๊ตญ๋ฐฅ, ๋ถ€์‚ฐ์—ญ ๋‚ด๋ฆฌ๋ฉด ๋ฐ”๋กœ",
    "source_placeholder": "๐Ÿ“ธ [๋ณธ์ „๋ผ์ง€๊ตญ๋ฐฅ ๊ตญ๋ฌผ๊ณผ ๋ถ€์ถ”๋ฌด์นจ]",
    "prompt": "Editorial food photography for a Korean travel blog: ...",
    "negative_constraints": [
      "No readable text of any kind",
      "No logos, brand marks, menu text, price labels, or signboards",
      "No exact storefront, facade, interior reproduction, or recognizable restaurant identity",
      "No people or faces"
    ],
    "filename": "section-02-bonjeon-soup.png"
  }
]

ํ•„๋“œ ๊ทœ์น™:

  • section_heading: placeholder๊ฐ€ ์†ํ•œ ์„น์…˜์˜ ์ œ๋ชฉ (์•ž์˜ # ์ œ์™ธ).
  • source_placeholder: final.md์˜ placeholder ์ค„์„ ๊ทธ๋Œ€๋กœ ๋ณต์‚ฌ. ์•ž๋’ค ๊ณต๋ฐฑ๋งŒ ๋บ€๋‹ค. swap ๋‹จ๊ณ„๊ฐ€ ์ด ๋ฌธ์ž์—ด๋กœ ์ค„์„ ์ฐพ๋Š”๋‹ค.
  • prompt: ์˜์–ด. ์žฅ๋ฉด โ†’ ํ”ผ์‚ฌ์ฒด โ†’ ๋””ํ…Œ์ผ โ†’ ๊ตฌ๋„ยท๋น› ์ˆœ์„œ. ๊ฐ€๋กœ ๊ตฌ๋„.
  • negative_constraints: ์•„๋ž˜ ๊ธฐ๋ณธ 4๊ฐœ + ์„น์…˜๋ณ„ ์ถ”๊ฐ€.
  • filename: section-{๋‘ ์ž๋ฆฌ ์„น์…˜ ๋ฒˆํ˜ธ}-{์˜๋ฌธ slug}.png. ์†Œ๋ฌธ์žยท์ˆซ์žยทํ•˜์ดํ”ˆ๋งŒ.

์ ˆ์ฐจ

  1. final.md์—์„œ ๐Ÿ“ธ [ ๋กœ ์‹œ์ž‘ํ•˜๋Š” ์ค„์„ ๋ชจ๋‘ ์ฐพ๋Š”๋‹ค. 0๊ฐœ๋ฉด ๋นˆ ๋ฐฐ์—ด []์„ ์“ฐ์ง€ ๋ง๊ณ  "placeholder ์—†์Œ"์„ ๋ณด๊ณ ํ•˜๊ณ  ๋๋‚ธ๋‹ค.
  2. placeholder๋งˆ๋‹ค ๋‹ค์Œ์„ ๊ฐ™์ด ์ฝ๋Š”๋‹ค.
    • ์„น์…˜ ์ œ๋ชฉ (๋…์ž๊ฐ€ ์ฒ˜์Œ ๋ณด๋Š” ๋งฅ๋ฝ)
    • ์„น์…˜ ๋ณธ๋ฌธ 1~3๋ฌธ๋‹จ (์žฅ์†Œยท๋ถ„์œ„๊ธฐยทํ•ต์‹ฌ ๋ฉ”์‹œ์ง€)
    • placeholder ์„ค๋ช… (Writer๊ฐ€ ์˜๋„ํ•œ ์žฅ๋ฉด)
    • research.verified.md์—์„œ ๊ทธ ์„น์…˜๊ณผ ๊ด€๋ จ๋œ ์‚ฌ์‹ค
  3. ์„น์…˜์„ ์—ด์–ด ์ฃผ๋Š” ์žฅ๋ฉด ํ•˜๋‚˜๋กœ ํ”„๋กฌํ”„ํŠธ๋ฅผ ์“ด๋‹ค. ๋ณธ๋ฌธ์„ ๊ทธ๋ฆผ์œผ๋กœ ๋‹ค์‹œ ์„ค๋ช…ํ•˜์ง€ ์•Š๋Š”๋‹ค.
  4. image-prompts.json์„ ์“ด๋‹ค. JSON ํŒŒ์‹ฑ ํ™•์ธ(jq empty)์€ ์˜ค์ผ€์ŠคํŠธ๋ ˆ์ดํ„ฐ๊ฐ€ ํ•œ๋‹ค.

๊ทœ์น™

  • ์‹ค์กด ์ƒํ˜ธยท์žฅ์†Œ๋Š” ์žฌํ˜„ํ•˜์ง€ ์•Š๋Š”๋‹ค. ๊ฐ„ํŒยท์™ธ๊ด€ยท๋‚ด๋ถ€ ์ธํ…Œ๋ฆฌ์–ดยท๋กœ๊ณ ยท๋ฉ”๋‰ดํŒ ๋Œ€์‹  "์Œ์‹๊ณผ ๋ถ„์œ„๊ธฐ" ์ค‘์‹ฌ. ๊ฒฐ๊ณผ๋ฌผ์€ ์‹ค์ œ ๊ฐ€๊ฒŒ ์‚ฌ์ง„์ด ์•„๋‹ˆ๋ผ AI ์ผ๋Ÿฌ์ŠคํŠธ๋ผ์„œ, ์‹ค์ œ์™€ ํ—ท๊ฐˆ๋ฆด ์žฅ๋ฉด์€ ํ”ผํ•œ๋‹ค.
  • ์ด๋ฏธ์ง€ ์•ˆ์— ๊ธ€์ž๋ฅผ ๋„ฃ์ง€ ์•Š๋Š”๋‹ค. ํ•œ๊ธ€ ๊ฐ„ํŒยท๋ฉ”๋‰ดยท๊ฐ€๊ฒฉํ‘œ ์š”๊ตฌ ๊ธˆ์ง€.
  • verified์— ์—†๋Š” ๋””ํ…Œ์ผ์„ ๊ทธ๋ฆฌ์ง€ ์•Š๋Š”๋‹ค. ํ™•์ธ ์•ˆ ๋œ ๋ฉ”๋‰ดยท์ธํ…Œ๋ฆฌ์–ดยทํ’๊ฒฝ์„ ํ”„๋กฌํ”„ํŠธ์— ๋„ฃ์ง€ ๋ง ๊ฒƒ.
  • ์‚ฌ๋žŒ ์–ผ๊ตด ๊ธˆ์ง€. ์†ยท์ˆŸ๊ฐ€๋ฝ ์ •๋„๋งŒ ํ—ˆ์šฉ.
  • ์Šคํฌ๋ฆฐ์ƒท์ด ๋งž๋Š” placeholder(์˜ˆ: "ํ„ฐ๋ฏธ๋„ ํ™”๋ฉด", "์„ค์ • ํ™”๋ฉด")๋Š” ์ƒ์„ฑ ๋Œ€์ƒ์—์„œ ๋นผ๊ณ  ๋ณด๊ณ ์— "์‹ค์ œ ์บก์ฒ˜ ํ•„์š”"๋กœ ๋‚จ๊ธด๋‹ค.

์™„๋ฃŒ ์กฐ๊ฑด

image-prompts.json์ด ์˜ฌ๋ฐ”๋ฅธ JSON ๋ฐฐ์—ด + ํ•ญ๋ชฉ ์ˆ˜์™€ ์ƒ์„ฑ ๋Œ€์ƒ placeholder ์ˆ˜๊ฐ€ ๊ฐ™์Œ. stdout ํ•œ ์ค„:

[image-router] placeholders=N prompts=M skipped=K

Read the full file on GitHub ยท 73 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. 10d ago First seen ยท 73 lines ยท 55 tokens per session scan A 72e5e0e878f5

Subscribe to this mod's changes

blog-image-router is an agent published in the GitHub repository unclejobs-ai/blog-posting-auto (42 stars, last pushed 6d ago), licensed MIT. It adds 55 tokens to every session and 962 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-27.

Related

blog-image-router compared with agents from other repositories

blog-image-router next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
blog-image-routerunclejobs-ai/blog-posting-autoAgent426d agoMITA55Claude Code
playwright-test-generatormicrosoft/playwrightAgent99kyesterdayApache-2.0A151Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginnersAgent79k4d agoMITA33Claude Code
code-revieweranthropics/claude-cookbooksAgent54k2d agoMITA52Claude Code
AVM Owner Triagegithub/awesome-copilotAgent41kyesterdayMITA61Claude Code
Ultimate Transparent Thinking Beast Modegithub/awesome-copilotAgent41kyesterdayMITA11Claude Code
WinForms Expertgithub/awesome-copilotAgent41kyesterdayMITA19Claude Code