blog-cms

blog-cms is a skill for Claude Code, Codex from kostja94/openblog. It costs 78 tokens per session (1,490 once invoked), scanned A, original, MIT.

An entry skill for OpenBlog, a Git-based blog system where Markdown files are stored in Git and rendered as website pages. It helps connect the blog module to a product site.

In plain words
What is it for?
Use it to integrate or set up an OpenBlog section with article pages, listings, RSS, sitemaps, and structured metadata.
Why use it?
It gives coding agents a clear way to choose the right blog setup or integration workflow without treating the whole website as a CMS.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions AGENTS.md.

Good fit Use it to integrate or set up an OpenBlog section with article pages, listings, RSS, sitemaps, and structured metadata.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kostja94/openblog/blog-cms
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.

Any agent
npx skills add kostja94/openblog --skill blog-cms
Clone the repo
git clone --depth 1 https://github.com/kostja94/openblog

Made for: Claude Code, Codex.

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-cms

README.md
[![agentmods](https://agentmods.dev/badge/skills/kostja94/openblog/blog-cms/github.svg)](https://agentmods.dev/skills/kostja94/openblog/blog-cms)
Your own site
<a href="https://agentmods.dev/skills/kostja94/openblog/blog-cms"><img src="https://agentmods.dev/badge/skills/kostja94/openblog/blog-cms/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 blog-cms

Your own site · 80×15
<a href="https://agentmods.dev/skills/kostja94/openblog/blog-cms"><img src="https://agentmods.dev/badge/skills/kostja94/openblog/blog-cms.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,490 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 $0.00078 $0.01490
Opus 5 $0.00039 $0.00745
Sonnet 5 $0.00016 $0.00298
Haiku 4.5 $0.00008 $0.00149

Measured 9d ago against content hash 8079316fba44, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

blog-cms 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 9d 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/blog-cms/SKILL.md · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Blog CMS (OpenBlog)

OpenBlog is an open-source, Git-based CMS for blogs — an agent-native blog module mounted on product websites (typically /blog). Markdown in Git is the source of truth; Next.js renders list/post pages, RSS, sitemap, and JSON-LD.

Git is the CMS. Your coding agent is the admin.

This skill is the entry point. It routes to the right workflow, then reads the matching skill in this pack when present.

Not in scope: whole-site CMS, WordPress-style dashboards, site-wide SEO/GEO — pair with marketing-skills for growth workflows on the host site.


Install

# Entry skill only
npx skills add kostja94/openblog --skill blog-cms

# Recommended — entry + primary workflows
npx skills add kostja94/openblog --skill blog-cms integrate-product-site setup-blog-module

# Full pack (content ops included)
npx skills add kostja94/openblog --skill '*'

# List all skills in the repo
npx skills add kostja94/openblog --list

Repo: github.com/kostja94/openblog · Docs: INTEGRATION.md

When working inside the OpenBlog monorepo, read AGENTS.md and skill files under skills/ directly.


Step 1 — Route the user

Ask before editing files if the path is unclear:

OpenBlog has two common paths:

  1. Existing product site → integrate /blog via INTEGRATION.md (recommended)
  2. Try it firstnpx create-openblog my-blog
    Which applies to you? If you have a product site URL, share it.
User situation Action Follow-up skill
Existing product / marketing site — wants /blog, matching nav/logo Read INTEGRATION.md first integrate-product-site
Greenfield — no site yet, local demo Scaffold with create-openblog setup-blog-module
Module already wired — add or edit a post Content model + validate create-post
Pre-merge / deploy checks on blog posts Validate + build validate-blog-seo
Ready to merge and deploy Git → CI checklist publish
Ready to merge and deploy Git → CI → CDN checklist publish

Read the full file on GitHub · 153 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. 9d ago First seen · 153 lines · 78 tokens per session scan A 8079316fba44

Subscribe to this mod's changes

blog-cms is a skill published in the GitHub repository kostja94/openblog (6 stars, last pushed 11d ago), licensed MIT. It adds 78 tokens to every session and 1,490 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.