integrate-product-site

integrate-product-site is a skill for Claude Code, Codex from kostja94/openblog. It costs 54 tokens per session (1,102 once invoked), scanned A, original, MIT.

A workflow for adding OpenBlog, a blog module, to an existing product website. It connects the blog’s URL, navigation, footer, logo, deployment setup, and brand assets with the main site.

In plain words
What is it for?
Use it when adding a /blog section or blog subdomain, matching an existing header and footer, or combining the blog with a monorepo, which is a repository containing multiple related projects.
Why use it?
It avoids treating a blog module as a complete website and helps keep the blog consistent with an existing product site. It also distinguishes integrating with an existing site from creating a new standalone blog.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is Do you already have a product site? If yes, start from **[INTEGRATION.md](../../INTEGRATION.md)** (subdirectory / subdomain / monorepo). Use `create-openblog` o.

Good fit Use it when adding a /blog section or blog subdomain, matching an existing header and footer, or combining the blog with a monorepo, which is a repository containing multiple related projects.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/kostja94/openblog
agentmods
npx agentmods add skills/kostja94/openblog/integrate-product-site

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 integrate-product-site

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/kostja94/openblog/integrate-product-site"><img src="https://agentmods.dev/badge/skills/kostja94/openblog/integrate-product-site.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,102 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 $0.00054 $0.01102
Opus 5.5 $0.00022 $0.00441
Sonnet 5.5 $0.00011 $0.00220
Haiku 4.5 $0.00005 $0.00110

Measured 3d ago against content hash d0c93bab03fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

integrate-product-site 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 3d 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/integrate-product-site/SKILL.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Integrate Product Site

OpenBlog is a blog module, not a full site builder. This skill wires the blog into an existing product domain so header/footer/logo match the main site.

This is the recommended default when the user mentions a product URL, marketing site, existing nav/footer, or “add blog to my site”.

Agent: confirm with the user

Before scaffolding, ask:

Do you already have a product site? If yes, start from INTEGRATION.md (subdirectory / subdomain / monorepo). Use create-openblog only for a greenfield demo.

If they have a site URL → proceed below. If greenfield only → hand off to setup-blog-module.

Start by reading INTEGRATION.md — it is the single entry point.

When to use

  • User has a product site and wants /blog, a subdomain, or monorepo merge
  • User needs navbar/footer/logo aligned with the main site
  • User asks to run npm run integrate or configure chrome.mode

Three layers (do not confuse)

Layer Where You replace?
Site Chrome templates/next/src/chrome/ Yes — match main site
Blog Chrome packages/components + config Toggle via components.optional
Brand assets public/brand/ or CDN in config Yes

Reuse components from the product site first. If a required navbar, footer, breadcrumb, article layout, or other named component does not exist, use Bricks component-builder for construction guidance, then implement it in the target repository. Do not copy Bricks guidance into OpenBlog.

Choose integration pattern

Pattern URL example Doc
Subdirectory (recommended) yourproduct.com/blog/post integrations/patterns/subdirectory.md
Monorepo merge Same deploy as main Next app integrations/patterns/monorepo.md
Subdomain blog.yourproduct.com/post integrations/patterns/subdomain.md

Read the full file on GitHub · 112 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. 3d ago Changed · +2 lines d0c93bab03fb
  2. 2mo ago First seen · 110 lines · 54 tokens per session scan A 5d817ea947f9

Subscribe to this mod's changes

integrate-product-site is a skill published in the GitHub repository kostja94/openblog (7 stars, last pushed 4d ago), licensed MIT. It adds 54 tokens to every session and 1,102 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 2026-08-31.

Related

Other skills, from other repositories