blog-to-site

blog-to-site is a skill for Claude Code from psd401/psd-claude-plugins. It costs 124 tokens per session (1,101 once invoked), scanned A, original, MIT.

A publishing workflow for turning an author's text and images into a live blog post on a website. It keeps the author's wording unchanged while handling page details, image preparation, a code review request, automated checks, and release.

In plain words
What is it for?
Use it to publish a post from a Google Doc, pasted text, or file, add its byline and metadata, prepare images, and ship the site change after checks pass.
Why use it?
It removes repetitive steps from publishing while preserving the supplied writing. It also stops before making changes when required tools or access are missing.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; reads .claude/ paths; mentions AGENTS.md.

Part of the psd-productivity plugin — 33 skills, 1 command, 1 agent shipped together

Good fit Use it to publish a post from a Google Doc, pasted text, or file, add its byline and metadata, prepare images, and ship the site change after checks pass.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/psd401/psd-claude-plugins/blog-to-site
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 psd401/psd-claude-plugins --skill blog-to-site
Clone the repo
git clone --depth 1 https://github.com/psd401/psd-claude-plugins

Made for: Claude Code.

Or install psd-productivity, the plugin that ships this one along with the rest of its 33 skills, 1 command, 1 agent.

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-to-site

README.md
[![agentmods](https://agentmods.dev/badge/skills/psd401/psd-claude-plugins/blog-to-site/github.svg)](https://agentmods.dev/skills/psd401/psd-claude-plugins/blog-to-site)
Your own site
<a href="https://agentmods.dev/skills/psd401/psd-claude-plugins/blog-to-site"><img src="https://agentmods.dev/badge/skills/psd401/psd-claude-plugins/blog-to-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 blog-to-site

Your own site · 80×15
<a href="https://agentmods.dev/skills/psd401/psd-claude-plugins/blog-to-site"><img src="https://agentmods.dev/badge/skills/psd401/psd-claude-plugins/blog-to-site.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 124 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,101 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00124 $0.01101
Opus 5.5 $0.00050 $0.00440
Sonnet 5.5 $0.00025 $0.00220
Haiku 4.5 $0.00012 $0.00110

Measured 14d ago against content hash 1dbdd332aad9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

blog-to-site scanned grade A with 1 finding 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 14d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- `git`, `curl`, and Node.js 20.9 or later with npm.
plugins/psd-productivity/skills/blog-to-site/SKILL.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Blog to site

Turns an author's text and images into a live post at https://psd401.ai/writing/<slug>.

The author's words are published exactly as written. You handle the byline, tags, description, formatting, images and shipping. You do not edit the writing.

The site's repository holds the detailed, current instructions, next to the code they describe. This skill gets a checkout and follows them, so the two cannot drift apart. If anything here disagrees with the repository's playbook, the playbook wins.

What you need

  • git, curl, and Node.js 20.9 or later with npm.
  • gh, signed in with write access to psd401/psd401.ai. Check with gh auth status.
  • For a Google Doc: read access from the account you run as, through the gws CLI (gws auth login -s drive) or another Google Workspace tool that can export Docs.
  • For images: sips (macOS) or ImageMagick to crop them.

If anything is missing, say what and stop before changing anything.

1. Get a checkout of the site

Use the first of these that applies:

  1. $PSD401_AI_REPO is set: use that directory.

  2. The current directory is inside a checkout whose origin is psd401/psd401.ai (git remote get-url origin): use it.

  3. Otherwise clone one:

    gh repo clone psd401/psd401.ai "$(mktemp -d)/psd401.ai"
    

    Clone the full history. The bundle's log.md is generated from it, and a shallow clone writes a wrong one.

Run npm ci in the checkout if node_modules/ is missing. Never commit on whatever branch an existing checkout is on; the ship steps make a new branch.

2. Read the playbook

In the checkout, read these in full before starting:

  • AGENTS.md: the site's rules.
  • .claude/skills/psd401-publish/post.md: this task, step by step.
  • .claude/skills/psd401-publish/ship.md: branch, checks, PR, CI, merge, and the live check.

If post.md is not there, the checkout is out of date. Run git fetch origin and read the files from origin/main (git show origin/main:.claude/skills/psd401-publish/post.md).

Read the full file on GitHub · 113 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. 14d ago Changed · -1 lines 1dbdd332aad9
  2. 25d ago First seen · 114 lines · 124 tokens per session scan A 868df223cbb7

Subscribe to this mod's changes

blog-to-site is a skill published in the GitHub repository psd401/psd-claude-plugins (2 stars, last pushed 9d ago), licensed MIT. It adds 124 tokens to every session and 1,101 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-11.