ghost-mcp CLAUDE.md

ghost-mcp CLAUDE.md is an instructions file for coding agents from stemcreations/ghost-mcp. It costs 1,019 tokens per session, scanned A, original, MIT.

A set of Claude Code instructions for developing an MCP server that styles and manages Ghost blogs. Ghost is a publishing system for blogs and websites, and MCP lets an AI agent use connected tools.

In plain words
What is it for?
It helps develop and run the Ghost MCP server, check its live API connection, inspect or style a blog, and maintain code quality with formatting and lint checks.
Why use it?
It gives contributors repository-specific guidance for setup, testing, formatting, and architecture. It also lets the agent work from the blog's rendered HTML and CSS instead of guessing its selectors.

Instructions file

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.

agentmods
npx agentmods add instructions/stemcreations/ghost-mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/stemcreations/ghost-mcp

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 ghost-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/stemcreations/ghost-mcp/claude-md.svg)](https://agentmods.dev/instructions/stemcreations/ghost-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/stemcreations/ghost-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/stemcreations/ghost-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,019 This file is loaded in full into every session.
When invoked 1,019 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01019 $0.01019
Opus 5 $0.00509 $0.00509
Sonnet 5 $0.00204 $0.00204
Haiku 4.5 $0.00102 $0.00102

Measured 4d ago against content hash 88f4c8141daa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ghost-mcp CLAUDE.md 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 4d 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.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What this is

A FastMCP (Python) MCP server for styling and managing a Ghost blog. The differentiator is vision: it fetches the live blog's rendered HTML + CSS so the model can write CSS against real selectors instead of guessing. Vision and styling ship first; the authenticated client is generic so the full Ghost Admin API (posts, members, tags, …) follows as thin tool wrappers.

This is a public repo. Keep code clean, typed, and documented; keep the README current for contributors.

Commands

uv manages everything (no global pip, no manual venv). If uv isn't found in a fresh shell, it's at ~/.local/bin/uv.exe; open a new terminal or prepend it to PATH.

uv sync                                  # install deps + the package (editable)
uv run python scripts/check_connection.py  # smoke-test live Admin API credentials
uv run fastmcp dev src/ghost_mcp/server.py # run with the MCP Inspector
uv run ghost-mcp                         # run the server over stdio
uv run ruff format                       # format
uv run ruff check                        # lint
uv run pytest                            # run all tests
uv run pytest tests/test_auth.py::test_audience_is_admin  # run a single test

Architecture

Layered package under src/ghost_mcp/, each layer with one responsibility:

  • config.py: load/validate env (GHOST_ADMIN_URL, GHOST_STAFF_ACCESS_TOKEN, optional GHOST_API_VERSION).
  • errors.py: the GhostError hierarchy (ConfigError, GhostAPIError).
  • admin/: authenticated Admin API: auth.py mints JWTs, client.py is the HTTP client.
  • vision/: structure.py fetches the public page + CSS (no auth).
  • tools/: thin MCP wrappers; one module per domain, each exposing register(mcp).
  • server.py: builds the FastMCP server and wires tools; main() is the entry point.

The core convention: business logic lives in a service module (admin/, vision/) as a plain, testable function; the tools/ wrapper only adapts it to MCP. To add a tool group: write+test the logic, add tools/<name>.py with register(mcp), and call it from register_all in tools/__init__.py.

Read the full file on GitHub · 83 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. 4d ago First seen · 83 lines · 1,019 tokens per session scan A 88f4c8141daa

Subscribe to this mod's changes

ghost-mcp CLAUDE.md is an instructions file published in the GitHub repository stemcreations/ghost-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 1,019 tokens to every session, about $0.0051 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.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens