Ghost-MCP-Server: Instructions file for Claude Code

CLAUDE.md

Ghost-MCP-Server CLAUDE.md is an instructions file for Claude Code from jgardner04/Ghost-MCP-Server. It costs 5,985 tokens per session, scanned C, original, MIT.

Security instructions for a Ghost MCP server based on common web-security guidance from OWASP. They require validating and cleaning inputs, protecting file paths, preventing script injection, and avoiding unsafe database queries.

In plain words
What is it for?
Use them when handling user input, file uploads or paths, HTML content, security headers, or database operations.
Why use it?
They reduce the risk that user-controlled data could expose files, run unwanted browser code, or alter database queries.

Instructions file for Claude Code

Written for Claude Code: SessionStart hook event. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is jgardner04/Ghost-MCP-Server's own configuration. It tells Claude Code how to work on Ghost-MCP-Server 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 Ghost-MCP-Server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jgardner04/Ghost-MCP-Server. 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/jgardner04/Ghost-MCP-Server/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/jgardner04/Ghost-MCP-Server

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 Ghost-MCP-Server CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jgardner04/ghost-mcp-server/claude-md.svg)](https://agentmods.dev/instructions/jgardner04/ghost-mcp-server/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/jgardner04/ghost-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/jgardner04/ghost-mcp-server/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 5,985 This file is loaded in full into every session.
When invoked 5,985 The same file — it is already loaded in full.
Security scan C 2 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 $0.05985 $0.05985
Opus 5 $0.02993 $0.02993
Sonnet 5 $0.01197 $0.01197
Haiku 4.5 $0.00598 $0.00598

Measured 8d ago against content hash 04fb8bffb1dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade C, and why

Ghost-MCP-Server CLAUDE.md scanned grade C with 2 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 8d 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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

<!-- rtk-instructions v2 -->

Makes network callslowCapability

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

rtk curl <url> # Compact HTTP responses (70%)
CLAUDE.md · 555 lines

How it starts

The opening of the file, as written. The whole thing — 555 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.

Security Requirements (OWASP Guidelines)

All code written for this project MUST follow OWASP security best practices to prevent common vulnerabilities:

Required Security Measures:

  1. Input Validation & Sanitization

    • Validate ALL user inputs using Zod schemas from src/schemas/
    • HTML sanitization is integrated into the schema layer (src/schemas/common.js)
    • Reject inputs that don't match expected patterns
    • Use allowlists for acceptable values, not denylists
  2. Path Traversal Prevention

    • Always resolve and validate file paths against expected directories
    • Use path.resolve() and verify paths start with allowed base directories
    • Never use user input directly in file system operations
    • Generate cryptographically secure filenames for uploads
  3. XSS (Cross-Site Scripting) Prevention

    • Sanitize all HTML content before storage or display
    • Escape special characters in user-generated content
    • Use Content Security Policy headers
    • Never use eval() or new Function() with user input
  4. SQL Injection Prevention

    • Use parameterized queries (though this project uses Ghost API, not direct SQL)
    • Escape special characters in filter strings
    • Validate query parameters against expected formats
  5. Authentication & Authorization

    • Use constant-time comparison for secrets (crypto.timingSafeEqual)
    • Implement rate limiting on sensitive endpoints
    • Validate API keys and tokens securely
    • Never log sensitive information
  6. Additional Security Controls

    • Set appropriate HTTP security headers
    • Implement request size limits
    • Use HTTPS for external requests
    • Validate URLs to prevent SSRF attacks
    • Clean up temporary files securely
    • Log security events appropriately

Security Libraries in Use:

  • zod - Runtime type validation and schema definition (primary validation)
  • sanitize-html - HTML sanitization (integrated into Zod schemas)
  • express-rate-limit - Rate limiting
  • crypto - Secure random generation and comparisons
  • helmet - HTTP security headers
  • joi - Legacy validation, allowlisted in 4 specific files only. New joi imports are blocked by ESLint no-restricted-imports — see eslint.config.js. Use Zod schemas under src/schemas/.

Read the full file on GitHub · 555 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. 8d ago First seen · 555 lines · 5,985 tokens per session scan C 04fb8bffb1dd

Subscribe to this mod's changes

Ghost-MCP-Server CLAUDE.md is an instructions file published in the GitHub repository jgardner04/Ghost-MCP-Server (7 stars, last pushed today), licensed MIT. It adds 5,985 tokens to every session, about $0.0299 per session on Opus 5. A static security scan graded it C with 2 findings (hidden instructions, makes network calls). 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

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 · 5,153 tokens

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

next.js AGENTS.md

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

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 · 4,469 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

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