agentmods.dev

hn-companion-mcp: Instructions file for Claude Code

CLAUDE.md

hn-companion-mcp CLAUDE.md is an instructions file for Claude Code from georgeck/hn-companion-mcp. It costs 319 tokens per session, scanned A, original, MIT.

Project instructions for an MCP server that retrieves Hacker News comments and prepares them for Claude prompts. Hacker News is a site where people share and discuss technology stories.

In plain words
What is it for?
Use them when starting the server, running its command-line tool, changing comment retrieval or prompt formatting, or checking its MCP API.
Why use it?
They explain the server's commands, files, communication format, and coding conventions so the agent can work on it correctly.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is georgeck/hn-companion-mcp's own configuration. It tells Claude Code how to work on hn-companion-mcp 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 hn-companion-mcp configures →

not rated 0repo 1y ago A scan 319 tokens original MIT
View source ↗ georgeck/hn-companion-mcp
Reuse

Borrowing it

Nothing to install: this file belongs to georgeck/hn-companion-mcp. 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/georgeck/hn-companion-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/georgeck/hn-companion-mcp

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 hn-companion-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/georgeck/hn-companion-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/georgeck/hn-companion-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/georgeck/hn-companion-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/georgeck/hn-companion-mcp/claude-md/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 hn-companion-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/georgeck/hn-companion-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/georgeck/hn-companion-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 319 This file is loaded in full into every session.
When invoked 319 The same file — it is already loaded in full.
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 $0.00319 $0.00319
Opus 5.5 $0.00128 $0.00128
Sonnet 5.5 $0.00064 $0.00064
Haiku 4.5 $0.00032 $0.00032

Measured 2mo ago against content hash 6725bce78952, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

hn-companion-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 2mo 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 · 32 lines

What it actually says

HN Companion MCP Guidelines

Commands

  • Start server: npm start
  • Run CLI: npm run cli -- <post-id-or-url>
  • Install dependencies: npm install or pnpm install

Code Structure

  • Entry points: index.js (CLI) and server.js (API server)
  • Core functionality in lib/ directory:
    • fetch-comments.js: HN data retrieval
    • format-prompt.js: Claude prompt generation
    • utils.js: Utility functions
  • MCP configuration: mcp.json

MCP Protocol

  • The server supports JSON-RPC 2.0 for MCP communication
  • Main endpoints:
    • POST /: JSON-RPC endpoint for initialize and invoke methods
    • POST /api/summarize: Legacy REST endpoint for direct API calls
  • Implementation follows the Model Context Protocol specification

Code Style

  • Type: ES Modules (import/export)
  • Imports: Group by external/internal, alphabetical order
  • Formatting: Use consistent whitespace, 4-space indentation
  • Naming: camelCase for variables/functions, PascalCase for classes
  • Functions: Always include JSDoc comments for functions
  • Error Handling: Use try/catch with specific error messages
  • Async: Use async/await pattern for asynchronous operations
  • Logging: Use console.log with descriptive prefixes
  • API Responses: Follow { status, data|error, message } structure
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. 2mo ago First seen · 32 lines · 319 tokens per session scan A 6725bce78952

Subscribe to this mod's changes

hn-companion-mcp CLAUDE.md is an instructions file published in the GitHub repository georgeck/hn-companion-mcp (0 stars, last pushed 1y ago), licensed MIT. It adds 319 tokens to every session, about $0.0013 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 2026-09-01.

Research
Related

hn-companion-mcp CLAUDE.md compared with instructions from other repositories

hn-companion-mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
hn-companion-mcp CLAUDE.mdgeorgeck/hn-companion-mcpInstructions file01y agoMITA319Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode