What is mcp-medium-reader AGENTS.md?

Repository instructions for a Node.js server that lets AI tools read Medium articles through an external Ruby package. They describe commands, architecture, platform support, and cookie handling.

Use them when working on the mcp-medium-reader project, including its TypeScript build, Vitest tests, command-line development mode, or committed build files.

They give coding agents the project-specific rules needed to build, test, package, and safely modify the repository.

mcp-medium-reader AGENTS.md — Instructions file for Codex and OpenCode by ZhgChgLi: Repository instructions for a Node.js server that lets A

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/zhgchgli/mcp-medium-reader/agents-md

Clone the repo

git clone --depth 1 https://github.com/ZhgChgLi/mcp-medium-reader

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/zhgchgli/mcp-medium-reader/agents-md.svg)](https://agentmods.dev/instructions/zhgchgli/mcp-medium-reader/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/zhgchgli/mcp-medium-reader/agents-md"><img src="https://agentmods.dev/badge/instructions/zhgchgli/mcp-medium-reader/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,405 This file is loaded in full into every session.

When invoked 1,405 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.

Model	Per session	Once invoked
Fable 5.1	$0.01405	$0.01405
Opus 5	$0.00702	$0.00702
Sonnet 5	$0.00281	$0.00281
Haiku 4.5	$0.00140	$0.00140

Measured 5d ago against content hash 761637d7c0c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

mcp-medium-reader AGENTS.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 5d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

mcp-medium-reader CLAUDE.md — 92% identical, 8 lines differ

AGENTS.md · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

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

Commands

npm run build — tsc → dist/ (the bin/mcp-medium-reader.js shim imports from dist/, so unbuilt source won't run via the bin).
npm run dev -- <subcommand> — run via tsx without building (e.g. npm run dev -- doctor).
npm test — full vitest run.
npm test -- test/runtime.test.ts — single test file. npm test -- -t "name" for a single test by name.
npm run build:watch / npm run test:watch — watch modes.
prepack runs tsc, so npm pack / publish always ships fresh dist/. The repo also commits dist/ because git-based installs (npm i -g github:…) skip the prepare step — keep committed dist/ in sync when shipping a fix that needs to be installable from git.

Architecture

Cross-platform MCP stdio server that wraps the external ZMediumToMarkdown Ruby gem (≥ 3.5.2). The Node process never talks to Medium directly; every tool call shells out to the gem and post-processes its stdout/stderr. Runs on macOS / Linux / Windows.

Cookie ownership boundary

Cookies (sid / uid / cf_clearance / _cfuvid) are managed entirely by the gem in its own AES-256-GCM encrypted cache at ~/.zmediumtomarkdown (mode 0600). The MCP server does NOT store, inject, or scrub cookies. Users populate the gem cache by running ZMediumToMarkdown --auth once in their own Terminal — the gem opens Chrome via ferrum for sign-in / Cloudflare clearance and caches the result. The MCP transport gives the gem a non-TTY stdin which trips its --non-interactive auto-detection, so the gem can never do its own Chrome flow under MCP.

The MCP server holds no Medium-side state of its own — no cookies, no proxy URLs, no per-user secrets. Earlier drafts had a Cloudflare Worker proxy pair (medium_host / miro_medium_host) stored at <config_dir>/credentials.json; that whole layer was removed. The only on-disk state mcp-medium-reader manages now is runtime.json (the bound Ruby runtime).

Read the full file on GitHub · 40 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.

5d ago First seen · 40 lines · 1,405 tokens per session scan A 761637d7c0c8

Subscribe to this mod's changes

mcp-medium-reader AGENTS.md is an instructions file published in the GitHub repository ZhgChgLi/mcp-medium-reader (2 stars, last pushed 3mo ago), licensed MIT. It adds 1,405 tokens to every session, about $0.0070 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.

Research ai claude claude-ai claude-code claude-code-plugin claude-skills

hyperclaude CLAUDE.md

Claude Code instructions for zeikar/hyperclaude, covering claude.md, what this repo is, commands, local dev install (dogfooding) and the bridge.

zeikar/hyperclaude · 4,954 tokens

embedded-systems-architect AGENTS.md

Instructions for Zachariah9420/embedded-systems-architect: This repository ships an agent skill for embedded-systems and edge-AI development work.

Zachariah9420/embedded-systems-architect · 177 tokens

embedded-systems-architect GEMINI.md

Instructions for Zachariah9420/embedded-systems-architect: This repository ships an agent skill for embedded-systems and edge-AI development work.

Zachariah9420/embedded-systems-architect · 116 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

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

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