news-digest-mcp: Instructions file for Claude Code

CLAUDE.md

news-digest-mcp CLAUDE.md is an instructions file for Claude Code from goldjee/news-digest-mcp. It costs 4,811 tokens per session, scanned A, original, Apache-2.0.

A CLAUDE.md instruction file describing how to develop and run a news server. The server collects news from Telegram channel previews and RSS or Atom feeds, which are subscription formats for regularly published updates.

In plain words
What is it for?
Installing dependencies, linting and formatting the code, building the server, and manually checking its JSON-based communication.
Why use it?
It gives a coding agent repository-specific guidance about commands, structure, checks, and how to run the server.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions .claude-plugin; mentions CLAUDE.md; mentions Claude Code.

This is goldjee/news-digest-mcp's own configuration. It tells Claude Code how to work on news-digest-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 news-digest-mcp configures →

Reuse

Borrowing it

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

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/goldjee/news-digest-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/goldjee/news-digest-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,811 This file is loaded in full into every session.
When invoked 4,811 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 $0.04811 $0.04811
Opus 5.5 $0.01924 $0.01924
Sonnet 5.5 $0.00962 $0.00962
Haiku 4.5 $0.00481 $0.00481

Measured 2mo ago against content hash 267d92bcc9a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

news-digest-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 · 257 lines

How it starts

The opening of the file, as written. The whole thing — 257 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

An MCP server (stdio transport) that aggregates news from Telegram channel previews and RSS/Atom feeds into structured JSON. It's designed to be launched by a host agent (e.g. osaurus) as bun src/server.ts on the host machine directly — no sandbox — so it has network access and a writable filesystem for state.

Commands

bun install               # install deps
bun run lint              # bunx biome lint
bun run format            # bunx biome format
bun run check             # bunx biome check (lint + format + organize imports)
bun run build             # bundle to dist/server.js (what CI publishes; not needed to develop)
bun src/server.ts         # run the MCP server directly (reads stdio)

There is no test suite. Biome is the only linter/formatter; a lefthook pre-commit hook runs bun run check --write on staged JS/TS/JSON/CSS files and re-stages fixes automatically.

To smoke-test the server manually, pipe JSON-RPC messages into it over stdio (see README.md for the exact initialize / tools/call sequence).

Architecture

Entry point: src/server.ts registers two MCP tools (get_news, list_sources) and delegates all logic to src/lib/run.ts. The server itself is just wiring — no business logic lives here. Both tools publish an outputSchema and return the payload as structuredContent and as serialized JSON in a text block (the spec's backwards-compatibility path for clients that read only content). list_sources wraps its list as { sources: [...] } because structuredContent must be a JSON object, not a bare array. Note that the content text block is not merely a fallback: osaurus, the host this was built for, reads only content and ignores structuredContent entirely, so that block is what a host's per-call output cap gets measured against — which is why get_news pages (below), and why its exact shape is configurable (src/lib/envelope.ts).

Read the full file on GitHub · 257 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. 2mo ago First seen · 257 lines · 4,811 tokens per session scan A 267d92bcc9a3

Subscribe to this mod's changes

news-digest-mcp CLAUDE.md is an instructions file published in the GitHub repository goldjee/news-digest-mcp (0 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 4,811 tokens to every session, about $0.0192 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 2026-08-31.

Related

news-digest-mcp CLAUDE.md compared with instructions from other repositories

news-digest-mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
news-digest-mcp CLAUDE.mdgoldjee/news-digest-mcpInstructions file02mo agoApache-2.0A4,811Claude 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