A read-only command-line and MCP client for Hacker News, a website where people share and discuss technology stories. It can query stories, comments, users, and other Hacker News data through the site's public API.

Use it to browse top, newest, best, Ask HN, Show HN, and job stories, or to inspect specific stories, comments, and user profiles.

It lets tools retrieve Hacker News content without opening the website manually or setting up authentication. JSON output is available for scripts and other software to parse.

hackernews — Skill for Claude Code and Codex by Riddhimaan-Senapati

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.

Any agent

npx skills add Riddhimaan-Senapati/unofficial-HackerNews-MCP-CLI --skill hackernews

Clone the repo

git clone --depth 1 https://github.com/Riddhimaan-Senapati/unofficial-HackerNews-MCP-CLI

Made for: Claude Code, Codex.

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/skills/riddhimaan-senapati/unofficial-hackernews-mcp-cli/hackernews/github.svg)](https://agentmods.dev/skills/riddhimaan-senapati/unofficial-hackernews-mcp-cli/hackernews)

Your own site

<a href="https://agentmods.dev/skills/riddhimaan-senapati/unofficial-hackernews-mcp-cli/hackernews"><img src="https://agentmods.dev/badge/skills/riddhimaan-senapati/unofficial-hackernews-mcp-cli/hackernews/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/riddhimaan-senapati/unofficial-hackernews-mcp-cli/hackernews"><img src="https://agentmods.dev/badge/skills/riddhimaan-senapati/unofficial-hackernews-mcp-cli/hackernews.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,464 The whole file, excluding the scripts and references it only reads on demand.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00040	$0.01464
Opus 5.5	$0.00016	$0.00586
Sonnet 5.5	$0.00008	$0.00293
Haiku 4.5	$0.00004	$0.00146

Measured 1mo ago against content hash 289140161fec, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

hackernews 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 1mo 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.

skills/hackernews/SKILL.md · 182 lines

How it starts

The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.

HackerNews CLI and MCP

A read-only client for the official HackerNews API (https://github.com/HackerNews/API). It ships two entry points over one shared async client, so both behave the same way:

hn, a Typer CLI with Rich tables, for terminal use.
hn-mcp, a FastMCP 4 server exposing the same operations as MCP tools, for MCP clients like Claude Desktop.

The API needs no authentication and has no rate limit. Timestamps are Unix epoch seconds. The title, text, and about fields contain HTML.

Setup

From the project root (uses uv):

uv sync

Run both commands through uv so they use the project's locked .venv:

uv run hn stories top
uv run hn-mcp

The examples below use installed commands. From a clone, prefix each command with uv run.

CLI usage

Every command takes --format (-f): table (the default), json, markdown, or text. Use --json as a shortcut for --format json. If you pass both options, --json takes precedence. Markdown and text output strip HTML.

Story lists

hn stories top                 # front-page (top) stories, 30 by default
hn stories top --limit 10      # or -n 10
hn stories top --offset 30 --limit 10   # skip the first 30
hn stories new                 # newest stories
hn stories best                # best recent stories
hn stories ask                 # latest Ask HN posts
hn stories show                # latest Show HN posts
hn stories job                 # latest job postings

The top, new, and best lists draw from up to 500 stories. The ask, show, and job lists draw from up to 200. --offset plus --limit must stay within the category's cap, or the CLI exits non-zero with a suggestion.

A single item

hn item 8863           # story, comment, job, or poll by id

A comment thread

hn comments 8863               # top-level comments + one level of replies
hn comments 8863 --depth 2     # nest replies 2 levels deep (-d)
hn comments 8863 --limit 50    # up to 50 comments per level (-n)
hn comments 8863 --offset 10   # skip the first 10 top-level comments

Read the full file on GitHub · 182 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.

1mo ago Changed · +22 lines · -119 tokens per session 289140161fec
2mo ago Changed · +6 lines · +4 tokens per session 83356e032e46
2mo ago First seen · 154 lines · 155 tokens per session scan A aa91b81a6d0e

Subscribe to this mod's changes

hackernews is a skill published in the GitHub repository Riddhimaan-Senapati/unofficial-HackerNews-MCP-CLI (0 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 1,464 once invoked, about $0.0002 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.

Research

hackernews next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
hackernewsRiddhimaan-Senapati/unofficial-HackerNews-MCP-CLI	Skill	0	1mo ago	MIT	A	40	Claude Code, Codex
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	2d ago	MIT	A	200	Claude Code, Codex
playwright-climicrosoft/playwright	Skill	100k	2d ago	Apache-2.0	A	19	Claude Code
browser-automationopenclaw/openclaw	Skill	394k	yesterday	MIT	A	36	Claude Code
systematic-debuggingobra/superpowers	Skill	315k	5d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code