hackernews-cli

A command-line tool for browsing and using Hacker News, a discussion site about technology and startups. Browsing and searching are available without signing in; voting, posting, commenting, saving, and hiding require login.

In plain words
What is it for?
Use it to read story feeds, Ask HN, Show HN, jobs, comments, searches, and public user profiles, or to manage your own Hacker News activity when logged in.
Why use it?
It lets developers work with Hacker News from the terminal instead of switching to a web browser.

Skill for Claude CodeCodex

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 skills/itamarzand88/cli-anything-web/hackernews-cli
Any agent
npx skills add ItamarZand88/CLI-Anything-WEB --skill hackernews-cli
Clone the repo
git clone --depth 1 https://github.com/ItamarZand88/CLI-Anything-WEB

Made for: Claude Code, Codex.

Per session 105 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 878 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00105 $0.00878
Opus 5 $0.00053 $0.00439
Sonnet 5 $0.00021 $0.00176
Haiku 4.5 $0.00011 $0.00088

Measured 3d ago against content hash c1e13034309f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hackernews-cli 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 3d 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/skills/hackernews-cli/SKILL.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

cli-web-hackernews

Hacker News on the command line: browsing and search need no auth; voting, submitting, commenting, favoriting, and hiding need login. Install: pip install cli-web-hackernews

Commands

Browse (no auth)

  • stories top|new|best|ask|show|jobs — story feeds. Options: -n/--limit N (default 30)
  • stories view STORY_ID — story + comment tree. Options: -n/--limit N (comments, default 10), --no-comments
  • search stories QUERY / search comments QUERY — Algolia search. Options: -n/--limit N (default 20), --page N (0-indexed), --sort-date (by date instead of relevance)
  • user view USERNAME — public profile (karma, member since, about)

Account actions (auth required)

  • upvote ITEM_ID — upvote a story or comment
  • submit -t TITLE [-u URL] [--text BODY] — submit a link, or omit -u for Ask HN
  • comment PARENT_ID TEXT — comment on a story or reply to a comment
  • favorite ITEM_ID / hide ITEM_ID — save / hide a story
  • user favorites|submissions|threads [USERNAME] — your activity (or another user's, where public). Options: -n/--limit N
  • auth login (username/password prompt), auth login-browser, auth status, auth logout

Examples

# Front page, top 10
cli-web-hackernews stories top -n 10 --json

# A story with its first 5 comments
cli-web-hackernews stories view 47530330 -n 5 --json

# Search recent stories about Rust
cli-web-hackernews search stories "rust" --sort-date -n 10 --json

# Submit an Ask HN (requires login)
cli-web-hackernews submit -t "Ask HN: Best CLI tooling?" --text "Looking for recommendations" --json

# Upvote then favorite a story
cli-web-hackernews upvote 47530330 --json && cli-web-hackernews favorite 47530330 --json

JSON output

Add --json for structured output. Stories: {id, title, url, score, by, descendants, age, domain}. Search results: {objectID, title, url, author, points, num_comments}. Users: {id, karma, member_since, about_plain, total_submissions}. Actions: {success, item_id, action}. Errors: {"error": true, "code": "...", "message": "..."}.

Read the full file on GitHub · 62 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. 3d ago First seen · 62 lines · 105 tokens per session scan A c1e13034309f

Subscribe to this mod's changes

hackernews-cli is a skill published in the GitHub repository ItamarZand88/CLI-Anything-WEB (216 stars, last pushed 9d ago), licensed MIT. It adds 105 tokens to every session and 878 once invoked, about $0.0005 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 2026-08-30.