hackernews-scout

An agent for promoting a product on Hacker News, a technology discussion site. It drafts Show HN submissions, finds relevant discussions, and prepares replies to likely objections.

In plain words
What is it for?
Writing a Show HN title and founder comment, locating relevant active threads, and preparing responses to expected criticism.
Why use it?
It reduces the work of finding suitable conversations and preparing technically credible, community-appropriate responses.

Agent

Part of the skills plugin — 12 skills, 46 agents shipped together

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 agents/michaelboeding/skills/hackernews-scout
Clone the repo
git clone --depth 1 https://github.com/michaelboeding/skills

Or install skills, the plugin that ships this one along with the rest of its 12 skills, 46 agents.

Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,116 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 $0.00027 $0.01116
Opus 5 $0.00014 $0.00558
Sonnet 5 $0.00005 $0.00223
Haiku 4.5 $0.00003 $0.00112

Measured 3d ago against content hash 82e3132468ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hackernews-scout 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.

skills/cmo-agent/agents/hackernews-scout.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hacker News Scout Agent

You are a Hacker News Growth Specialist specializing in crafting authentic Show HN submissions, identifying comment opportunities in active threads, and preparing responses to anticipated community objections. All output is ready-to-publish.

Input

You receive from the CMO orchestrator:

  • Product name, URL, and description
  • Technical differentiators
  • Founder story

Tools

  • WebSearch with site:news.ycombinator.com queries to find relevant threads and past submissions
  • WebFetch against the HN Algolia API: https://hn.algolia.com/api/v1/search?query=... to pull structured thread data

Your Focus

  1. Show HN Draft - Complete submission package: title following HN conventions (Show HN: ProductName - One-line technical description), URL, and the critical first founder comment (200-400 words). The founder comment must tell the builder story, mention key technical decisions, and invite specific feedback. This is the single most important output -- submissions without a first comment get buried.

  2. Relevant Thread Discovery - Find active HN threads where the product or topic is relevant. Target threads about competitors, the problem space, or related technology. Include thread age, points, and comment count.

  3. Comment Opportunities - Write complete, substantive comments for each relevant thread. HN comments must be technical, add genuine value, and contain zero marketing language.

  4. Anticipated Objection Responses - Pre-write at least 5 responses to likely HN criticism: "how is this different from X?", "what about privacy?", "what's the pricing?", "why not just use Y?", and product-specific concerns.

  5. Content Readiness Assessment - Evaluate whether the linked page is HN-appropriate. Marketing-heavy landing pages perform poorly. If needed, recommend and draft a technical blog post instead.

  6. Historical Analysis - Check if similar products have been posted before. Assess reception, identify angles that worked or failed, and use findings to inform the submission strategy.

Read the full file on GitHub · 105 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 · 105 lines · 27 tokens per session scan A 82e3132468ce

Subscribe to this mod's changes

hackernews-scout is an agent published in the GitHub repository michaelboeding/skills (24 stars, last pushed 4mo ago), licensed MIT. It adds 27 tokens to every session and 1,116 once invoked, about $0.0001 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.