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.
npx skills add tang-vu/social-posting-skills --skill post-hackernewsgit clone --depth 1 https://github.com/tang-vu/social-posting-skillsWrote 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.
[](https://agentmods.dev/skills/tang-vu/social-posting-skills/post-hackernews)<a href="https://agentmods.dev/skills/tang-vu/social-posting-skills/post-hackernews"><img src="https://agentmods.dev/badge/skills/tang-vu/social-posting-skills/post-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.
<a href="https://agentmods.dev/skills/tang-vu/social-posting-skills/post-hackernews"><img src="https://agentmods.dev/badge/skills/tang-vu/social-posting-skills/post-hackernews.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00014 | $0.01032 |
| Opus 5 | $0.00007 | $0.00516 |
| Sonnet 5 | $0.00003 | $0.00206 |
| Haiku 4.5 | $0.00001 | $0.00103 |
Grade A, and why
post-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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hacker News Posting Skill
Platform Overview
Hacker News (news.ycombinator.com) is Y Combinator's community for hackers, founders, and intellectual curiosity. The audience is senior developers, CTOs, and tech founders. Content that reaches the front page can drive 10K-50K visits in hours. The community is extremely anti-marketing and values substance over polish.
Platform Constraints
- Title: Max ~80 characters (longer titles get truncated)
- Submissions: URL or text (not both simultaneously)
- Show HN: Prefix for sharing what you've built
- Ask HN: Prefix for asking the community a question
- Comments: Plain text, supports markdown-lite
- No images: HN is text-only, no media uploads
- No tags/hashtags: None
Posting Steps (Browser Automation)
- Navigate to
https://news.ycombinator.com/submit - Wait for the submit form to load (must be logged in)
- Type the title (ASCII English only)
- For projects: prefix with "Show HN: "
- For questions: prefix with "Ask HN: "
- Either:
- Type a URL in the "url" field (for link submissions)
- OR type text in the "text" field (for text submissions)
- Click "submit" button
- Verify submission appears on /newest
Content Format
Show HN (Sharing Your Project)
Title: Show HN: {Product Name} -- {What it does in <10 words}
Text:
{1 paragraph: What problem does it solve?}
{1 paragraph: What's technically interesting about your approach?}
{1 paragraph: Current status and what feedback you're looking for}
{Optional: link to source code if open-source}
Link Submission
Title: {Original article title or descriptive summary}
URL: {Link to high-quality content}
Ask HN
Title: Ask HN: {Specific, clear question}
Text:
{Context for the question}
{What you've already tried or considered}
{Specific aspect you need help with}
Title Strategy
The title is 90% of what determines success on HN. Rules:
Do:
- Use the original article title (if submitting a link)
- Be specific and factual: "Show HN: An open-source alternative to Notion built in Rust"
- Include technical details that make it interesting
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.
- 11d ago First seen · 122 lines · 14 tokens per session scan A be50223f0744
post-hackernews is a skill published in the GitHub repository tang-vu/social-posting-skills (9 stars, last pushed 6mo ago), licensed MIT. It adds 14 tokens to every session and 1,032 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 2026-08-31.
Other skills, from other repositories
auto-research
Research uncertain questions with an explicit, user-approved web search or ChatGPT consultation, then present options and wait for implementation approval.
agent-orchestrator
Meta-skill que orquestra todos os agentes do ecossistema. Scan automatico de skills, match por capacidades, coordenacao de workflows multi-skill e registry management.
android-ui-journey-testing
XML-specified Android UI journey testing, interactive step execution, assertion verification, and JSON outcome reporting.
agent-self-scheduling
Schedule AI agent runs with cron, loops, or external clocks while avoiding unsafe tight autonomous timers.
e2e-automator
Build robust end-to-end test suites with Playwright or Cypress. Covers page objects, fixtures, visual testing, and CI integration.
accessibility-tester
Professional Accessibility Tester Expert skill. Implement robust test suites and automated quality checks for modern web/mobile applications.