teaser-block-writer

teaser-block-writer is a skill for Claude Code from ur-grue/autopunk-media-skills. It costs 49 tokens per session (1,751 once invoked), scanned A, original, MIT.

A writing helper for short recommendations that lead readers from one article or content item to another.

In plain words
What is it for?
Use it to write related-article cards, “read next” blocks, “previously on” summaries, and other short links between content pieces.
Why use it?
It turns longer content descriptions into brief teaser text for related-content areas, newsletters, and series recaps.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the autopunk-media-skills plugin — 187 skills shipped together

Good fit Use it to write related-article cards, “read next” blocks, “previously on” summaries, and other short links between content pieces.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ur-grue/autopunk-media-skills/teaser-block-writer
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 ur-grue/autopunk-media-skills --skill teaser-block-writer
Clone the repo
git clone --depth 1 https://github.com/ur-grue/autopunk-media-skills

Made for: Claude Code.

Or install autopunk-media-skills, the plugin that ships this one along with the rest of its 187 skills.

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 teaser-block-writer

README.md
[![agentmods](https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/teaser-block-writer/github.svg)](https://agentmods.dev/skills/ur-grue/autopunk-media-skills/teaser-block-writer)
Your own site
<a href="https://agentmods.dev/skills/ur-grue/autopunk-media-skills/teaser-block-writer"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/teaser-block-writer/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 teaser-block-writer

Your own site · 80×15
<a href="https://agentmods.dev/skills/ur-grue/autopunk-media-skills/teaser-block-writer"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/teaser-block-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,751 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00049 $0.01751
Opus 5 $0.00024 $0.00875
Sonnet 5 $0.00010 $0.00350
Haiku 4.5 $0.00005 $0.00175

Measured 8d ago against content hash fb429bf0e64c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

teaser-block-writer 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 8d 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/production-support/reference/teaser-block-writer/SKILL.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Teaser Block Writer

What This Skill Does

Writes "read next," "related articles," or "previously on" teaser blocks for web pages, newsletters, or app interfaces — short, click-worthy summaries that drive readers from one piece of content to another.

When To Use This Skill

  • You are building a web article page and need 3–5 related-article teasers for the sidebar or footer
  • You are assembling a newsletter and need short teaser summaries for each linked article
  • You are creating a "previously on this series" block to help readers catch up before a new installment
  • You need to write promotional teaser cards for a homepage, category page, or content hub

What You Need To Provide

Required: The articles or content pieces to tease (provide headlines and a brief description of each, or the full text if available); the context where the teasers will appear (sidebar, newsletter, homepage, end-of-article block); the number of teasers needed.

Optional: The article the reader is currently viewing (so teasers can be editorially relevant, not random); maximum character or word count per teaser; whether each teaser should include a category label, publication date, or reading time; the publication's teaser style (headline-only, headline-plus-one-sentence, headline-plus-two-sentences); tone (news-formal, conversational, provocative).

How the Assistant Approaches This

  1. Identifies the hook in each article. Reads the provided material and finds the single most compelling element — the fact, question, or revelation that would make a reader click. This becomes the core of the teaser, not a generic summary.

  2. Writes each teaser as a self-contained unit. Every teaser must work on its own — a reader encountering it in a sidebar or newsletter should understand what the article offers without needing additional context. The teaser answers: "What will I learn or experience if I click this?"

  3. Differentiates teasers from each other. When writing a block of 3–5 teasers, ensures each one uses a different hook structure (question, statistic, bold claim, scene-setting detail) so the block does not feel repetitive. Variety in opening structure increases the chance that at least one teaser resonates with any given reader.

Read the full file on GitHub · 112 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 8d ago First seen · 112 lines · 49 tokens per session scan A fb429bf0e64c

Subscribe to this mod's changes

teaser-block-writer is a skill published in the GitHub repository ur-grue/autopunk-media-skills (32 stars, last pushed 12d ago), licensed MIT. It adds 49 tokens to every session and 1,751 once invoked, about $0.0002 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 2026-09-04.