social-media-excerpt

social-media-excerpt is a skill for Claude Code from ur-grue/autopunk-media-skills. It costs 33 tokens per session (1,635 once invoked), scanned A, original, MIT.

A social-media excerpt tool selects a shareable passage or argument from a published article and formats it for specific social platforms.

In plain words
What is it for?
It creates posts for X, Instagram, and LinkedIn, including teasers for paywalled articles and long-form features.
Why use it?
It lets publishers reuse existing journalism for social posts without changing the article’s meaning or voice.

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 It creates posts for X, Instagram, and LinkedIn, including teasers for paywalled articles and long-form features.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ur-grue/autopunk-media-skills/social-media-excerpt
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 social-media-excerpt
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 social-media-excerpt

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/ur-grue/autopunk-media-skills/social-media-excerpt"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/social-media-excerpt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,635 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 $0.00033 $0.01635
Opus 5 $0.00016 $0.00817
Sonnet 5 $0.00007 $0.00327
Haiku 4.5 $0.00003 $0.00163

Measured 8d ago against content hash 8426d0d48f02, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

social-media-excerpt 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/magazine-journalism/distribution/social-media-excerpt/SKILL.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Social Media Excerpt

What This Skill Does

Extracts and reformats the most shareable passage or argument from a published article into platform-specific social media posts — without rewriting the journalism.

When To Use This Skill

  • Your article is published and you need ready-to-post social content that drives traffic or builds brand
  • You want to tease a paywalled article on social without giving away its core findings
  • You are repurposing a long-form feature across a social media calendar and need multiple distinct posts from a single piece
  • You want the excerpt to sound like the article — not like marketing copy

What You Need To Provide

Required: Full article text or a substantial excerpt (at least 400 words); which platforms to format for (X/Twitter, Instagram, LinkedIn, or all three) Optional: Publication handle/username for attribution; specific passage you think is the most shareable; tone directive (threads/commentary style vs. quote-card style vs. straight excerpt); whether to include a link and call-to-read; paywall status

How the Assistant Approaches This

  1. Reads the full article and identifies 2–3 candidate excerpts: the most arresting sentence or statistic, the strongest quote from a source, and the article's most counterintuitive or surprising claim
  2. For each platform, formats the excerpt to fit the platform's natural register and character conventions — not just truncation, but structural adaptation
  3. For X/Twitter: a 240-character lead post that works standalone, optionally followed by a 2–3 tweet thread continuation
  4. For LinkedIn: a slightly longer, context-setting frame before the excerpt, closing with a professional takeaway
  5. For Instagram: a quote-card format with a caption that extends the thought
  6. Preserves the article's voice — these posts should read like the journalism, not like promotional copy for it
  7. Closes with a "Next Step" note: which post to publish first, whether to schedule the thread or post all platforms simultaneously, and whether thumbnail-concept-brief should be run to create a matching visual asset for the Instagram quote card

Read the full file on GitHub · 111 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 · 111 lines · 33 tokens per session scan A 8426d0d48f02

Subscribe to this mod's changes

social-media-excerpt is a skill published in the GitHub repository ur-grue/autopunk-media-skills (32 stars, last pushed 12d ago), licensed MIT. It adds 33 tokens to every session and 1,635 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.