antwork-repurpose

antwork-repurpose is a skill for Claude Code from iker-gonzalez/antwork-skills. It costs 103 tokens per session (993 once invoked), scanned A, original, MIT.

A skill for turning one source piece, such as a blog post, newsletter, transcript, or talk, into separate posts suited to different social platforms.

In plain words
What is it for?
Use it to repurpose source content into a coordinated set of platform-specific posts. The source can be supplied as text, a URL, or a transcript.
Why use it?
It avoids copying the same text everywhere by preserving the main idea while adapting the format and writing style for each platform and account.

Skill for Claude Code

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

Part of the antwork-skills plugin — 12 skills, 5 agents, 2 MCP servers shipped together

Good fit Use it to repurpose source content into a coordinated set of platform-specific posts. The source can be supplied as text, a URL, or a transcript.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/iker-gonzalez/antwork-skills/antwork-repurpose
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 iker-gonzalez/antwork-skills --skill antwork-repurpose
Clone the repo
git clone --depth 1 https://github.com/iker-gonzalez/antwork-skills

Made for: Claude Code.

Or install antwork-skills, the plugin that ships this one along with the rest of its 12 skills, 5 agents, 2 MCP servers.

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 antwork-repurpose

README.md
[![agentmods](https://agentmods.dev/badge/skills/iker-gonzalez/antwork-skills/antwork-repurpose/github.svg)](https://agentmods.dev/skills/iker-gonzalez/antwork-skills/antwork-repurpose)
Your own site
<a href="https://agentmods.dev/skills/iker-gonzalez/antwork-skills/antwork-repurpose"><img src="https://agentmods.dev/badge/skills/iker-gonzalez/antwork-skills/antwork-repurpose/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 antwork-repurpose

Your own site · 80×15
<a href="https://agentmods.dev/skills/iker-gonzalez/antwork-skills/antwork-repurpose"><img src="https://agentmods.dev/badge/skills/iker-gonzalez/antwork-skills/antwork-repurpose.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 103 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 993 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.
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 $0.00103 $0.00993
Opus 5 $0.00051 $0.00496
Sonnet 5 $0.00021 $0.00199
Haiku 4.5 $0.00010 $0.00099

Measured 10d ago against content hash 7697bfb666c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

antwork-repurpose 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 10d 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/antwork-repurpose/SKILL.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repurposing one piece into platform-native posts

Antwork binds each post to a single account, and platform is derived from that account. Repurposing means writing a distinct, native version per platform — never one body copy-pasted everywhere — and grouping them under a shared campaign_id. This workflow codifies the mistakes assistants make when atomizing content.

1. Anchor the source

Identify the one source piece and its core idea. If the user hasn't pasted it, ask for the text, URL, or transcript. Extract the spine before reshaping:

  • The single biggest claim or takeaway.
  • 3–5 supporting points or moments that can each stand alone.
  • Any quotable line, stat, or hook.

This spine is what gets reshaped per platform — not the prose itself.

2. Pick targets and pull each voice

Confirm which accounts to publish to (list_social_accounts if unsure — note account_id, platform, token health). For each target platform, before writing:

  • get_post_context(platform, account_id) — brand, that account's voice profile, recent posts, voiceStale flag. Each account has its own voice; LinkedIn-you and X-you are not the same writer. If voiceStale, say so and offer the antwork-voice refresh first.

3. Reshape — do not reuse

Write a native variant per platform. Reusing one body across platforms is the core failure: X's 280-char cap mangles LinkedIn prose, and LinkedIn-length paragraphs look broken on Threads. Reshape for each:

  • X (280) — the sharpest single claim, or a thread broken into beats. No fluff.
  • Threads (500) — conversational, one idea, lighter than LinkedIn.
  • LinkedIn (3000) — room to tell the story; hook line, whitespace, a takeaway. Longer (300–600 words) is fine only here.
  • Instagram (2200) — caption that works under a visual; front-load the hook.
  • Facebook / YouTube / Pinterest / TikTok — match the platform's norm and limit.

Honor every hard limit (X 280, Threads 500, Pinterest 800, IG 2200, LinkedIn 3000, TikTok 4000, YouTube 5000, FB 63206) — schedule_post/publish_post reject anything over. Match the voice profile's tone, emoji and hashtag policy, and CTA style per account. Avoid AI tells ("Here's the thing:", "Let me break it down", emoji-heavy openers).

Read the full file on GitHub · 60 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. 10d ago First seen · 60 lines · 103 tokens per session scan A 7697bfb666c9

Subscribe to this mod's changes

antwork-repurpose is a skill published in the GitHub repository iker-gonzalez/antwork-skills (0 stars, last pushed 2mo ago), licensed MIT. It adds 103 tokens to every session and 993 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 2026-08-31.

Related

Other skills, from other repositories