social-posts

social-posts is a skill for Claude Code, Codex from milind-soni/OpenMausBot. It costs 65 tokens per session (1,547 once invoked), scanned A, original, Apache-2.0.

A preview guide for social-media posts that shows how a post will appear on platforms such as Instagram, LinkedIn, X, TikTok and Facebook.

In plain words
What is it for?
It is for generating platform-specific previews for social posts, including image carousels and short-video formats.
Why use it?
It helps catch layout, text and media problems before a post is published.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It is for generating platform-specific previews for social posts, including image carousels and short-video formats.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/milind-soni/openmausbot/social-posts
About the project

OpenMausBot is an open-source chat application where users interact with multiple AI bots, each backed by an agent, model, computer, and connected apps. It is for people who want to run Claude, Codex, or Grok-based agents locally through a messaging-style interface. Its catalogue add-ons provide skills and instructions for working with the application.

milind-soni/OpenMausBot · 13,395 stars · on GitHub · openmausbot.com

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 milind-soni/OpenMausBot --skill social-posts
Clone the repo
git clone --depth 1 https://github.com/milind-soni/OpenMausBot

Made for: Claude Code, Codex.

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-posts

README.md
[![agentmods](https://agentmods.dev/badge/skills/milind-soni/openmausbot/social-posts/github.svg)](https://agentmods.dev/skills/milind-soni/openmausbot/social-posts)
Your own site
<a href="https://agentmods.dev/skills/milind-soni/openmausbot/social-posts"><img src="https://agentmods.dev/badge/skills/milind-soni/openmausbot/social-posts/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-posts

Your own site · 80×15
<a href="https://agentmods.dev/skills/milind-soni/openmausbot/social-posts"><img src="https://agentmods.dev/badge/skills/milind-soni/openmausbot/social-posts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,547 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 $0.00065 $0.01547
Opus 5.5 $0.00026 $0.00619
Sonnet 5.5 $0.00013 $0.00309
Haiku 4.5 $0.00006 $0.00155

Measured 2d ago against content hash b47065edfc49, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

social-posts 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 2d 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/social-posts/SKILL.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Social post previews

Whenever you write a social post, show it as it will look. Don't ask first, and don't wait for an answer: show the preview and carry on with the work. It's for social posts only, so skip it for a blog post or an article.

Fill the template

posts.html sits next to this guide, in the folder named by this skill's root. Copy it to your working folder and replace only the JSON in the posts-data block at the top. Keep the rest, including the licence notice at the top of the file.

{
  "account": { "name": "Juniper Coffee", "handle": "junipercoffee", "subtitle": "Roasters in Leeds", "avatar": "avatar.png" },
  "posts": [{
    "title": "Autumn launch",
    "when": "Draft",
    "text": "Text for every platform that has none of its own.",
    "media": [{ "src": "photo.jpg", "alt": "A bag of coffee" }],
    "platforms": {
      "instagram": { "text": "Its own caption.", "media": [] },
      "x": {}
    }
  }]
}
  • platforms decides which previews show: instagram, linkedin, x, threads, facebook, tiktok, reels, shorts. Each can have its own text, media and when; anything left out comes from the post. Write each platform's text for that platform.
  • A plan of several posts is several entries in posts; they stack on one page.
  • With no avatar the card shows initials. No media and empty text still draw properly.
  • media items: an image { "src", "alt" }, a video { "video", "poster", "duration" } (seconds), or a slide (below). Add width and height when a file's size can't be read, so its shape can be checked.

Show it

Pick by what the post has:

The post has Do this
Only text, or slides you wrote Send the file's whole text as html. At most 256 KB, and the template is about 48 KB.
Images on disk Make a folder: the template as index.html, the images beside it, named in src ("src": "photo.jpg"). Show it with path. png, jpg, gif, webp, avif and svg work. The folder holds at most 5 MB and 200 files, and index.html at most 256 KB, so shrink big images first.
An image on the web Download it into the folder first. The chat blocks images from other sites, and the card says so.
A video on disk Put it in the folder and name it: { "video": "clip.mp4", "poster": "frame.jpg" }. It plays and seeks in the chat, at any size: mp4 (H.264), webm or mov. It plays from the folder and isn't copied, so keep the file there unchanged. If it is moved, edited or deleted, the card falls back to the poster until you show the page again. Always add a poster.
A public link publish_page leaves video out and says so, and the public page shows the poster with a play mark. The chat card keeps playing the video.

Read the full file on GitHub · 93 lines

Files

What ships with it

2 files 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. 2d ago First seen · 93 lines · 65 tokens per session scan A b47065edfc49

Subscribe to this mod's changes

social-posts is a skill published in the GitHub repository milind-soni/OpenMausBot (13,395 stars, last pushed today), licensed Apache-2.0. It adds 65 tokens to every session and 1,547 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-11-04.

Related

social-posts compared with skills from other repositories

social-posts next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
social-postsmilind-soni/OpenMausBotSkill13ktodayApache-2.0A65Claude Code, Codex
search-docselie222/rakazoSkill7.2ktodayApache-2.0A28Claude Code, Codex
say-helloelie222/rakazoSkill7.2ktodayApache-2.0A31Claude Code, Codex
chroniclemicrosoft/vscodeSkill195ktodayMITA72Claude Code, Codex
winapp-mauimicrosoft/winappCliSkill1.4ktodayMITA68Claude Code
winui-setupmicrosoft/winappCliSkill1.4ktodayMITA73Claude Code
computer-use-linuxagent-sh/computer-use-linuxSkill810yesterdayMITA39Claude Code