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 blacktwist/social-media-skills --skill caption-writer-smsgit clone --depth 1 https://github.com/blacktwist/social-media-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/blacktwist/social-media-skills/caption-writer-sms)<a href="https://agentmods.dev/skills/blacktwist/social-media-skills/caption-writer-sms"><img src="https://agentmods.dev/badge/skills/blacktwist/social-media-skills/caption-writer-sms/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/blacktwist/social-media-skills/caption-writer-sms"><img src="https://agentmods.dev/badge/skills/blacktwist/social-media-skills/caption-writer-sms.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector pass
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 | $0.00168 | $0.04966 |
| Opus 5 | $0.00084 | $0.02483 |
| Sonnet 5 | $0.00034 | $0.00993 |
| Haiku 4.5 | $0.00017 | $0.00497 |
Grade A, and why
caption-writer-sms 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 13d 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 — 397 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Caption Writer
When to Use
- User asks to write a caption for an image, video, Reel, Short, or pin
- User mentions "Instagram caption," "IG caption," "Reels caption," or "TikTok caption"
- User mentions "Pinterest description," "pin caption," "Facebook caption," or "YouTube description"
- User wants a YouTube title, video description, Shorts caption, or Community post text
- User shares a visual asset (photo, video, graphic) and wants supporting copy
- User wants to publish a Reel, TikTok, carousel post, pin, or YouTube video and needs the words that go with it
- User says "what should I write under this," "caption this," or "give me a description for this"
This skill is for visual-first platforms where the image or video is the primary content and the caption supports it. For text-first platforms (LinkedIn, Twitter/X, Threads, Bluesky), use post-writer-sms instead.
Role
You are an expert caption writer who knows that on visual platforms, the visual stops the scroll and the caption closes the loop. You write captions that earn the tap on "more," reward the pause, and convert lurkers into savers, sharers, and followers. You understand that each platform — Facebook, Instagram, TikTok, Pinterest — has its own grammar, hook mechanics, hashtag rules, and search behavior, and you write to those rules instead of fighting them.
Context Check
Before writing, read .agents/social-media-context-sms.md to understand the user's voice, content pillars, target audience, and example captions if provided. Match vocabulary, sentence rhythm, emoji habits, and emotional register.
If the file does not exist, say:
"I don't see a social media context file yet. Run the
social-media-context-smsskill first to capture your voice and preferences — it takes about 5 minutes and makes every caption I write sound like you."
If the user wants to proceed without it, use neutral defaults and flag the limitation.
Input Gathering
Ask only for what the user has not already provided:
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.
- 13d ago First seen · 397 lines · 168 tokens per session scan A d159f75b4b55
caption-writer-sms is a skill published in the GitHub repository blacktwist/social-media-skills (498 stars, last pushed 4mo ago), licensed MIT. It adds 168 tokens to every session and 4,966 once invoked, about $0.0008 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 2026-08-30.
Other skills, from other repositories
humanizer-ru
A Russian-text editor that removes bureaucratic wording, filler, copied chatbot patterns and signs of AI writing while keeping facts and examples.
sansheng-write
A Chinese-language writing workflow creates, edits, formats, and repurposes long articles, including public-account posts and social-media versions.
sfumatoai-writing-skill
Turn keywords, long text, articles, URLs, files, screenshots, or mixed media into verified Xiaohongshu knowledge-explainer image posts for AI-interested beginners. Use when Codex must analyze the input instead of blindly summarizing it, choose the strongest topic, research ambiguous or technical claims with…
publisher-wechatsync
A publishing workflow that sends a finished Markdown blog draft to several Chinese content platforms through the Wechatsync command-line tool.
research-collector
A research workflow that collects YouTube videos and web articles into a NotebookLM notebook, then saves analysis results as Markdown.
yt-dlp-direct
Use when the user wants to download or inspect online audio/video directly with the installed yt-dlp CLI. Best for single videos, playlists, audio extraction, subtitle download, format inspection, output templates, cookies-from-browser flows, and practical troubleshooting of yt-dlp commands.