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 ur-grue/autopunk-media-skills --skill social-media-visual-batchgit clone --depth 1 https://github.com/ur-grue/autopunk-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/ur-grue/autopunk-media-skills/social-media-visual-batch)<a href="https://agentmods.dev/skills/ur-grue/autopunk-media-skills/social-media-visual-batch"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/social-media-visual-batch/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/ur-grue/autopunk-media-skills/social-media-visual-batch"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/social-media-visual-batch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- 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 | $0.00059 | $0.02690 |
| Opus 5 | $0.00030 | $0.01345 |
| Sonnet 5 | $0.00012 | $0.00538 |
| Haiku 4.5 | $0.00006 | $0.00269 |
Grade A, and why
social-media-visual-batch 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.
How it starts
The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Social Media Visual Batch
What This Skill Does
Produces a coordinated batch of image prompts for a social media campaign — a set of 5 to 10 visually consistent images that work together as a series while each standing alone, suitable for a planned content push, a show launch, or a recurring visual format.
When To Use This Skill
- You are launching a new show, series, or publication and need a set of social media images that introduce the project visually
- You are planning a week or month of content and want a batch of images that look like they belong together without being identical
- You have established a visual identity and need to extend it into a series of social media posts that maintain consistency
- You are promoting a specific episode, issue, or piece of content across multiple posts and need visual variety within a single aesthetic
What You Need To Provide
Required:
- The campaign goal: what are these images for? (show launch, episode promotion, thematic series, editorial calendar fill)
- The visual style or reference to an existing visual identity brief
- How many images you need (typically 5–10)
- The primary platform (Instagram, Twitter/X, LinkedIn) — this sets the default format
- A description of the themes or subjects to cover across the batch
Optional:
- Whether images should form a narrative sequence (each image is a chapter) or a thematic collection (each image is a standalone in the same visual world)
- Text overlay requirements (captions only, or text embedded in the image)
- Any specific subjects or scenes that must be included
- Color palette if defined (or reference to an existing color-palette-brief)
- Image generation tool (Midjourney, Flux, DALL-E)
How the Assistant Approaches This
- Establishes the visual anchor string — the shared aesthetic DNA that will appear in every prompt in the batch, ensuring all images are recognizably from the same project
- Defines the batch structure: sequential (tells a story or progression across the posts) or thematic (varied subjects within a consistent visual world) — and maps out what each of the N images will depict
- Writes each individual prompt around a distinct scene or subject, ensuring no two images are compositionally identical while all images share the same lighting approach, palette, and register
- Plans visual variety deliberately: varies composition (close/medium/wide), subject (person/object/environment), and mood within the shared aesthetic — so the batch feels like a curated editorial series, not a set of variations on one image
- Outputs the batch with a brief content note per image suggesting caption direction or where in a posting calendar the image fits
- Closes with a "Next Step" note: which image to generate first to establish the visual anchor, whether to review the grid layout before scheduling (for Instagram), and whether cover-image-pipeline should be run if any batch image also needs to be produced in multiple platform formats
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.
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.
- 8d ago First seen · 190 lines · 59 tokens per session scan A f43a701ff7c6
social-media-visual-batch is a skill published in the GitHub repository ur-grue/autopunk-media-skills (32 stars, last pushed 12d ago), licensed MIT. It adds 59 tokens to every session and 2,690 once invoked, about $0.0003 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.
Other skills, from other repositories
zernio
Schedule posts, manage inbox, broadcasts, sequences, and automations across 14 platforms from the CLI.
xiaoyuzhou-podcast-notes
A workflow that turns a public Xiaoyuzhou FM podcast episode into structured Markdown notes and a saved transcript. Xiaoyuzhou FM is a Chinese podcast platform.
Article Repurposer
Takes a long-form article and repurposes it into multiple formats: tweet thread, LinkedIn post, TL;DR, and key quotes.
Social Post Thread Writer
Converts a blog post, idea, or document into an engaging Twitter/X or LinkedIn thread with hooks and CTAs.
c-research
Summarize web URLs, PDFs, YouTube videos, and podcasts using the summarize CLI. Instantly extract key points from any content type without manual reading. Useful for research, link digests, and media review.
X Twitter Source Packet Builder
Converts reviewed X/Twitter evidence into compact source packets for research and writing workflows.