repurpose-visual

repurpose-visual is an agent for coding agents from AgriciDaniel/claude-repurpose. It costs 75 tokens per session (1,454 once invoked), scanned A, original, MIT.

A visual-content agent that turns source content into scripts and plans for Instagram, TikTok, Pinterest, Snapchat, and quote graphics.

In plain words
What is it for?
Use it to create carousel scripts, video scripts, captions, pin descriptions, story ideas, and image-generation plans.
Why use it?
One piece of content needs different formats and styles on different visual platforms; this produces those adaptations from shared source material.

Agent

Part of the claude-repurpose plugin — 21 skills, 6 agents, 1 hook shipped together

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.

agentmods
npx agentmods add agents/agricidaniel/claude-repurpose/repurpose-visual
Clone the repo
git clone --depth 1 https://github.com/AgriciDaniel/claude-repurpose

Or install claude-repurpose, the plugin that ships this one along with the rest of its 21 skills, 6 agents, 1 hook.

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 repurpose-visual

README.md
[![agentmods](https://agentmods.dev/badge/agents/agricidaniel/claude-repurpose/repurpose-visual.svg)](https://agentmods.dev/agents/agricidaniel/claude-repurpose/repurpose-visual)
Your own site
<a href="https://agentmods.dev/agents/agricidaniel/claude-repurpose/repurpose-visual"><img src="https://agentmods.dev/badge/agents/agricidaniel/claude-repurpose/repurpose-visual.svg" alt="Measured on agentmods" height="20"></a>
Per session 75 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,454 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00075 $0.01454
Opus 5 $0.00037 $0.00727
Sonnet 5 $0.00015 $0.00291
Haiku 4.5 $0.00007 $0.00145

Measured 4d ago against content hash 857e14321862, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

repurpose-visual 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 4d 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.

agents/repurpose-visual.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a visual content director who understands Instagram's algorithm and image-first storytelling.

Your Task

Generate visual content for Instagram, TikTok, Pinterest, Snapchat, and quote graphics from the provided content atoms.

Process

  1. Read the atoms file provided in your prompt
  2. Load sub-skills:
    • repurpose-instagram/SKILL.md for Instagram rules
    • repurpose-tiktok/SKILL.md for TikTok rules
    • repurpose-pinterest/SKILL.md for Pinterest rules
    • repurpose-snapchat/SKILL.md for Snapchat rules
    • repurpose-quotes/SKILL.md for quote card rules
  3. Load repurpose/references/image-sourcing.md for 3-tier image pipeline
  4. Load repurpose/references/voice-adaptation.md for tone
  5. Generate all outputs

Instagram Outputs

Carousel Script (7-10 slides)

  • Slide 1: Bold hook headline (5-8 words), "swipe left" prompt, visual pattern interrupt
  • Slides 2-8: One insight per slide, mix text-heavy and visual slides
  • Final slide: CTA (save, follow, share) + summary takeaway
  • Format: 1080x1350 (4:5) portrait
  • Consider mixed media suggestion (image+video slides = 2.33% vs 1.80%)

Caption

  • Front-load value in first 125 chars (visible before "more")
  • Engagement question
  • 3-5 niche hashtags at end

Reel Script

  • 30-90 second script with timestamps
  • Hook in first 3 seconds
  • Jump cut markers every 3-5 seconds
  • Text overlay suggestions at key moments
  • Structure: Hook → Context → Value → CTA

TikTok Outputs

Video Script (15-60s)

  • Hook in first 0.5-1.5 seconds (completion rate is #1 algorithm signal)
  • Jump cuts every 2-3 seconds to maintain attention
  • Text overlay timestamps for every section (avoid bottom 20% for TikTok UI)
  • Structure: Hook → Context → Value → CTA
  • Audio direction: trending sound, voiceover, or original
  • Write as spoken words, not written prose -- fragments, pauses, emphasis marks

Carousel / Photo Mode (2-10 slides)

  • 1080x1350 (4:5) format, text-forward
  • One idea per slide, large readable text
  • Hook slide + value slides + CTA slide
  • Caption: 150-300 chars with 3-5 hashtags

Read the full file on GitHub · 152 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. 4d ago First seen · 152 lines · 75 tokens per session scan A 857e14321862

Subscribe to this mod's changes

repurpose-visual is an agent published in the GitHub repository AgriciDaniel/claude-repurpose (142 stars, last pushed 4mo ago), licensed MIT. It adds 75 tokens to every session and 1,454 once invoked, about $0.0004 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.

Related

Other agents, from other repositories

visual-architect

Freeze a visual brief and compile bounded, model-aware prompts for complex, branded, text-heavy, or ambiguous image work. Use only when the main banana skill supplies the user request, current model constraints, and any references. Never execute generation.

AgriciDaniel/banana-claude · 52 tokens

visual-critic

Independently inspect generated or edited image files against a frozen brief. Use after generation for high-value, branded, text-heavy, edited, or multi-candidate work. Never generate, edit, or rewrite files.

AgriciDaniel/banana-claude · 47 tokens

blog-researcher

Research specialist for blog content. Finds current statistics (2025-2026), verifies sources against tier 1-3 quality standards, discovers Pixabay/Unsplash/Pexels images, and identifies competitive content gaps. Invoked for statistic research, image discovery, and competitive analysis tasks during blog writing…

AgriciDaniel/claude-blog · 66 tokens

blog-reviewer

Quality assessment specialist for blog posts. Runs the full 5-category, 100-point scoring system, identifies issues by severity, checks for AI editorial style diagnostics, validates source quality, and flags unsupported factual or first-hand claims. Invoked for quality review tasks during blog workflows.

AgriciDaniel/claude-blog · 59 tokens

blog-writer

Content generation specialist for blog posts. Writes optimized articles with answer-first formatting, proper heading hierarchy, sourced statistics, and natural readability. Follows the 6 pillars of dual optimization. Invoked for content writing and rewriting tasks during blog workflows.

AgriciDaniel/claude-blog · 52 tokens

blog-translator

Specialized translation and localization agent for blog content. Produces native-quality translations of an entire blog post, optimized for both human readers and search engines, with format preservation (markdown, MDX, HTML, frontmatter, schema JSON-LD, SVG charts) and locale-correct number, date, currency, and quote…

AgriciDaniel/claude-blog · 105 tokens