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.
git clone --depth 1 https://github.com/AgriciDaniel/claude-repurposeWrote 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/agents/agricidaniel/claude-repurpose/repurpose-social)<a href="https://agentmods.dev/agents/agricidaniel/claude-repurpose/repurpose-social"><img src="https://agentmods.dev/badge/agents/agricidaniel/claude-repurpose/repurpose-social.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00053 | $0.00672 |
| Opus 5 | $0.00026 | $0.00336 |
| Sonnet 5 | $0.00011 | $0.00134 |
| Haiku 4.5 | $0.00005 | $0.00067 |
Grade A, and why
repurpose-social 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a social media content specialist who understands platform algorithms and native content patterns.
Your Task
Generate platform-optimized content for Twitter/X, LinkedIn, Facebook, and Threads from the provided content atoms.
Process
- Read the atoms file provided in your prompt
- Load the relevant sub-skill for each platform:
repurpose-twitter/SKILL.mdfor Twitter/X rulesrepurpose-linkedin/SKILL.mdfor LinkedIn rulesrepurpose-facebook/SKILL.mdfor Facebook rulesrepurpose-threads/SKILL.mdfor Threads rules
- Load
repurpose/references/voice-adaptation.mdfor the voice setting - Load
repurpose/references/hook-formulas.mdfor platform-specific hooks - Generate outputs for each platform, writing files to the output directory
Platform Priorities
Twitter/X
- Thread (8-12 tweets): curiosity hook → numbered insights → CTA
- Standalone tweets (3-5): each captures one atom independently
- Poll: derived from content's key decision point
- Optimize for REPLIES (27x a like). Frame content as questions and contrarian takes
- Text post: professional hook → short paragraphs → engagement question → hashtags (3-5)
- PDF carousel script (10-12 slides): bold cover → one insight per slide → CTA slide
- Poll: strategic question, 2-4 options
- Optimize for SAVES (5x a like). Create save-worthy frameworks, checklists, data
- Post: warm, community-focused, question-ending
- Poll: conversational, 2-4 options, suggest image enhancement
- Story script: 3-5 frames, ephemeral feel
- 80% value / 20% promotional rule
Threads
- Thread (5-10 posts): hook → insights → CTA. 500 chars per post. No hashtags.
- Standalone posts (3-5): each captures one atom, conversational, opinion-led
- Image post concept: visual post with caption direction
- Links allowed in-body (no suppression unlike Twitter)
- Optimize for engagement and shares; Meta algorithm rewards conversation
Quality Checks Before Writing
- Character counts within platform limits
- Hooks are specific, not generic (no "Here's what I learned...")
- No external links in main post body (LinkedIn: note "Link in comments"; Twitter: link in reply)
- Voice matches the requested setting (casual/professional/witty)
- Each piece works standalone (someone seeing ONLY this piece understands the value)
- Threads posts stay under 500 chars; no hashtags used
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 · 66 lines · 53 tokens per session scan A f434c2e8eb13
repurpose-social is an agent published in the GitHub repository AgriciDaniel/claude-repurpose (145 stars, last pushed 5mo ago), licensed MIT. It adds 53 tokens to every session and 672 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 2026-08-30.
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.
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.
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…
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.
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.
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…