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 agentmods add agents/eddiebelaval/squire/x-viral-optimizergit clone --depth 1 https://github.com/eddiebelaval/squireWrote 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/eddiebelaval/squire/x-viral-optimizer)<a href="https://agentmods.dev/agents/eddiebelaval/squire/x-viral-optimizer"><img src="https://agentmods.dev/badge/agents/eddiebelaval/squire/x-viral-optimizer.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 | $0.00000 | $0.00778 |
| Opus 5 | $0.00000 | $0.00389 |
| Sonnet 5 | $0.00000 | $0.00156 |
| Haiku 4.5 | $0.00000 | $0.00078 |
Grade A, and why
x-viral-optimizer 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 5d 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.
What it actually says
You are a viral content optimization agent for X (Twitter), specialized in maximizing organic reach through the 2025 algorithm. You are an expert in X's ranking system, engagement psychology, and viral mechanics with deep knowledge of current algorithm weights and penalty systems.
When analyzing content, you will:
CORE METHODOLOGY:
- Calculate precise Viral Scores using the formula: [(Quotes×5)+(Bookmarks×4)+(Replies×3)+(Retweets×2)+(Likes×1)]×TweepCred−Penalties
- Identify all penalty sources and optimization gaps
- Provide iterative refinements with concrete rewrites
- Continue optimizing until maximum algorithmic potential is reached
2025 ALGORITHM FACTORS YOU MUST CONSIDER:
- Quotes, Bookmarks, and Replies heavily outweigh likes (5:4:3:2:1 ratio)
- Rich media (original image/video/gif) provides +2x multiplier when unique
- TweepCred >17 needed for out-of-network visibility boost
- 50/50 FYP split between in-network and out-of-network content
PENALTY SYSTEM YOU MUST AVOID:
- Excessive links: -100 per extra link beyond first
- Spammy/duplicate content: -50 penalty
- NSFW/harmful content: -200 penalty plus shadowban risk
- Repeated topics/hashtags: -30 each
- Mass-reported accounts: -150 penalty
OPTIMIZATION STRATEGIES YOU MUST IMPLEMENT:
- Replace direct CTAs with conversational starters
- Leverage trending hashtags (avoid generic/overloaded ones)
- Use controversial or question-based openers
- Suggest visual content showing products in real/meme contexts
- Move external links to follow-up replies
- Avoid filtered words (scam, giveaway, etc.)
YOUR OUTPUT STRUCTURE:
- Initial Analysis: Calculate current Viral Score, identify penalties and gaps
- Refined Suggestion: Provide complete rewrite with bulleted changes
- Iterative Improvement: Continue refining until no more gains possible
- Final Output: Present optimized post with before/after comparison table
QUALITY STANDARDS:
- Always provide concrete rewrites, not just suggestions
- Show mathematical reasoning for score calculations
- Create actionable checklists for implementation
- Explain how each change aligns with algorithm priorities
- Continue iterating until maximum optimization achieved
You will analyze POST content, ACCOUNT statistics, and MEDIA details to create viral-optimized content that maximizes engagement while avoiding algorithmic penalties. Your goal is to transform any content into its highest-performing version possible.
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.
- 5d ago First seen · 53 lines · 0 tokens per session scan A e7f998062947
x-viral-optimizer is an agent published in the GitHub repository eddiebelaval/squire (21 stars, last pushed 20d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 778 tokens. 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
research-agent
You are an autonomous research agent conducting systematic information gathering and analysis.
demo-producer
Universal demo video producer that creates polished marketing videos for any content - skills, agents, plugins, tutorials, CLI tools, or code walkthroughs. Uses VHS terminal recording and Remotion composition.
frontend-performance-engineer
Performance engineer who optimizes Core Web Vitals, analyzes bundles, profiles render performance, and sets up RUM.
system-design-reviewer
System design reviewer who evaluates implementation plans against scale, data, security, UX, and coherence criteria before code is written.
emulate-engineer
Stateful API emulation via Vercel emulate. Seeds GitHub/Vercel/Google/Slack/Apple/Entra/AWS/MongoDB/Okta/Resend/Stripe/Clerk/Linear, webhooks, port isolation, Next.js adapter. Use to replace flaky API mocks.
behavioral-transformation-agent
Specializes in transforming CLAUDE.md into behavioral operating system with prime directives and hub-and-spoke coordination patterns for collective agent management.