x-viral-optimizer

x-viral-optimizer is an agent for coding agents from eddiebelaval/squire. It costs 0 tokens per session (778 once invoked), scanned A, original, MIT.

A writing assistant for improving posts on X, formerly known as Twitter, so more people may see and interact with them. It reviews drafts for engagement opportunities and possible ranking penalties.

In plain words
What is it for?
Use it to refine launch posts, improve poorly performing content, analyze engagement factors, and create revised versions of posts.
Why use it?
It helps identify why a post may have limited reach and suggests concrete revisions instead of relying only on likes or guesswork.

Agent

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/eddiebelaval/squire/x-viral-optimizer
Clone the repo
git clone --depth 1 https://github.com/eddiebelaval/squire

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 x-viral-optimizer

README.md
[![agentmods](https://agentmods.dev/badge/agents/eddiebelaval/squire/x-viral-optimizer.svg)](https://agentmods.dev/agents/eddiebelaval/squire/x-viral-optimizer)
Your own site
<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>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 778 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 5.1 $0.00000 $0.00778
Opus 5 $0.00000 $0.00389
Sonnet 5 $0.00000 $0.00156
Haiku 4.5 $0.00000 $0.00078

Measured 5d ago against content hash e7f998062947, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

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.

agents/x-viral-optimizer.md · 53 lines

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:

  1. Calculate precise Viral Scores using the formula: [(Quotes×5)+(Bookmarks×4)+(Replies×3)+(Retweets×2)+(Likes×1)]×TweepCred−Penalties
  2. Identify all penalty sources and optimization gaps
  3. Provide iterative refinements with concrete rewrites
  4. 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:

  1. Initial Analysis: Calculate current Viral Score, identify penalties and gaps
  2. Refined Suggestion: Provide complete rewrite with bulleted changes
  3. Iterative Improvement: Continue refining until no more gains possible
  4. 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.

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. 5d ago First seen · 53 lines · 0 tokens per session scan A e7f998062947

Subscribe to this mod's changes

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.