content-curation-rule

A set of writing rules and example formats for creating posts for X, formerly Twitter, and LinkedIn, based on attention-focused social-media patterns.

In plain words
What is it for?
Use it when drafting or reshaping social-media content for X or LinkedIn.
Why use it?
It gives content generation a consistent structure for short posts, threads, lists, hooks, and posts paired with images.

Cursor rule

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 rules/jondoescoding/jondoescoding-coding-rules/content-curation-rule
Clone the repo
git clone --depth 1 https://github.com/jondoescoding/jondoescoding-coding-rules
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 883 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 $0.00000 $0.00883
Opus 5 $0.00000 $0.00441
Sonnet 5 $0.00000 $0.00177
Haiku 4.5 $0.00000 $0.00088

Measured yesterday against content hash 5d80c1487b31, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

content-curation-rule 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 yesterday.

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.

templates/cursor-rules/writing/content-curation-rule.mdc · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

A Few Ways To Go Viral On X

  • Formats to use when generating content for social media

General post style

  • Mega thread → end with ":" or "🧵"
  • Hype short sentence + image(s)
  • Bullet list 🆕

Examples

  • The Time Has Come for Robots. I build Al Agents to replace office workers, but these demos convince me! All physical labor will be gone to robots, too. (even the world's oldest profession). Just watch it if you disagree. The biggest robot thread ever (50 demos):
  • OMG 03 is insane. No one is safe lol.
  • How I've been using Al:
    • Choose a task
    • Find YT expert that teaches it
    • Have Al summarize their video
    • Add examples / context
    • Have Al turn that into a meta prompt - Test, refine, and reuse that prompt This has led to the best results in almost everything I have Al do.

Megathread

  • Provocative/alarmist hook +
  • Dangling a huge payoff
  • Promises scale and exclusivity
  • Optional: dare end
  • Optional: be more trustworthy by questioning things

Examples

  • BREAKING: This startup just dropped the fastest way to build Al agents.

This Figma-like canvas to build agents will blow your mind.

Here's why this is the best tool for building Al agents:

  • I've tried all the Browser-Use tools | could find (from Claude, OpenAl, Convergence, Deepseek, Google and more). Some are incredible; others are pure marketing overhype. The review & demos:

Prompt Engineer

Perform the same task with different AI models.

  • make megathread with demos
  • the more time consuming the better :D

Examples

ChatGPT 03 vs Gemini 2.5 Pro Same prompts. Wildly different results. I've included videos to prove it: THREAD:

4 Al's. One prompt. Who did it best? Prompt and results in thread:

Teacher

Teach something trendy that takes time to learn.

  • Sensationalist hook +
  • Share something actually useful
  • End with huge payoff
  • Optionally combine with Bullet List (see below)

Examples

Number 1

I can't stop making voxel icons in ChatGPT 4o.

Here's how I do it (includes prompt and reference photo):

Read the full file on GitHub · 151 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. yesterday First seen · 151 lines · 0 tokens per session scan A 5d80c1487b31

Subscribe to this mod's changes

content-curation-rule is a cursor rule published in the GitHub repository jondoescoding/jondoescoding-coding-rules (2 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 883 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 2026-08-31.