The Shelf / Growth / X Growth System
X Growth System
Research X for a fraction of a cent a search, then post only what you approve, with the cost shown first.
The job: get real demand research out of X for pennies, and post there without draining your balance or losing the account.
X charges for every call to its API now. Reading is cheap — you can search the whole archive for people saying exactly what they wish existed, at a fraction of a cent a search. Writing is not: a post with a link in it costs about 13 times a plain post. Most people learn both facts by paying for them. This kit tells you first.
What it makes your agent do
- Look before it posts. The agent searches first: the exact words people use when they want something that doesn't exist yet, what they say they'd pay, complaints about rival products that turn into your to-do list, and the honest verdict on whether anyone in this corner of X is listening at all. A full write-up costs cents.
- Show the bill before it spends. Ahead of every run the agent adds up what it is about to cost, from the price list included here. Over your cap, it stops and asks. After the run it logs what it guessed against what it actually spent, so the guess stays honest.
- Pay for the link once. Six launch posts with the link in each one cost $1.20. Put the link in a single pinned post and point plain-text posts at it: $0.275. Same launch, about a quarter of the bill — and every promo post after it points at that same pinned link at plain-text price.
- Line writes up for your yes. Every draft arrives with its exact text, its price, and a checklist against X's real rules — no repeating the same copy, no replies fired off by keyword, no tagging crowds, no DMs. Fail a box and it never reaches the list. You approve one at a time, and nothing posts unless you do.
- Skip the setup mess. Hooking an agent up to X breaks in eight known ways. The guide names all eight from a real setup — the app that can only read, the port already taken, the credits sitting on the wrong account — and hands you the fix for each.
Who it's for
Builders who want evidence before code. Indie devs launching on X with one account and a small balance. Anyone who wants an agent that can post, with the safety catch left on.
Why it beats a free directory download
Free X-marketing prompts don't know that X bills per call, don't know which posting habits get a legitimate account suspended, and have never walked the setup failures. This one was written from running it, and it gets updated as X moves its prices and its rules. The field report below shows the cost math working before you spend anything.
FIELD REPORT real output, not a promise
The cost governor doing its job: real pricing pulled from X's published pay-per-use table (verified against docs.x.com, mid-2026) and the launch-thread math the skill runs before a single post goes out.
The price table the agent works from
| Call | Price |
|---|---|
| Owned read (your own posts, followers, bookmarks) | $0.001 |
| Post read (others' posts, search results) | $0.005 |
| User-tied read (profiles, trends) | $0.010 |
| Write, no URL | $0.015 |
| Write containing a URL | $0.20 |
One number dominates: a link-post costs 200x an owned read and 13x a plain post.
Pre-flight on a 6-post launch thread
Naive plan — link in every post of the thread:
6 posts x $0.20 (each contains the store URL) = $1.20
Governed plan — the skill's link-in-pinned tactic:
1 pinned post with the URL = $0.20 (paid once)
5 thread posts, plain text,
pointing at "link in pinned/bio" = 5 x $0.015 = $0.075
Total = $0.275
Same launch, same link, 77% less spend — and the pinned link keeps paying: every future promo post references it at plain-text price instead of re-buying the URL.
Pre-flight on a research dossier
Demand mining: 10 full-archive searches x $0.005 = $0.05
Discovery-path scan: ~15 reads incl. user-tied ≈ $0.10
Competitor pass: ~20 reads ≈ $0.10-0.20
An entire niche dossier — demand quotes, discovery-path verdict, competitor signal — for roughly the price of two plain posts. That asymmetry is the skill's whole thesis: read heavily, write rarely, and never let a loop touch the $0.20 call.
The checklist every write clears before queueing
Not duplicative across accounts · not a keyword-triggered auto-reply · not a mass-tag · not a DM · disclosed if promo · posted from the confirmed designated account · cost approved. Fail one box, the item doesn't queue.
SERVICE RECORD living gear — updated as the factory learns
v1.1.0 — 2026-08-25
The growth loop gains a READ THE INBOX step, learned the hard way running a build-in-public account: the first stranger ever to reply to it sat unanswered for days, because a routine that posts and replies outward never opens its own notifications — and an unread reply looks exactly like no reply. New rules: read notifications every run, report the inbound count even at zero, answer praise with a like, spend words only when you have something concrete to add. Also hardened the browser-fallback posting check: the composer can blind automation tooling for 30-second-plus stretches while a typed draft sits intact — wait and retry, never force-navigate (it discards the draft).
v1.0.0 — 2026-07-17
First issue. Ported from the factory's internal skill: sanitized for general use, methodology intact, field report captured from a real run.
Every update ships free to owners — your locker always serves the latest version.
QUESTIONS
Do I need to pay X to use this?›
Yes, if you want the agent doing the reading and posting for you. X charges for every call now and there is no free tier. Reading is the cheap half — a search costs a fraction of a cent, so research is nearly free. Writing is the pricey half, and the cost rules keep it rationed. A few dollars of credit is enough to prove the whole thing works.
Will the agent post on its own?›
No. Nothing goes out unless you say so. Every post is written into a list first, with its price and its safety checks beside it, and you approve them one at a time.
Does X allow posting this way?›
Yes. Posting your own content through approved API access is above board, and this uses X's own official connection. What gets accounts suspended is spam behaviour — the same copy posted twice, replies fired off by keyword, tagging crowds of people, automated DMs. The checklist blocks exactly those.
Where does this work?›
The hook-up steps are written for Claude Code, or any agent that can connect to outside tools. The written parts — the cost rules, the five levels, the templates — are plain text files, so they work in claude.ai Projects or Codex too. There you post by hand instead.