algorithm-cultivation

A set of tools for shaping an X/Twitter account's feed around a specific topic and managing a matching online persona. It includes browser scripts, command-line tools, and automated sessions using Puppeteer and a language model.

In plain words
What is it for?
Use it to create personas, train a feed toward selected topics, run engagement sessions, check persona status, and automate activity.
Why use it?
It helps reduce the manual work of searching, browsing, engaging, and posting around a niche on X/Twitter.

Skill for Claude CodeCodex

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 skills/nirholas/xactions/algorithm-cultivation
Any agent
npx skills add nirholas/XActions --skill algorithm-cultivation
Clone the repo
git clone --depth 1 https://github.com/nirholas/XActions

Made for: Claude Code, Codex.

Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,280 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 $0.00095 $0.01280
Opus 5 $0.00048 $0.00640
Sonnet 5 $0.00019 $0.00256
Haiku 4.5 $0.00010 $0.00128

Measured 2d ago against content hash dd74d5d2d1d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

algorithm-cultivation 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 2d 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.

skills/algorithm-cultivation/SKILL.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Algorithm Cultivation & Thought Leadership

Train your X/Twitter algorithm for a specific niche. Three approaches:

  1. Browser script -- paste into DevTools console for manual sessions
  2. CLI + Persona Engine -- create personas and run from the command line
  3. 24/7 Algorithm Builder -- headless Puppeteer + LLM running continuously

Quick Reference

Goal Solution
Create a persona (CLI) xactions persona create
Run 24/7 with LLM (CLI) xactions persona run <id>
Check persona status xactions persona status <id>
Browser console (with core.js) src/automation/algorithmBuilder.js
Browser console (standalone) scripts/thoughtLeaderCultivator.js
Browser console (algorithm trainer) src/automation/algorithmTrainer.js
Persona Engine (Node.js module) src/personaEngine.js
Algorithm Builder (Node.js module) src/algorithmBuilder.js

Core Concepts

  • Persona -- identity config: niche, activity pattern, engagement strategy, topics
  • Session -- one period of activity (search, browse, engage, post)
  • Strategy -- engagement limits (aggressive/moderate/conservative/thoughtleader)
  • Activity pattern -- human-like schedule (night-owl/early-bird/nine-to-five/always-on/weekend-warrior)

Algorithm Builder -- src/algorithmBuilder.js

24/7 headless automation: Puppeteer + stealth + OpenRouter LLM.

import { startAlgorithmBuilder } from './algorithmBuilder.js';

await startAlgorithmBuilder({
  personaId: 'persona_1234',
  authToken: 'your_auth_token',
  headless: true,
  dryRun: false,
  maxSessions: 0, // 0 = infinite
});

Requires OPENROUTER_API_KEY env var for LLM-generated comments and posts.

Algorithm Trainer -- src/automation/algorithmTrainer.js

Browser console script for manual training sessions. Requires src/automation/core.js pasted first.

Training Phases (cycles through all 8)

  1. Search top tweets for niche keywords
  2. Search latest tweets for niche keywords
  3. Follow people from search results
  4. Engage with home feed (like/reply)
  5. Visit influencer profiles
  6. Browse random profiles in niche
  7. Explore page browsing
  8. Idle dwell time (human-like pauses)

Read the full file on GitHub · 127 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 127 lines · 95 tokens per session scan A dd74d5d2d1d3

Subscribe to this mod's changes

algorithm-cultivation is a skill published in the GitHub repository nirholas/XActions (496 stars, last pushed 5d ago), licensed Apache-2.0. It adds 95 tokens to every session and 1,280 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

tmux

Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.

the-open-agent/openagent · 22 tokens

browser-test

Validate a feature works by driving a real browser with Playwright MCP. No test files — just interactive verification.

langwatch/langwatch · 25 tokens

browser-pair

Collaborative headed browser session for UI work. Launch Playwright Chromium visible to the user, handle auth, then interactively drive the browser while the user watches and gives real-time visual feedback. Edit code and refresh to verify fixes live. Use when the user says 'browser pair', 'paired browser', 'let's…

langwatch/langwatch · 87 tokens

debug-frontend-with-browser

Frontend diagnosis extension for the acceptance skill. Use for intermittent rendering, ordering, stale-state, navigation, virtual-list, React/Zustand, optimistic-update, refresh-dependent, or browser-only failures where the first broken boundary may be DOM, component input, derived state, client cache, network data…

lobehub/lobehub · 118 tokens

design-prototype

Produce an interactive single-file HTML design prototype using the REAL LobeHub design system (@lobehub/ui + antd + antd-style tokens) with production-style React — no build step, opens directly in a browser. Use when asked for a design prototype / interactive mockup / 交互原型 / 出个原型 / 设计稿 HTML for a page or flow, or to…

lobehub/lobehub · 92 tokens

share

Use when a user needs a browser-accessible link to preview, present, or send Agent-generated workspace files, an entire project, or the current topic outside Super Magic—especially rendered output such as HTML that messaging or file-viewing channels cannot display directly—or when they need to find, reuse, change, or…

dtyq/magic · 69 tokens