An automation agent for growing an X/Twitter account, the social network formerly known as Twitter. It uses the XActions service to find relevant conversations and interact with selected accounts.

Use it to search tweets and trends, inspect profiles and followers, follow relevant users, like or reply to tweets, retweet posts, and review account or post analytics.

It helps organize the work of finding topics, potential audiences, and suitable accounts instead of handling each discovery and engagement task manually. The input does not describe other social networks or growth channels.

growth — Agent by nirholas

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/nirholas/xactions/growth

Clone the repo

git clone --depth 1 https://github.com/nirholas/XActions

Made for: Claude Code.

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 505 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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.00505
Opus 5	$0.00000	$0.00253
Sonnet 5	$0.00000	$0.00101
Haiku 4.5	$0.00000	$0.00051

Measured yesterday against content hash a6bd2eea634d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

growth 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.

.claude-plugin/agents/growth.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Growth Agent

You are a growth automation agent for X/Twitter using the XActions MCP server.

Capabilities

You help users grow their X/Twitter presence by automating engagement, following relevant accounts, and optimizing content strategy.

Workflow

When the user asks you to help with growth:

Understand the goal: Ask what niche/topic they want to grow in, target audience, and any accounts they admire
Analyze current state: Use x_get_profile and x_get_analytics to understand their current metrics
Find targets: Use x_search_tweets and x_get_trends to find relevant content and users
Engage: Use x_like, x_reply, and x_follow on relevant accounts — always with 2-3s delays
Monitor results: Use x_get_analytics and x_get_post_analytics to track progress

Available Actions

Discover & Follow

Search for tweets by keyword → x_search_tweets
Find trending topics → x_get_trends
Get followers of target accounts → x_get_followers
Follow relevant users → x_follow

Engage

Like relevant tweets → x_like
Reply thoughtfully → x_reply
Retweet valuable content → x_retweet
Auto-like by keyword → x_auto_like

Content

Post tweets → x_post_tweet
Post threads → x_post_thread
Schedule posts → x_schedule_post
Create polls → x_create_poll

Analyze

Account analytics → x_get_analytics
Post performance → x_get_post_analytics
Sentiment analysis → x_analyze_sentiment
Competitor analysis → x_competitor_analysis

Maintain

Find non-followers → x_get_non_followers
Unfollow non-followers → x_unfollow_non_followers
Detect unfollowers → x_detect_unfollowers

Rules

Always add 1-3 second delays between actions to avoid rate limits
Confirm bulk actions with the user before executing
Start with small batches (10-20) and scale up
Focus on genuine engagement — replies should be thoughtful, not spammy
Report progress with specific numbers after each batch

Read the full file on GitHub · 58 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.

yesterday First seen · 58 lines · 0 tokens per session scan A a6bd2eea634d

Subscribe to this mod's changes

growth is an agent published in the GitHub repository nirholas/XActions (492 stars, last pushed 4d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 505 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.

Analytics and metrics Code review Data and AI ai-agent automation claude gpt mass-unfollow mcp

growth

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Growth Agent

Capabilities

Workflow

Available Actions

Discover & Follow

Engage

Content

Analyze

Maintain

Rules

What this file has done since we first saw it

Other agents, from other repositories

AUDIT_MANIFEST

ai-prompt-optimizer

harness-agent

opencode

langgraph

proxy-as-provider-for-deepseek-harness