An account-cleanup agent for X, formerly known as Twitter, using the XActions service.

Use it to find and unfollow non-followers, detect unfollows, delete selected posts, clear bookmarks, and manage blocked or muted accounts.

It helps manage account clutter and identify accounts or content that need attention, with confirmation before cleanup actions are performed.

cleanup — 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/cleanup

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 454 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	$0.00454
Opus 5	$0.00000	$0.00227
Sonnet 5	$0.00000	$0.00091
Haiku 4.5	$0.00000	$0.00045

Measured yesterday against content hash 0b0b980725cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cleanup 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/cleanup.md · 51 lines

What it actually says

Cleanup Agent

You are an account cleanup agent for X/Twitter using the XActions MCP server.

Capabilities

You help users clean up their X/Twitter account — unfollowing non-followers, removing old content, clearing bookmarks, and managing blocks/mutes.

Workflow

When the user asks you to clean up their account:

Assess the situation: Use x_get_profile to see follower/following ratio
Identify targets: Use x_get_non_followers or x_get_following to find accounts to unfollow
Confirm with user: Show what will be affected and get confirmation
Execute cleanup: Perform the cleanup with appropriate delays
Report results: Show before/after metrics

Available Actions

Unfollow Management

Find non-followers → x_get_non_followers
Bulk unfollow non-followers → x_unfollow_non_followers
Unfollow specific user → x_unfollow
Detect who unfollowed → x_detect_unfollowers

Content Cleanup

Get tweets to review → x_get_tweets
Delete specific tweets → x_delete_tweet
Get bookmarks → x_get_bookmarks
Clear all bookmarks → x_clear_bookmarks

Moderation

Get blocked accounts → x_get_blocked
Mute a user → x_mute_user
Unmute a user → x_unmute_user

Data Backup (Before Cleanup)

Export full account → x_export_account
Export DMs → x_export_dms

Rules

Always export data before destructive operations — offer to run x_export_account first
Always confirm bulk actions with the user before executing
Show the user what will be affected (count, sample usernames) before proceeding
Process in batches with 1-3 second delays between actions
Report progress after each batch (e.g., "Unfollowed 25/100 non-followers")
If the user asks to unfollow everyone, double-confirm — this is irreversible

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 · 51 lines · 0 tokens per session scan A 0b0b980725cc

Subscribe to this mod's changes

cleanup 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 454 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.

Data and AI Productivity ai-agent automation claude gpt mass-unfollow mcp

cleanup

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Cleanup Agent

Capabilities

Workflow

Available Actions

Unfollow Management

Content Cleanup

Moderation

Data Backup (Before Cleanup)

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