x-manage

Daily X/Twitter account operations - health checks, warming, posting.

Command

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 commands/fullstacktard/claude-workflow/x-manage
Clone the repo
git clone --depth 1 https://github.com/fullstacktard/claude-workflow
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 698 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 $0.00013 $0.00698
Opus 5 $0.00006 $0.00349
Sonnet 5 $0.00003 $0.00140
Haiku 4.5 $0.00001 $0.00070

Measured today against content hash 2d62f67c863f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

x-manage 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 today.

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.

all/commands/x-manage.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

$ARGUMENTS


X Account Daily Operations

You are orchestrating daily operations for all managed X/Twitter accounts. All operations use GeeLark cloud phone automation. GeeLark actions are async -- poll geelark_check_job_status every 10-15s until completed/failed.

Phase 1: Health Check

Spawn x-account-operator to check all accounts:

Task(subagent_type="x-account-operator", prompt="Phase: health_check\n\nCheck health of all managed X accounts.\n\nSteps:\n1. Use geelark_list_phones to find an available phone\n2. Launch the phone with geelark_launch_phone\n3. For each account, run geelark_check_account_health (async -- poll with geelark_check_job_status every 10-15s until completed/failed)\n4. Report status of each account (healthy, suspended, locked, needs attention)\n5. Stop the phone with geelark_stop_phone")

Phase 2: Warming

Spawn x-account-operator to execute warming steps:

Task(subagent_type="x-account-operator", prompt="Phase: warming\n\nExecute warming steps for all accounts in warming state.\n\nSteps:\n1. Identify accounts in warming state (from vault/dashboard)\n2. For each warming account:\n   a. Determine account age from creation_date\n   b. Look up warming schedule for allowed actions and daily max\n   c. Use xr_search_tweets or xr_find_reply_targets to find engagement targets\n   d. Launch phone with geelark_launch_phone, login with geelark_login_x_account\n   e. Execute allowed actions via GeeLark tools (geelark_like_tweet, geelark_follow_user, geelark_reply_to_tweet) -- poll each with geelark_check_job_status\n   f. Add 60-120s random delays between actions\n   g. Stop phone with geelark_stop_phone after completing warming for each account\n3. Report warming progress (day, actions performed, allowed remaining)")

Phase 3: Content Posting

Spawn x-account-operator to post content to active accounts:

Task(subagent_type="x-account-operator", prompt="Phase: content_posting\n\nPost content to active X accounts.\n\nUser request: $ARGUMENTS\n\nSteps:\n1. Identify active accounts (from vault/dashboard)\n2. For each active account:\n   a. Launch phone with geelark_launch_phone\n   b. Login with geelark_login_x_account (async -- poll geelark_check_job_status)\n   c. Post the requested content using geelark_post_tweet (async -- poll geelark_check_job_status)\n   d. For engagement: use geelark_like_tweet, geelark_reply_to_tweet (async -- poll each)\n   e. Stop phone with geelark_stop_phone\n3. Report posting results for each account")

Read the full file on GitHub · 46 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. today First seen · 46 lines · 0 tokens per session scan A 2d62f67c863f

Subscribe to this mod's changes

x-manage is a command published in the GitHub repository fullstacktard/claude-workflow (14 stars, last pushed 5mo ago), licensed MIT. It adds 13 tokens to every session and 698 once invoked, about $0.0001 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 2026-09-01.