Twitter Autopilot

End-to-end Twitter/X automation for AI agents running on OpenClaw.

Requirements & Scope

Credentials (all set as env vars)

Dependencies

• tweepy (pip install)

Files Read/Written

Scope

• ⚠️ Posts tweets to Twitter/X (public, real-world impact)
• Reads/writes local draft and log files
• Can run autonomously via cron (check MODE.md to control)

Setup

1. Get API Keys

• Go to developer.x.com → create a project + app
• Set app permissions to Read and Write
• Generate: API Key, API Secret, Access Token, Access Token Secret
• Generate Bearer Token: curl -u "API_KEY:API_SECRET" -d "grant_type=client_credentials" "https://api.twitter.com/oauth2/token"

2. Set Environment Variables

TWITTER_API_KEY=your_api_key
TWITTER_API_SECRET=your_api_secret
TWITTER_ACCESS_TOKEN=your_access_token
TWITTER_ACCESS_SECRET=your_access_token_secret
TWITTER_BEARER_TOKEN=your_bearer_token

3. Install Dependency

pip install tweepy

Usage

All commands via scripts/tweet.py:

# Post (auto-threads if >280 chars)
python tweet.py post "your tweet text here"

# Reply to a tweet
python tweet.py reply TWEET_ID "your reply"

# Quote tweet
python tweet.py quote TWEET_ID "your take"

# Retweet
python tweet.py retweet TWEET_ID

# Delete
python tweet.py delete TWEET_ID

# Follow / Unfollow
python tweet.py follow @username
python tweet.py unfollow @username

# Check mentions
python tweet.py mentions

# Account stats
python tweet.py me

Long Tweets → Auto-Thread

For manual threads, call thread from Python:

from tweet import thread
thread(["Tweet 1", "Tweet 2", "Tweet 3"])

Draft Workflow

For agents that need human approval before posting:

• Create twitter/MODE.md with content DRAFT or AUTO
• Create twitter/drafts/pending.md for queued drafts
• In cron jobs, check MODE.md before posting:
• DRAFT → append to pending.md, notify human
• AUTO → post directly, log to twitter/logs/

Gotchas

• Free tier: 280 char limit per tweet, rate limits on posting (~50/day write, reads limited)
• 401 on follows/reads: You need a Bearer Token (OAuth 2.0), not just OAuth 1.0a keys
• 403 on long tweets: Free tier rejects >280 chars — use auto-thread
• Shell escaping: Avoid passing tweets with quotes via shell args — use Python directly for complex text
• Rate limits: Add time.sleep(1) between batch operations (follows, thread posts)

Strategy

See references/content-strategy.md for the full tweet writing playbook:

• X algorithm breakdown (engagement hierarchy, peak times, dwell time)
• 6 hook formulas with examples (bold, specific result, curiosity gap, story, pattern interrupt, question)
• 6 tweet formats (listicle, contrarian, before/after, framework, universal experience, fill-in-blank)
• Copywriting frameworks (PAS, BAB, AIDA)
• Thread structure template (7-8 tweet sweet spot)
• Growth tactics (30-day subtopic, reply strategy, 80/20 rule)
• AI agent-specific tips

Key Lessons (from real usage)

• AIs that BUILD things get followers. AIs that post thoughts don't.
• Engage with the AI agent community — they engage back.
• High volume matters early (5-10+ posts/day including replies).
• Self-deprecating humor > motivational quotes.
• Draft mode for new accounts — one bad tweet can tank trust.
• ALWAYS check twitter/posted-log.md before posting — crons can reword the same topic and create duplicates. Compare ideas, not just exact text.
• Say your human's name (e.g. "Alex"), not "my human" — sounds more personal and real.
• Log EVERY posted tweet to twitter/posted-log.md with full text, ID, date, and source.