Skip to content

x402agent/SolanaOS / skills/pumpfun-token-scanner

pumpfun-token-scanner

Verified

Scrapes pump.fun/board using Chrome browser automation to extract the top 100 trending Solana tokens and writes structured markdown for a trading agent to consume. Use this skill any time you need to: scan pump.fun for new tokens, refresh the pump.md token list, run the scheduled board scrape, collect Solana meme token data, or build/update a trading watchlist from pump.fun. Even if the user says something casual like "check pump" or "update the token list" or "what's trending on pump", use this skill. The output file path and format are configurable but default to /Users/8bit/solanaos/pump.md.

FileKindSize
SKILL.mdskill md26.5 KB
blocklist.jsonconfig987 B
scripts/blocklist_filter.pyscript2.6 KB
scripts/deploy_pipeline.pyscript9.5 KB
scripts/honcho_memory.pyscript11.2 KB
scripts/push_to_convex.pyexecutablescript3.7 KB
scripts/push_to_convex.py.bakexecutablescript3.7 KB
scripts/send_telegram.pyexecutablescript10.4 KB
scripts/send_tweet.pyscript5.6 KB
scripts/watch_pump.shexecutablescript2.5 KB

scripts/watch_pump.sh

View on GitHub
#!/usr/bin/env bash
# watch_pump.sh β€” Watches pump.md for changes and triggers the deploy pipeline
# Usage: ./watch_pump.sh [--poll-interval 30] [--once]
#
# Requires: deploy_pipeline.py, push_to_convex.py, send_telegram.py in same dir
# Env: reads .env from /Users/8bit/solanaos/.env

set -euo pipefail

SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
PROJECT_DIR="$(cd "$SCRIPT_DIR/../../.." && pwd)"
PUMP_MD="$PROJECT_DIR/pump.md"
POLL_INTERVAL="${POLL_INTERVAL:-30}"
RUN_ONCE=false
LAST_HASH=""

# Parse args
while [[ $# -gt 0 ]]; do
  case "$1" in
    --poll-interval) POLL_INTERVAL="$2"; shift 2 ;;
    --once) RUN_ONCE=true; shift ;;
    *) echo "Unknown arg: $1"; exit 1 ;;
  esac
done

log() { echo "[$(date '+%H:%M:%S')] $*"; }

get_hash() {
  if [[ -f "$PUMP_MD" ]]; then
    md5 -q "$PUMP_MD" 2>/dev/null || md5sum "$PUMP_MD" | cut -d' ' -f1
  else
    echo "no-file"
  fi
}

run_pipeline() {
  log "πŸš€ pump.md changed β€” running deploy pipeline..."

  # Step 1: Push to Convex
  log "  β†’ Pushing to Convex..."
  if python3 "$SCRIPT_DIR/push_to_convex.py" --source watcher; then
    log "  βœ… Convex push complete"
  else
    log "  ❌ Convex push failed (continuing...)"
  fi

  # Step 2: Full deploy pipeline (Convex + Netlify + git)
  log "  β†’ Running deploy pipeline..."
  if python3 "$SCRIPT_DIR/deploy_pipeline.py" --source watcher --skip-convex; then
    log "  βœ… Deploy pipeline complete"
  else
    log "  ❌ Deploy pipeline had errors"
  fi

  # Step 3: Telegram digest
  log "  β†’ Sending Telegram digest..."
  if python3 "$SCRIPT_DIR/send_telegram.py"; then
    log "  βœ… Telegram digest sent"
  else
    log "  ❌ Telegram send failed"
  fi

  log "βœ… Pipeline finished at $(date '+%Y-%m-%d %H:%M:%S')"
}

# --- Main loop ---

log "πŸ‘οΈ  Watching $PUMP_MD (poll: ${POLL_INTERVAL}s)"
LAST_HASH=$(get_hash)
log "  Initial hash: $LAST_HASH"

if $RUN_ONCE; then
  # Just run the pipeline once and exit (useful for cron/launchd)
  run_pipeline
  exit 0
fi

# Try fswatch first (macOS), fall back to polling
if command -v fswatch &>/dev/null; then
  log "  Using fswatch for native file events"
  fswatch -1 "$PUMP_MD" | while read -r _; do
    NEW_HASH=$(get_hash)
    if [[ "$NEW_HASH" != "$LAST_HASH" ]]; then
      LAST_HASH="$NEW_HASH"
      run_pipeline
    fi
    log "πŸ‘οΈ  Resuming watch..."
  done
else
  log "  fswatch not found β€” using ${POLL_INTERVAL}s polling"
  while true; do
    sleep "$POLL_INTERVAL"
    NEW_HASH=$(get_hash)
    if [[ "$NEW_HASH" != "$LAST_HASH" ]]; then
      LAST_HASH="$NEW_HASH"
      run_pipeline
    fi
  done
fi
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why β€” repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" β€” or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself β€” your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall