token-efficiency-guide
Go from weekly limit on Tuesday to weekly limit on Sunday. 10 steps, one afternoon.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/globalcaos/token-efficiency-guideToken Efficiency Guide
Make your Claude Max subscription last the whole week. One afternoon, 10 steps, 80-90% fewer tokens burned.
What You Get
10 changes ordered by impact. Most take minutes.
| Step | Saves | Effort |
|---|---|---|
| 1. Heartbeat → Haiku | ~25% | 1 minute |
| 2. Session compaction | ~20% | 10 minutes |
| 3. Simple crons → bash | ~15% | 1-2 hours |
| 4. Cron jobs → Sonnet | ~10% | 5 minutes |
| 5. Isolate large outputs | ~10% | 10 minutes |
| 6. Reduce cron frequency | ~8% | 5 minutes |
| 7. Workspace file cleanup | ~7% | 30 minutes |
| 8. Enable cache retention | ~3% | 1 minute |
| 9. Coordinate multi-agent usage | ~2% | Agreement |
| 10. Automated maintenance crons | ~5% | 1-2 hours |
Step 1 alone buys you an extra day. Steps 1-3 together cover 60%.
Who This Is For
- OpenClaw users on Claude Max who know what "it's Tuesday and the limit hit" feels like
- Teams sharing one subscription across multiple agents
- Anyone who'd rather spend tokens on work than on heartbeats
What's Included
- Step-by-step instructions with config snippets
- Ready-to-use maintenance scripts
- Model routing recommendations per task type
Clone it. Fork it. Break it. Make it yours.
👉 Explore the full project: github.com/globalcaos/clawdbot-moltbot-openclaw
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-globalcaos-token-efficiency-guide": {
"enabled": true,
"auto_update": true
}
}
}Related Skills
jarvis-voice
Turn your AI into JARVIS. Voice, wit, and personality — the complete package. Humor cranked to maximum.
shell-security-ultimate
Classify every shell command as SAFE, WARN, or CRIT before your agent runs it.
memory-pioneer
Benchmark your agent's memory. Contribute anonymized scores to open research. Citizen science for AI memory.
subagent-overseer
Monitor sub-agent health and progress via a pull-based bash daemon. Use when spawning sub-agents that need progress tracking, staleness detection, and automatic status reporting. Replaces manual heartbeat polling with a deterministic status file the agent reads every 3 minutes. Zero AI tokens for monitoring — pure OS-level process checks and filesystem diffs.
model-router
Automatic LLM model selection for sub-agent tasks. Classifies tasks by complexity and type, then routes to the optimal model (cost vs capability). Use when spawning sub-agents, choosing models for cron jobs, or deciding which model to use for any task. Eliminates manual model specification by providing a decision tree and optional cheap-model classifier for ambiguous cases.