tokenoptimizer
di smartpeopleconnected
Coding Agents & IDEsSintesi
Reduce OpenClaw AI costs by 97%.
Descrizione
Cosa fa questa skill
Routes OpenClaw agent requests to Haiku by default, escalating to Sonnet or Opus only when needed. Offloads heartbeat checks to local providers like Ollama or free tiers like Groq, reduces session context from ~50KB to ~8KB, and caches repeated prompts at 10% of standard cost. All changes write to ~/.openclaw/ with automatic backups.
Every change runs in dry-run mode by default, creates timestamped backups before writing, and produces a verification report after applying, so there is no guesswork about what changed or whether it worked.
Quando usarla
- Cutting a $1,500/month AI bill down to under $50
- Running heartbeat checks locally with Ollama instead of paying per token
- Previewing config changes in dry-run mode before applying them to a live setup
- Rolling back to a previous config after an optimization breaks agent behavior
- Setting daily and monthly token budget caps to avoid unexpected charges
Esempio di workflow
User asks: optimize my OpenClaw setup to reduce API costs
- 1
Runs
python cli.py analyzeto inspect current model routing, heartbeat config, and context load - 2
Runs
python cli.py optimizein dry-run mode to generate a diff of proposed changes - 3
User confirms and runs
python cli.py optimize --applyto write the config - 4
Runs
python cli.py setup-heartbeat --provider ollama --applyto route heartbeats to a local model - 5
Runs
python cli.py verifyto confirm the new config and view projected savings
OpenClaw config updated with Haiku as default model, Ollama handling heartbeats, 8KB session context, and prompt caching enabled, with a backup created and a savings report generated
Installazione
clawhub install smartpeopleconnected/tokenoptimizerEsegui il comando CLI oppure incolla il prompt in Claude Code, Cursor, Codex o nell'agente di coding che usi.