Tokenoptimizer
Reduce OpenClaw AI costs by 97%. Haiku model routing, free Ollama heartbeats, prompt caching, and budget controls. Go from $1,500/month to $50/month in 5 minutes.
Why this rating
Deterministic checks triggered by the tool capabilities and evidence.
- Locality: Local
Operates through local Python CLI commands and workspace configuration files.
- Data access: Sensitive
Touches model routing, heartbeat providers, and potentially credential-adjacent config.
- Action surface: Write
`optimize` applies configuration changes and supports rollback from backups.
Best practices
Follow these steps to reduce risk when using this skill.
- Run `--dry-run` and review diffs before applying optimizer changes.
- Keep backup files encrypted or access-restricted because configs may contain sensitive values.
- Validate behavior after optimization and rollback quickly if unexpected routing occurs.
Evidence links
Public sources backing the indicator assignments.
Always be careful when navigating away from the website.
Max-risk rule
If any capability reaches a higher level, the entire indicator level bumps up to keep ratings deterministic and easy to scan.