Julia's OpenClaw Token Optimizer
ReviewAudited by ClawScan on May 10, 2026.
Overview
This skill is clearly meant to reduce model costs, but it can directly change your default OpenClaw model settings without an explicit confirmation or rollback step.
Before installing or using this skill, decide whether you want it to only recommend cheaper models or actually change your OpenClaw defaults. If you use it, ask for a cost/quality matrix first, require a visible config diff and explicit approval before patching, and keep a rollback plan for restoring your previous model settings.
Findings (2)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Your agent's default model could be changed persistently, which may affect future answer quality, cost, provider routing, or rate-limit behavior.
The skill instructs the agent to patch model-selection configuration, including defaults, but the artifacts do not require explicit user approval, scope the patch to a session/profile, or provide a rollback plan.
3. gateway config.schema.lookup 'agents.defaults.modelSelection'. ... 6. gateway config.patch {modelSelection: {primary: 'best-cheap-model'}}.Use this only with an explicit approve-before-patch workflow: require the agent to show the proposed config diff, expected cost/quality tradeoff, target scope, and rollback command before making changes.
Benchmark prompts may be processed by additional models and may consume tokens; private or sensitive prompts should not be used as test data unless intentionally approved.
Benchmarking through a subagent/model is aligned with the optimizer purpose, but it does involve sending prompts through another agent/model boundary.
4. Benchmark: spawn subagent with test prompts on cheap models.
Use synthetic benchmark prompts, disclose which models/providers will be tested, and get user approval before sending any sensitive content.