Token Optimizer

Automatically analyze and reduce OpenClaw token waste through context compression, tool-call deduplication insights, model selection guidance, and session hygiene checks. Use when sessions are nearing context limits, costs are climbing, or you want proactive token optimization before expensive tasks.

Before installing or running this skill: - Verify you have the 'openclaw' CLI installed and accessible on PATH. The code calls 'openclaw' via subprocess though the registry metadata lists no required binary. - Review the included code (scripts/token_optimize, src/*.py) yourself — the tool reads session transcript files (~/.openclaw/agents/main/sessions/*.jsonl) and will process potentially sensitive message contents and tool arguments. - Run read-only actions first (e.g., --analyze, --health-check, --compress) to inspect output and confirm behavior. Avoid using --cleanup --apply until you’ve reviewed what 'apply' does (operating-notes indicate it currently issues a gateway restart) and tested in a staging environment. - Confirm where compressed snapshots and config files will be written (~/.openclaw/workspace/token-usage/), and whether that storage is acceptable for your data sensitivity requirements. - Because the skill source is 'unknown' and not from a verified publisher, prefer running it on a non-production system first and consider searching for the repository or contacting the author to verify provenance. If you want, I can list the exact lines where the tool invokes the 'openclaw' CLI and where it reads/writes files so you can more easily audit the risky calls.

Type: OpenClaw Skill Name: mkhaytman-token-optimizer Version: 1.0.0 The skill is classified as suspicious due to two main high-risk capabilities. Firstly, the `token_optimize.py` script allows an arbitrary file write via the `--output` argument, which could overwrite any file on the system if the agent has sufficient permissions, potentially leading to denial of service or system instability, even though the content written is a benign JSON report. Secondly, the `--cleanup --apply` command executes `openclaw gateway restart`, a privileged action that could disrupt the OpenClaw environment. While this action is conditional on detecting 'stuck sessions' and explicitly documented as the only automated cleanup action in `references/operating-notes.md`, it represents a significant impact capability that could be exploited if the conditions for 'stuck sessions' are manipulable.