Model Usage Linux
PassAudited by ClawScan on May 1, 2026.
Overview
This skill is a local usage summarizer that reads OpenClaw session logs and prints aggregate token and cost totals, with no network, credential, write, or persistence behavior shown.
This appears safe for its stated purpose if you are comfortable with it reading OpenClaw session logs. Run it manually, consider using --sessions-dir to point at a limited set of files, and do not rely on the --session option for filtering unless it is fixed.
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.
Running the skill lets it process local OpenClaw session logs to calculate usage totals.
The script reads local OpenClaw session JSONL files, which may contain sensitive conversation history even though the script only summarizes usage fields.
DEFAULT_SESSIONS_DIR = os.path.expanduser("~/.openclaw/agents/main/sessions") ... jsonl_files = list(sessions_dir.glob("*.jsonl"))Use it only on session directories you are comfortable processing, and prefer --sessions-dir pointing to a limited directory if you want narrower scope.
A user expecting --session to limit analysis to one session could still get aggregate results from all sessions in the directory.
The command-line help suggests a specific-session scope, but main() never uses args.session and instead iterates over every *.jsonl file in the chosen sessions directory.
p.add_argument("--session", help="Specific session ID or 'all' (default: all)") ... for f in jsonl_files:Do not rely on --session for scoping until the script implements it; use a separate directory with only the intended session files if precise limiting is needed.