openclaw-cost-guard

✓Verified·Scanned 2/17/2026

This skill extracts token and USD cost data from OpenClaw/Clawdbot session logs, summarizes usage, lists top sessions, and performs budget checks. It reads ~/.openclaw/agents/*/sessions/*.jsonl and ~/.clawdbot/agents/*/sessions/*.jsonl, uses PRICE_INPUT/PRICE_OUTPUT/PRICE_CACHE_READ/PRICE_CACHE_WRITE env vars, and shows python3 scripts/extract_cost.py example commands.

from clawhub.ai·v3b3fe03·13.9 KB·0 installs
Scanned from 0.1.0 at 3b3fe03 · Transparency log ↗
$ vett add clawhub.ai/dasweltall/openclaw-cost-guard

openclaw-cost-guard

Track real OpenClaw/Clawdbot usage + cost from session JSONL logs, generate summaries, and support budget alerts.

What it does

  • Reads OpenClaw logs: ~/.openclaw/agents/*/sessions/*.jsonl
  • Also reads legacy logs: ~/.clawdbot/agents/*/sessions/*.jsonl
  • Extracts per-call usage from message.usage (tokens + cost breakdown when available)
  • Summarizes cost by day and can list top expensive sessions
  • Can act as a budget check (exit code 2 on breach) so it can be wired into cron/alerts

Quick start

python3 scripts/extract_cost.py --today
python3 scripts/extract_cost.py --last-days 7
python3 scripts/extract_cost.py --today --top-sessions 10
python3 scripts/extract_cost.py --today --top-sessions 10 --json

Budget alerts

Exit code behavior:

  • 0 = OK
  • 2 = budget exceeded

Examples:

python3 scripts/extract_cost.py --today --budget-usd 5

# non-failing (always exit 0)
python3 scripts/extract_cost.py --today --budget-usd 5 --budget-mode warn

Fallback cost estimation (optional)

If a provider doesn’t write usage.cost, you can estimate using env vars (per 1M tokens):

export PRICE_INPUT=1.75
export PRICE_OUTPUT=14
export PRICE_CACHE_READ=0.175
export PRICE_CACHE_WRITE=0

python3 scripts/extract_cost.py --last-days 7

Token-saving playbook

See SKILL.md (kept short on purpose). It includes a playbook the agent can follow to keep output/tool usage minimal.