Track token use across Clawdbot sessions and estimate API costs for supported Claude, GPT, and Codex models. Save daily snapshots, compare usage between dates, and produce cost figures for daily or weekly spending reports.
Track Clawdbot AI model usage and estimate costs. Use when reporting daily/weekly costs, analyzing token usage across sessions, or monitoring AI spending. Supports Claude (opus/sonnet), GPT, and Codex models.
Run score Not tested
See how to installReview the instructions the agent will receive before you install.
Track token usage and estimate API costs across all Clawdbot sessions.
# Use sessions_list to get token data
sessions_list --limit 20 --messageLimit 0
Extract totalTokens and model from each session.
Model pricing (USD per million tokens):
| Model | Input | Output | Avg Ratio |
|---|---|---|---|
| claude-opus-4-5 | $15 | $75 | 30/70 |
| claude-sonnet-4 | $3 | $15 | 30/70 |
| codex-mini-latest | $1 | $5 | 30/70 |
| gpt-4o | $2.5 | $10 | 30/70 |
| gpt-4o-mini | $0.15 | $0.6 | 30/70 |
Cost formula (assuming 30% input, 70% output):
cost = tokens * (0.3 * input_price + 0.7 * output_price) / 1,000,000
Store daily snapshots in memory/usage/YYYY-MM-DD.json:
{
"date": "2026-01-29",
"timestamp": "2026-01-29T08:20:00+08:00",
"sessions": {
"session_key": {
"model": "claude-opus-4-5",
"totalTokens": 123456,
"channel": "discord"
}
},
"summary": {
"totalTokens": 250000,
"byModel": {
"claude-opus-4-5": 220000,
"codex-mini-latest": 30000
}
}
}
Compare consecutive days to get daily usage:
daily_tokens = today.totalTokens - yesterday.totalTokens
daily_cost = estimate_cost(daily_tokens, model)
scripts/snapshot-usage.jsCreates a usage snapshot from current session data.
node scripts/snapshot-usage.js [output-dir]
# Default output: memory/usage/YYYY-MM-DD.json
scripts/calculate-cost.jsCalculates cost for a date range.
node scripts/calculate-cost.js [date]
# Default: today
# Output: JSON with token delta and estimated cost
Add to HEARTBEAT.md:
sessions_list to get current tokensmemory/usage/💰 **Clawdbot Cost** (yesterday)
• Used: 45.2k tokens
• Estimated: ~$1.23
For financial displays in Chinese context:
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Set up and use the 1Password command-line tool `op` to sign in, verify account access, and work with vault data. The skill covers single or multiple accounts and shows how to run commands or fill templates with secrets while limiting exposure in logs and files.
Check live prices, price changes, and trading volume for Shanghai, Shenzhen, and Beijing stocks. Review intraday volume patterns and possible large-investor activity, and manage holdings with cost, quantity, and profit or loss summaries.
Scan HTML or JSX files and directories for accessibility issues such as missing image descriptions, form labels, and keyboard access problems. The skill identifies WCAG guideline failures and provides suggested code fixes alongside its findings.
Plan A/B tests that compare page or product changes, with clear hypotheses, sample sizes, success metrics, and traffic allocation. Get a structured test plan and guidance for interpreting results and deciding what to try next.
Turn LinkedIn profile URLs into coordinated account-based outreach. The workflow gathers profile details, enriches contacts with email and phone data, looks up mailing addresses, and prepares email, LinkedIn, and handwritten-letter touches with the specified services.
Work with Apple Calendar on macOS to list calendars, find and view events, and check busy time slots across calendars. Create, update, or delete events with details such as dates, locations, and descriptions.