claude-usageCalculate Claude Max subscription usage from OpenClaw session data. Shows credits consumed, weekly budget percentage, 5-hour rate limit window, and per-session breakdown.
Install via ClawdBot CLI:
clawdbot install lemodigital/claude-usageTrack your Claude Max subscription usage based on the reverse-engineered credits system from she-llac.com/claude-limits.
When the user asks about Claude usage, credits, subscription consumption, rate limits, or wants to know how much budget is left.
Ask the user for:
pro ($20), 5x ($100), or 20x ($200). Default: 5xSave it so they never have to repeat:
python3 {SKILL_DIR}/scripts/claude-usage.py "2026-02-09 14:00" --plan 5x --save# Weekly overview (uses saved config after first --save)
python3 {SKILL_DIR}/scripts/claude-usage.py
# Override plan or timezone
python3 {SKILL_DIR}/scripts/claude-usage.py --plan 20x --tz "America/New_York"
# Top N sessions only
python3 {SKILL_DIR}/scripts/claude-usage.py --top 5
# Single session detail (substring match on key or id)
python3 {SKILL_DIR}/scripts/claude-usage.py --session "main"
python3 {SKILL_DIR}/scripts/claude-usage.py --session "9aadee"
# JSON output
python3 {SKILL_DIR}/scripts/claude-usage.py --json--session)credits = (input_tokens + cache_write_tokens) Ć input_rate + output_tokens Ć output_rate| Model | Input rate | Output rate |
|--------|-----------|-------------|
| Haiku | 2/15 | 10/15 |
| Sonnet | 6/15 | 30/15 |
| Opus | 10/15 | 50/15 |
Cache reads are free. Non-Claude models (Gemini, Codex, etc.) don't consume Claude credits.
| Plan | $/month | Credits/5h | Credits/week |
|------|---------|-----------|-------------|
| Pro | $20 | 550,000 | 5,000,000 |
| 5Ć | $100 | 3,300,000 | 41,666,700 |
| 20Ć | $200 | 11,000,000| 83,333,300 |
~/.openclaw/agents/main/sessions/)Generated Mar 1, 2026
A freelance developer using Claude Max via OpenClaw for client projects needs to track usage to stay within subscription limits and avoid overage charges. This skill helps them monitor weekly credits, identify high-cost sessions, and adjust usage patterns to optimize their budget.
A small marketing team relies on Claude Max for content generation and editing tasks. They use this skill to allocate usage across team members, ensure they don't exceed the 5-hour rate limit during peak work hours, and report on model-specific costs for budgeting.
Researchers using Claude Max for data analysis and paper drafting need to track usage to comply with grant-funded subscription plans. This skill provides detailed session breakdowns to justify expenses and optimize token usage across Haiku, Sonnet, and Opus models.
A startup integrating Claude Max into their product via OpenClaw uses this skill to monitor API consumption, forecast costs based on user growth, and set alerts for approaching rate limits to maintain service reliability.
An IT team managing Claude Max subscriptions for multiple departments uses this skill to enforce usage policies, generate JSON reports for auditing, and identify inefficient sessions to reduce overall subscription costs.
Offer a service that helps businesses optimize their Claude Max usage by providing automated monitoring, alerts for budget thresholds, and detailed analytics. Charge a monthly fee based on the number of subscriptions managed or usage volume analyzed.
Provide consulting to organizations using Claude Max, using this skill to audit usage patterns and recommend adjustments like switching models or rescheduling high-volume tasks. Charge per project or hourly rates for analysis and implementation.
Develop and sell custom integrations of this skill into existing business workflows, such as dashboards or reporting tools, with enhanced features like real-time alerts or multi-user support. Revenue comes from one-time development fees or ongoing support contracts.
š¬ Integration Tip
Integrate this skill into existing monitoring dashboards by using the --json output option for easy data parsing, and automate setup with saved configurations to reduce user friction.
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Search and analyze your own session logs (older/parent conversations) using jq.
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.
Ultimate AI agent memory system for Cursor, Claude, ChatGPT & Copilot. WAL protocol + vector search + git-notes + cloud backup. Never lose context again. Vibe-coding ready.
Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection