claude-usage
Check Claude Max plan usage limits by launching Claude Code and running /usage. Use when the user asks about Claude plan usage, remaining quota, rate limits, or sends /claude_usage.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/chunhualiao/openclaw-claude-usageWhat This Skill Does
The claude-usage skill provides a mechanism for OpenClaw to retrieve real-time data regarding your Claude Max subscription limits. Because Claude Code's usage information is presented within an interactive terminal UI (TUI) rather than as a standard machine-readable CLI output, this skill utilizes expect automation to spawn the process, navigate the interface, and extract key metrics. It parses terminal output to inform you of current session consumption, weekly model usage, and specific Sonnet-only quotas, ensuring you stay within your plan's bounds.
Installation
To install this skill, run the following command in your terminal:
clawhub install openclaw/skills/skills/chunhualiao/openclaw-claude-usage
Ensure that you have the expect package installed on your system. On macOS, this is typically pre-installed at /usr/bin/expect. Additionally, verify that the claude CLI is installed and that you are already authenticated through your terminal environment before invoking the skill.
Use Cases
Use this skill whenever you need granular visibility into your AI service consumption. It is particularly useful for power users who leverage Claude heavily for coding tasks throughout the week. If you receive rate-limit notifications or simply want to plan your workflow to avoid hitting quota caps, this skill provides the necessary transparency. It acts as a bridge between the interactive nature of the Claude Code tool and the programmatic requirements of the OpenClaw agent.
Example Prompts
- "Check how much of my Claude weekly quota I have left."
- "/claude_usage - tell me if I'm close to my Sonnet rate limit."
- "Am I going to run out of my current session tokens soon?"
Tips & Limitations
- Expect Dependency: This skill relies on
expectscripts. If your environment lacks this utility, the skill will gracefully fall back to checking~/.claude/stats-cache.json. Note that the fallback method is less precise than the primary method. - Authentication: Ensure your terminal has an active session with Claude Code. If the
claudecommand requires manual login, the script may fail to execute correctly. - ANSI Parsing: The skill includes logic to strip ANSI escape codes, but extreme changes in the TUI layout by future Claude Code updates might require adjustment to the regex parsing logic used in the script.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-chunhualiao-openclaw-claude-usage": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-read, code-execution
Related Skills
task-runner
Persistent task queue system. Users add tasks at any time via natural language; tasks are stored in a single persistent queue file and executed asynchronously via subagents. A heartbeat/cron dispatcher wakes periodically to check pending tasks, spawn workers, and report completions. The system never "finishes" — it always remains ready for the next task.
git-repo-to-book
Write a full-length technical book using multi-agent AI orchestration. Spawns parallel research, writing, and review agents to produce 60K-100K+ word manuscripts. Also supports revising individual chapters of existing books. Based on the real workflow that produced an 88,000-word, 14-chapter book in under 18 hours.
skill-engineer
Design, test, review, and maintain agent skills for OpenClaw systems using multi-agent iterative refinement. Orchestrates Designer, Reviewer, and Tester subagents for quality-gated skill development. Use when user asks to "design skill", "review skill", "test skill", "audit skills", "refactor skill", or mentions "agent kit quality".
rose-container-tools
Build and run ROSE compiler tools using ROSE installed in a Docker container. Use when developing source-to-source translators, call graph analyzers, AST processors, or any tool that links against librose.so. Triggers on "ROSE tool", "callgraph", "AST traversal", "source-to-source", "build with ROSE", "librose".
deepwiki
Query DeepWiki MCP to get AI-grounded answers about any public GitHub repository. Use when answering questions about a repo's source code, architecture, configuration, or internals. Triggers on "how does X work in <repo>", "deepwiki", "look up in codebase", "ask deepwiki", "check the source code".