Monitor context window usage, token consumption, and session costs from statusLine JSON.
npx skills add https://github.com/zylos-ai/zylos-core --skill check-context
Please help me install this Agent Skill. Skill: check-context Source: https://github.com/zylos-ai/zylos-core/tree/main/skills/check-context Command: npx skills add https://github.com/zylos-ai/zylos-core --skill check-context
This Skill provides clear visibility into the AI's current context window usage and token consumption, helping to manage resources and understand operational costs.
Check the current context window usage and token consumption.
High-intent search queries and answers about installing and using this skill.
Check AI context window usage by parsing the statusLine JSON file to report input and output tokens, total window size, and remaining context capacity for real-time resource monitoring.
Track session costs and token usage by monitoring real-time metrics that display estimated USD costs alongside input and output token consumption throughout extended LLM interactions.
Prevent context truncation by checking if the current context window is sufficient before starting a long-running task, ensuring the remaining token capacity can handle the extended interaction.
Context monitoring works by parsing the statusLine JSON file to extract real-time metrics for context window usage, token consumption, and session costs without requiring external dependencies.
Estimate operational costs for LLM resource allocation by tracking the estimated session cost in USD, helping you manage resources and understand financial expenditures during extended AI operations.
Context monitoring limitations include relying entirely on parsing the statusLine JSON file for metrics, meaning it cannot track historical usage or predict future token consumption beyond the current session's real-time data.
richardmbaileyAnalyzes Codex session JSONL files to extract and report token usage metrics.
gonzalezpazmonicaCompress AI context windows using a 5-phase framework to reduce token usage.
ProyectoG007Monitor OpenClaw AI agents with a real-time dashboard.
Prathmesh2000Analyze and estimate token usage for LLM API calls.
