Analyzes Codex session JSONL files to extract and report token usage metrics.
npx skills add https://github.com/richardmbailey/rb-skills --skill rb-context-tokens
Please help me install this Agent Skill. Skill: rb-context-tokens Source: https://github.com/richardmbailey/rb-skills/tree/main/rb-context-tokens Command: npx skills add https://github.com/richardmbailey/rb-skills --skill rb-context-tokens
This skill solves the uncertainty regarding how much of the Codex context window is currently consumed, preventing unexpected model behavior or truncation due to token limits.
Ask the agent to report the current context token usage by invoking the rb-context-tokens skill.
High-intent search queries and answers about installing and using this skill.
To monitor Codex context window token usage, this Skill parses local session JSONL files to extract real-time token consumption metrics from token_count events. It automatically identifies your most recent session log to report current input, output, and cached token counts.
Checking context token utilization before complex tasks is handled by analyzing session JSONL files to calculate percentage-based usage statistics. This reports how much of the context window is consumed, helping prevent unexpected model behavior or truncation.
Yes, you can retrieve a report of input and output token counts by parsing your latest Codex session JSONL files. The Skill extracts these precise metrics from the most recent session events to provide an accurate token usage breakdown.
Yes, you need local session logs to analyze token consumption metrics. The Skill requires access to local Codex session JSONL files to parse token_count events and calculate the percentage-based context-window utilization statistics.
Unexpected model behavior or truncation occurs when context window token limits are reached. This Skill solves that uncertainty by monitoring real-time token consumption from session JSONL files so you can verify context utilization before initiating complex tasks.
Yes, this token monitoring Skill works with cached token counts by extracting them from session JSONL files. It parses token_count events to provide precise metrics on input, output, and cached tokens from the latest development session.
tkerseyParse Codex JSONL session logs to extract skill usage and token counts.
MasterleeausCheck AI context window usage and token consumption from runtime status files.
wangqianCAISummarize CodexBar JSONL cost logs for Codex and Claude providers.
abhattacherjeeParse JSONL transcripts to display color-coded Claude Code context usage.
