Parse Pi session JSONL files with jq to extract metrics and tool usage.
npx skills add https://github.com/oddship/bosun --skill session-analysis-oddship
Please help me install this Agent Skill. Skill: session-analysis Source: https://github.com/oddship/bosun/tree/main/.pi/skills/session-analysis Command: npx skills add https://github.com/oddship/bosun --skill session-analysis-oddship
This Skill helps you quickly extract valuable insights, metrics, and historical data from Pi session log files, which are often large and complex.
jq patterns to pull specific information like model usage, user prompts, assistant responses, tool calls, and file interactions.Use the session-analysis skill to count the number of user messages in the file 'session.jsonl'.
High-intent search queries and answers about installing and using this skill.
You can extract tool usage metrics from Pi session logs by applying jq patterns to parse the JSONL files. This process identifies specific tool calls, message types, and interaction frequencies to summarize workflow patterns within the session history.
The best way to calculate token costs from a Pi session JSONL file is to parse the structured log data using jq. This allows you to extract usage statistics and compute total costs per session turn based on model interactions.
Yes, you need jq installed because this session analysis process requires it to process structured log data. jq is used to query the JSONL files and extract the necessary metrics, tool usage, and cost data.
Yes, you can summarize assistant responses and user prompts from session logs using jq. By parsing the JSONL format, jq filters specific message types to isolate user inputs and assistant outputs for session summarization.
To locate and list Pi session files for data extraction, you can utilize session discovery features within the analysis workflow. This identifies available JSONL log files so you can subsequently parse them for metrics and usage statistics.
When parsing session JSONL files for workflow analysis, you should look for patterns in message types, tool calls, and usage statistics. Identifying these patterns helps track file interactions and model usage throughout the session history.
zkcpkuSearch and analyze past conversation logs in JSONL files using jq and rg.
aresbitAnalyze CodexBar cost logs to report per-model usage and costs.
sentientspriteSearch and analyze past conversation logs in JSONL files using jq and rg.
mikkeymooGenerate session and project health metrics from JSONL logs, Git status, and hooks configuration.