sse-lines-round-extractor

Extract and organize Codex/Claude SSE logs into per-round NDJSON files.

2|Updated Jan 30, 2026
One-click install
npx skills add https://github.com/tankygranny05/agent-box --skill sse-lines-round-extractor
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: sse-lines-round-extractor
Source: https://github.com/tankygranny05/agent-box/tree/main/agent-box/seed/claude-skills/sse-lines-round-extractor
Command: npx skills add https://github.com/tankygranny05/agent-box --skill sse-lines-round-extractor

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This skill automates the process of extracting and organizing data from large, continuously updated SSE (Server-Sent Events) log files, making them easier to analyze and manage.

Core Features & Use Cases

  • Log Freezing: Captures a static snapshot of dynamic log files to ensure consistent processing.
  • Round Extraction: Parses logs to extract individual communication rounds into separate files.
  • Session Indexing: Creates a central index for all extracted sessions, enabling quick lookups.
  • Validation: Verifies the integrity and completeness of the extracted data.
  • Incremental Updates: Supports resuming processing for newly appended log data using checkpoints.
  • Use Case: Process massive sse_lines.jsonl logs from Codex or Claude to create structured, per-round data files, a session index, and validation reports, preventing the need to re-parse large log files.

Quick Start

Run the full extraction workflow for both codex and claude providers, then build the sessions index and validate the outputs.

Frequently Asked Questions about sse-lines-round-extractor

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I extract individual rounds from Claude SSE logs?

To parse Codex or Claude SSE logs into structured files, you freeze the dynamic log into a static snapshot, extract communication rounds into separate NDJSON files, and generate a sessions index with validation artifacts.

What is the best way to process large SSE JSONL log files without re-parsing them every time?

The best way to process large SSE JSONL logs is to freeze them into a static snapshot and use chunked extraction with resume capabilities, allowing you to process newly appended data via checkpoints without re-parsing the entire file.

Can I validate extracted SSE log data against a defined contract?

Yes, you can validate extracted SSE log data against a defined contract to verify the integrity and completeness of the per-round NDJSON outputs, ensuring no data was lost during the extraction process.

Does this log extraction method support both Codex and Claude providers?

Yes, the log extraction method supports both Codex and Claude providers, allowing you to run a full extraction workflow for each provider to create structured, per-round data files and a unified sessions index.

How does log freezing work for continuously updated SSE log files?

Log freezing captures a static snapshot of continuously updated SSE log files to ensure consistent processing, preventing data changes during extraction from corrupting the per-round NDJSON output.