Menu
Guide for adding a new AI coding agent analyzer to Splitrail. Use when implementing support for a new tool like Copilot, Cline, or similar.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Guide for updating model pricing in Splitrail. Use when adding new AI model costs or updating existing pricing data.
Guide for working with Splitrail's MCP server. Use when adding tools, resources, or modifying the MCP interface.
Performance optimization guidelines for Splitrail. Use when optimizing parsing, reducing memory usage, or improving throughput.
Guide for Splitrail's terminal UI and file watching. Use when modifying the TUI, stats display, or real-time update logic.
Reference for Splitrail's core data types. Use when working with ConversationMessage, Stats, DailyStats, or other type definitions.
| name | new-analyzer |
| description | Guide for adding a new AI coding agent analyzer to Splitrail. Use when implementing support for a new tool like Copilot, Cline, or similar. |
Splitrail tracks token usage from AI coding agents. Each agent has its own "analyzer" that discovers and parses its data files.
Application enum in src/types.rssrc/analyzers/{agent_name}.rs implementing Analyzer trait from src/analyzer.rssrc/analyzers/mod.rssrc/main.rssrc/analyzers/tests/{agent_name}.rs, export in src/analyzers/tests/mod.rssrc/models.rs if agent doesn't provide cost dataTest fixtures go in src/analyzers/tests/source_data/. See src/types.rs for message and stats types.
Use discover_vscode_extension_sources() and get_vscode_extension_tasks_dirs() helpers from src/analyzer.rs.
src/analyzers/pi_agent.rs, src/analyzers/piebald.rssrc/analyzers/cline.rs, src/analyzers/roo_code.rssrc/analyzers/claude_code.rssrc/analyzers/opencode.rs