mcp
Guide for working with Splitrail's MCP server. Use when adding tools, resources, or modifying the MCP interface.
Guide for adding a new AI coding agent analyzer to Splitrail. Use when implementing support for a new tool like Copilot, Cline, or similar.
Claude Code
$ npx -y skills add Piebald-AI/splitrail --skill new-analyzer --agent claude-code
Codex
$ npx skills add Piebald-AI/splitrail --skill new-analyzer -a codex -y
Cursor
$ npx skills add Piebald-AI/splitrail --skill new-analyzer -a cursor -y
Gemini CLI
$ npx skills add Piebald-AI/splitrail --skill new-analyzer -a gemini-cli -y
GitHub Copilot
$ npx skills add Piebald-AI/splitrail --skill new-analyzer -a github-copilot -y
OpenCode
$ npx skills add Piebald-AI/splitrail --skill new-analyzer -a opencode -y
Windsurf
$ npx skills add Piebald-AI/splitrail --skill new-analyzer -a windsurf -y
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.
1. Add variant to `Application` enum in `src/types.rs` 2. Create `src/analyzers/{agent_name}.rs` implementing `Analyzer` trait from `src/analyzer.rs` 3. Export in `src/analyzers/mod.rs` 4. Register in `src/main.rs` 5. Add tests in `src/analyzers/tests/{agent_name}.rs`, export in `src/analyzers/tests/mod.rs` 6. Update README.md 7. (Optional) Add model pricing to `src/models.rs` if agent doesn't provide cost data
Test 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`.
Splitrail is a fast, cross-platform, real-time token usage tracker and cost monitor for: Gemini CLI (and Qwen Code) Claude Code Codex CLI Cline / Roo Code / Zoo Code / Kilo Code (VS Code extension + CLI) GitHub Copilot (VS Code) GitHub Copilot CLI OpenCode Pi
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 updating model pricing in Splitrail. Use when adding new AI model costs or updating existing pricing data.
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…
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…
Ask which skill or flow fits your situation. A router over the skills in this repo.