mcp
Guide for working with Splitrail's MCP server. Use when adding tools, resources, or modifying the MCP interface.
@piebald-aiInstall SkillDevelopment
Skill
/performance
Performance optimization guidelines for Splitrail. Use when optimizing parsing, reducing memory usage, or improving throughput.
Claude Code
$ npx -y skills add Piebald-AI/splitrail --skill performance --agent claude-code
Codex
$ npx skills add Piebald-AI/splitrail --skill performance -a codex -y
Cursor
$ npx skills add Piebald-AI/splitrail --skill performance -a cursor -y
Gemini CLI
$ npx skills add Piebald-AI/splitrail --skill performance -a gemini-cli -y
GitHub Copilot
$ npx skills add Piebald-AI/splitrail --skill performance -a github-copilot -y
OpenCode
$ npx skills add Piebald-AI/splitrail --skill performance -a opencode -y
Windsurf
$ npx skills add Piebald-AI/splitrail --skill performance -a windsurf -y
SKILL.md
performance.SKILL.mdname: performance description: Performance optimization guidelines for Splitrail. Use when optimizing parsing, reducing memory usage, or improving throughput.
Performance Considerations
Techniques Used
- **Parallel analyzer loading** - `futures::join_all()` for concurrent stats loading
- **Parallel file parsing** - `rayon` for parallel iteration over files
- **Fast JSON parsing** - `simd_json` exclusively for all JSON operations (note: `rmcp` crate re-exports `serde_json` for MCP server types)
- **Fast directory walking** - `jwalk` for parallel directory traversal
- **Lazy message loading** - TUI loads messages on-demand for session view
See existing analyzers in `src/analyzers/` for usage patterns.
Guidelines
1. Prefer parallel processing for I/O-bound operations 2. Use `parking_lot` locks over `std::sync` for better performance 3. Avoid loading all messages into memory when not needed 4. Use `BTreeMap` for date-ordered data (sorted iteration)
Ships withsplitrail
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
2276 skills
Stars on GitHub
Momentum
- stars in total
- 227
Other skills on splitrail.
@piebald-aiInstall Skillnew-analyzer
Guide for adding a new AI coding agent analyzer to Splitrail. Use when implementing support for a new tool like Copilot, Cline,…
@piebald-aiInstall Skillpricing
Guide for updating model pricing in Splitrail. Use when adding new AI model costs or updating existing pricing data.
@piebald-aiInstall Skilltui
Guide for Splitrail's terminal UI and file watching. Use when modifying the TUI, stats display, or real-time update logic.
@piebald-aiInstall Skilltypes
Reference for Splitrail's core data types. Use when working with ConversationMessage, Stats, DailyStats, or other type…
@piebald-aiInstall SkillMore skills from other plugins.
Auto-invoked
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…
@obraInstall Skillask-matt
Ask which skill or flow fits your situation. A router over the skills in this repo.
@mattpocockInstall SkillAuto-invoked
Questions about performance.
- Which coding agents can use performance?
- performance installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.