Guide for adding a new AI coding agent analyzer to Splitrail. Use when implementing support for a new tool like Copilot, Cline, or similar.
Scanned 9/3/2026
Install to Claude Code
npx -y skills add Piebald-AI/splitrail --skill new-analyzer --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of New Analyzer?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/piebald-ai-new-analyzer)More formats (shields.io, HTML) on the badges page.
---
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.
---
# Adding a New Analyzer
Splitrail tracks token usage from AI coding agents. Each agent has its own "analyzer" that discovers and parses its data files.
## Checklist
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.
## VS Code Extensions
Use `discover_vscode_extension_sources()` and `get_vscode_extension_tasks_dirs()` helpers from `src/analyzer.rs`.
## Reference Analyzers
- **Simple JSONL CLI**: `src/analyzers/pi_agent.rs`, `src/analyzers/piebald.rs`
- **VS Code extension**: `src/analyzers/cline.rs`, `src/analyzers/roo_code.rs`
- **Complex with dedup**: `src/analyzers/claude_code.rs`
- **External data dirs**: `src/analyzers/opencode.rs`
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.