new-analyzer
Skill228 starsChanged 5 months agoMITView on GitHub
Guide for adding a new AI coding agent analyzer to Splitrail. Use when implementing support for a new tool like Copilot, Cline, or similar.
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 0 are distinctive, and 5 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 12
Add variant to Application enum in src/types.rs
- Very specific: line 13
Create src/analyzers/{agent_name}.rs implementing Analyzer trait from src/analyzer.rs
- Very specific: line 16
Add tests in src/analyzers/tests/{agent_name}.rs, export in src/analyzers/tests/mod.rs
- Very specific: line 20
Test fixtures go in src/analyzers/tests/source_data/.
- Very specific: line 24
Use discover_vscode_extension_sources() and get_vscode_extension_tasks_dirs() helpers from src/analyzer.rs.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
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
- Add variant to
Applicationenum insrc/types.rs - Create
src/analyzers/{agent_name}.rsimplementingAnalyzertrait fromsrc/analyzer.rs - Export in
src/analyzers/mod.rs - Register in
src/main.rs - Add tests in
src/analyzers/tests/{agent_name}.rs, export insrc/analyzers/tests/mod.rs - Update README.md
- (Optional) Add model pricing to
src/models.rsif 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
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

