claude-performance
Measure Claude Code sessions and turn findings into behavioral rules.
Measure Claude Code sessions and turn findings into behavioral rules.
Run a weekly digest over local Claude Code JSONL sessions to measure work patterns such as activity mix, one-shot edit rate, agent usage, model allocation, and project attention. When a diagnostic threshold fires, the plugin appends a concrete rule to CLAUDE.md or adds an investigation item, then measures the same behavior again in later reports. It also sends a one-time anonymous install signal unless the documented opt-out environment variable is set.
Resource types
Use cases
Platforms
Runtime
Add modular agents, skills, rules, memory, and security hooks to coding assistants.
Keep long-running agent plans and shared state durable on disk.
Capabilities
Public GitHub facts last synced Jul 10, 2026.
Write and review more modern, accessible SwiftUI code with an AI coding skill.
Load local UI and native-feature tweaks into the Codex desktop app.