Enables a side-panel companion that watches your coding session and provides context-aware answers about your codebase and session state through a small, token-cheap MCP interface.
Enables users to view average token throughput, output and reasoning token counts, and recent speed trends for local Codex Desktop conversations through a session panel without modifying the client.
Enables local monitoring of Codex token usage, prompt-cache reuse and estimated credits by reading existing session logs and exposing an embedded dashboard plus tools for whole-chat, latest-call and latest-prompt readings and call history. All collection and refresh stay local on-device, requiring no model calls, API key or hosted backend.
Provides AI coding agents with a read-only live view of a project's task state, including progress, blockers, and evidence, via zero-token conditional polling and an optional widget for rendering a dashboard card.
Provides coding agents with pre-flight cost estimation by analyzing local logs to forecast token usage and quota impact before expensive work, exposing tools for remaining quota, per-task cost estimates, and attempt affordability.