$ loading_
Monitor Claude usage live, predict limits, and control costly AI coding actions.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "mcp-token-saver" yet — see the docs or source repo.
Please read my current Claude subscription usage, tell me the remaining quota, estimate when I may hit the limit, and assess whether now is a good time to start a large code refactoring request.
Returns current usage, remaining quota, predicted limit timing, and a recommendation on whether to run the large task now.
Before generating the full project test suite and a complete code review, check live usage first; if the cost is too high or I am near the limit, block the operation and suggest lower-usage alternatives.
Decides whether to allow the task based on live quota and provides savings options like splitting tasks or narrowing scope.
Help me track the actual subscription consumption for this task, 'fix the login module bug and add tests'; after completion, output a cost summary and compare it with the previous similar task.
Produces the task’s real consumption, a cost summary, and a historical comparison to optimize future AI usage.
Query Claude Code transcript analytics for cost, safety, audit, and efficiency insights.
Check Claude Code rate-limit capacity before launching subtasks.
Monitor Claude Code costs, ROI, budgets, anomalies, and usage forecasts.
Detects wasteful AI token usage and warns about verbose, repetitive context.
Route lightweight text tasks to cheaper models and save main-model tokens.
Control Claude Code sessions in tmux with fine-grained orchestration and efficient extraction.