tokentoll
01MCP server Claude CodeCodexCursor +2
Catch LLM cost changes in code review. Infracost for LLM spend. Runs locally from the tokentoll Python package.
4 3mo ago A
tokens not measured
original MIT
llmprobe
02Plugin Claude Code
Synthetic monitoring for LLM inference endpoints. Measure TTFT, latency, throughput, and errors.
3 3mo ago A
tokens not measured
original MIT
llmprobe
03Skill Claude CodeCodex
Check LLM API endpoint health, measure TTFT, latency, and throughput. Use when deploying LLM-powered features, debugging slow AI responses, verifying provider SLAs, checking if an LLM API is down, or measuring inference performance before a deploy.
3 3mo ago A 51 tokens
original MIT
llmprobe
04MCP server Claude CodeCodexCursor +2
MCP server "llmprobe" as configured in Jwrede/llmprobe. Launched with llmprobe mcp.
3 3mo ago A
tokens not measured
original MIT