Debug and inspect LLM/AI agent traces using PostHog's MCP tools. Use when the user pastes a trace or session URL (e.g. /ai-observability/traces/<id> or /ai-observability/sessions/<id>), asks to debug a trace, figure out what went wrong, check if an agent used a tool correctly, verify context/files were surfaced, inspect subagent behavior, investigate LLM decisions, or analyze token usage and…
Install
npx skills add PostHog/ai-plugin --skill exploring-llm-tracesnpx skills add PostHog/ai-plugin --skill exploring-llm-traces -a claude-code -gnpx skills add PostHog/ai-plugin --skill exploring-llm-traces -a codex -ggemini skills install https://github.com/PostHog/ai-plugin.git --path skills/exploring-llm-tracesgh skill install PostHog/ai-plugin exploring-llm-tracesgit clone --depth 1 https://github.com/PostHog/ai-plugin /tmp/PostHog__ai-plugin
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/PostHog__ai-plugin/skills/exploring-llm-traces ~/.claude/skills/exploring-llm-traces # Claude Code
cp -R /tmp/PostHog__ai-plugin/skills/exploring-llm-traces ~/.agents/skills/exploring-llm-traces # Codex, Cursor, Gemini CLI, Copilot, OpenCode