Review recorded AI coding-tool usage and recommend concrete optimizations. Reads real token, cost, session and harness-configuration data from the AI Insights MCP server, then reports ranked, evidence-backed fixes — trimming instruction files, raising the prompt-cache hit rate, right-sizing models, cutting MCP overhead, turning repeated work into skills or commands, and repairing dead hooks, shadowed commands, thin permission allowlists and settings written to layers the tool never reads. Use when the user asks to review, audit or optimize their AI usage, wants to cut token spend or cost, asks why sessions are expensive, slow, or keep running out of context, asks how to structure CLAUDE.md / skills / hooks / MCP servers / subagents, or mentions AI Insights.
Install with
Claude CodeCodexCursorGitHub CopilotGemini CLI
Supported by the Atlas install prompt. Skill-specific requirements vary.
Skill stats
Skills1CategoryGeneralStars0
About this skill
Review recorded AI coding-tool usage and recommend concrete optimizations. Reads real token, cost, session and harness-configuration data from the AI Insights MCP server, then reports ranked, evidence-backed fixes — trimming instruction files, raising the prompt-cache hit rate, right-sizing models, cutting MCP overhead, turning repeated work into skills or commands, and repairing dead hooks, shadowed commands, thin permission allowlists and settings written to layers the tool never reads. Use when the user asks to review, audit or optimize their AI usage, wants to cut token spend or cost, asks why sessions are expensive, slow, or keep running out of context, asks how to structure CLAUDE.md / skills / hooks / MCP servers / subagents, or mentions AI Insights.
Quick start
Copy the install prompt. Use the green button above this README.
Send it to your agent. Paste it into your coding agent’s chat and send.
Review the setup. Your agent checks the skill’s instructions, requirements, and installation scope.
Review recorded AI coding-tool usage and recommend concrete optimizations. Reads real token, cost, session and harness-configuration data from the AI Insights MCP server, then reports ranked, evidence-backed fixes — trimming instruction files, raising the prompt-cache hit rate, right-sizing models, cutting MCP overhead, turning repeated work into skills or commands, and repairing dead hooks, shadowed commands, thin permission allowlists and settings written to layers the tool never reads. Use when the user asks to review, audit or optimize their AI usage, wants to cut token spend or cost, asks why sessions are expensive, slow, or keep running out of context, asks how to structure CLAUDE.md / skills / hooks / MCP servers / subagents, or mentions AI Insights.
About this listing
Category
General
Reported license
MIT
Listing language (estimated)
English
Review status
Not individually reviewed
Agent compatibility
Atlas installation supports Claude Code, Codex, and Cursor. Skill-specific dependencies and features are checked during setup.