Use when the user asks about THIS Claude Code session's token, cost, or runtime metrics — cost so far, tokens burned, runtime/elapsed/working time, per-model split (Opus/Sonnet/Haiku), or controller-vs-subagent breakdown. Fires whether they want the numbers shown directly ("how much has this cost", "how long has this been running", "what's my token usage") or formatted to embed elsewhere (PR body, commit message, changelog, Slack, standup, status update — e.g. "give me a markdown block of session stats", "drop the cost into the PR description"). Trigger on intent, not verb — show, share, include, append, post, drop, paste, give me all qualify. Do NOT trigger for lines-of-code or git-diff stats (this skill is about API spend, not code volume), Anthropic API list pricing, console.anthropic.com / org billing dashboards, plan-tier comparisons (Pro vs Max), prompt benchmarking, or sessions in a different working directory.
Install with
Claude CodeCodexCursorGitHub CopilotGemini CLI
Supported by the Atlas install prompt. Skill-specific requirements vary.
Skill stats
Skills1CategoryGeneralStars0
About this skill
Use when the user asks about THIS Claude Code session's token, cost, or runtime metrics — cost so far, tokens burned, runtime/elapsed/working time, per-model split (Opus/Sonnet/Haiku), or controller-vs-subagent breakdown. Fires whether they want the numbers shown directly ("how much has this cost", "how long has this been running", "what's my token usage") or formatted to embed elsewhere (PR body, commit message, changelog, Slack, standup, status update — e.g. "give me a markdown block of session stats", "drop the cost into the PR description"). Trigger on intent, not verb — show, share, include, append, post, drop, paste, give me all qualify. Do NOT trigger for lines-of-code or git-diff stats (this skill is about API spend, not code volume), Anthropic API list pricing, console.anthropic.com / org billing dashboards, plan-tier comparisons (Pro vs Max), prompt benchmarking, or sessions in a different working directory.
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.
Use when the user asks about THIS Claude Code session's token, cost, or runtime metrics — cost so far, tokens burned, runtime/elapsed/working time, per-model split (Opus/Sonnet/Haiku), or controller-vs-subagent breakdown. Fires whether they want the numbers shown directly ("how much has this cost", "how long has this been running", "what's my token usage") or formatted to embed elsewhere (PR body, commit message, changelog, Slack, standup, status update — e.g. "give me a markdown block of session stats", "drop the cost into the PR description"). Trigger on intent, not verb — show, share, include, append, post, drop, paste, give me all qualify. Do NOT trigger for lines-of-code or git-diff stats (this skill is about API spend, not code volume), Anthropic API list pricing, console.anthropic.com / org billing dashboards, plan-tier comparisons (Pro vs Max), prompt benchmarking, or sessions in a different working directory.
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.