Usage Analysis | Agent Skills Atlas

About this skill

Use when the user asks an interpretive question about their Claude Code token spend — budget status across the 5h / 7d / Sonnet-7d billing buckets, which agents/skills/projects are eating their budget, model-distribution drift, or what to change to reduce spend. Regenerates the claude-prospector dashboard as needed and reads the embedded data to answer. Do NOT use for bare "regenerate the dashboard" requests with no question attached (use usage-dashboard instead). Trigger phrases: "am I close to my Claude limit", "how much Sonnet am I using", "where are my Claude tokens going", "what's eating my Claude budget", "which agent uses the most tokens", "why is my Claude spend so high".

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.

Installation guide →

Review, license & listing details

Review the source before using this skill

This is an imported listing. We haven’t certified its safety, license, or compatibility. Skills may include executable scripts.

Automated security scan: Partial

Only SKILL.md was scanned. Supporting files and scripts were not checked. No safety grade has been assigned.

0 potential findings · Scanned 11/4/2026 · Scanner 0.2.1

Content SHA-256: e8348978488d8387057b4ac87d02786876c8a6bd6e95336dd7885d3ebeb8ddf9

About scan coverage and limitations

Original listing metadata

Original name

usage-analysis

Original description

Use when the user asks an interpretive question about their Claude Code token spend — budget status across the 5h / 7d / Sonnet-7d billing buckets, which agents/skills/projects are eating their budget, model-distribution drift, or what to change to reduce spend. Regenerates the `claude-prospector` dashboard as needed and reads the embedded data to answer. Do NOT use for bare "regenerate the dashboard" requests with no question attached (use `usage-dashboard` instead). Trigger phrases: "am I close to my Claude limit", "how much Sonnet am I using", "where are my Claude tokens going", "what's eating my Claude budget", "which agent uses the most tokens", "why is my Claude spend so high".

About this listing

Category: Sales
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.