Score breakdown
Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.
Why it matters
Useful for developers who cannot tell which project is burning their agent quota; for teams that need per-project agent cost attribution without sending logs to a vendor; for anyone auditing coding-agent spend before renewing a plan.
Who should use it
Who should skip it
Skip tokentab — local CLI that totals Claude Code, Codex, Cursor and Gemini CLI token spend from session logs unless the captured evidence suggests it solves a problem you are actively working on.
About this signal
tokentab — local CLI that totals Claude Code, Codex, Cursor and Gemini CLI token spend from session logs is tracked by RepoRadar as a developer tool in the Agent Cost Tracking section. First seen —; the source record was last checked on 2026-08-28. The current verdict is 'try now' with a Bronze tier and easy setup difficulty. Across RepoRadar's eight signals, tokentab — local CLI that totals Claude Code, Codex, Cursor and Gemini CLI token spend from session logs is strongest on workflow potential (8.8) and setup ease (8.8) and weakest on momentum (7.0) — a profile worth weighing against your own priorities. This page summarizes the public evidence on the linked source page and states where additional review is still needed.
How this item is evaluated
The tokentab — local CLI that totals Claude Code, Codex, Cursor and Gemini CLI token spend from session logs record combines a 7.3/10 composite score with separate popularity (100.0), risk (conditional), and setup (easy) signals. See the scoring methodology for the current weights and evidence definitions.
Questions worth asking before you adopt this
Putting this into practice? Read How to vet an AI agent or MCP server before you wire it in for the checklist behind this score.
Risk explanation
The tool reads local agent session logs, which contain your prompts and code context; it stays local per the README, but confirm that before running it on a shared machine; Cost figures are derived from published model pricing, not from your provider invoice; treat them as an estimate.