CLI to budget Claude Code session costs
Per-task budget tracking for Claude Code when the official CLI lacks cost controls.
Various Claude Skills created along the way
Real-time cost tracking for Claude Code sessions; saves money intuition before you ship.
Claude Code users, AI application developers
I use it in interactive Claude Code sessions. For example, if I want to add a Claude API feature to an app, I'll often hack it together first in CC. This skill lets me start and stop tracking so I get get a sense for what the API costs will be.
For example:
> /cost-tracking > [do stuff] > stop tracking
Then I get a nice little table showing tokens and cost for the model that was used:
Haiku cost report (this session's work):
┌───────────────────┬───────────┬─────────┐ │ Category │ Tokens │ Cost │ ├───────────────────┼───────────┼─────────┤ │ Base input │ 182 │ $0.0002 │ ├───────────────────┼───────────┼─────────┤ │ Output │ 3,276 │ $0.0164 │ ├───────────────────┼───────────┼─────────┤ │ Cache writes (1h) │ 25,619 │ $0.0512 │ ├───────────────────┼───────────┼─────────┤ │ Cache reads │ 1,585,531 │ $0.1586 │ ├───────────────────┼───────────┼─────────┤ │ Grand Total │ │ $0.2264 │ └───────────────────┴───────────┴─────────┘
Per-task budget tracking for Claude Code when the official CLI lacks cost controls.
Like top for AI agents: tracks token costs across 6 coding agents, 100% offline.
Prompt clustering with cost attribution when LangSmith already does observability.
Strava for AI coding, but leaderboards gamify the wrong metric.
Claude Code usage dashboard reading local files—fills exact gap Anthropic didn't address.
Debugger for Claude Code sessions—niche but solves real frustration with cost visibility.