# Token Budgeter

> Track and enforce token budgets per tier.

- Skill: `cleanexpo/token-budgeter` (Agent Skill)
- Install (CLI): `npx skillmds@latest add cleanexpo/token-budgeter`
- Raw SKILL.md: https://api.skillmd.com/api/skills/cleanexpo/token-budgeter/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: cleanexpo (https://skillmd.com/u/cleanexpo)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/cleanexpo/token-budgeter

---


# Token Budgeter

## Model Costs (April 2026)
- Opus 4.7: $15.00 / M output tokens ($75 input cache write, $3.75 cache read)
- Sonnet 4.6: $3.00 / M output tokens ($3 input, $0.30 cache read)
- Haiku 4.5: $1.25 / M output tokens ($0.80 input, $0.08 cache read)

On Claude Max: $0 for everything — all execution is via `claude` CLI subprocess.