Use token-budget-estimator

Estimates input and output token usage for a described agentic workflow, surfaces the dominant cost drivers, and suggests max_tokens budget controls per component

Estimates input and output token usage for a described agentic workflow, surfaces the dominant cost drivers, and suggests max_tokens budget controls per component.

Reach for it when planning a new Claude API integration, sizing a cost budget for a feature, or diagnosing why a workflow's token usage is higher than expected.

Install it

npx skilldrop-cli install token-budget-estimator                 # Claude Code, your user folder
npx skilldrop-cli install token-budget-estimator --project       # Claude Code, this repo
npx skilldrop-cli install token-budget-estimator --ide cursor    # or kiro, codex, antigravity, copilot

It is part of the API builder pack: --pack api-builder installs it with its neighbours.

Ask for it

Say it the way you would to a colleague. Requests like these route to it:

• "How many tokens will this agentic workflow use per session?"
• "Size a cost budget for our new Claude integration before we build it"
• "Our agent's token usage is way higher than expected — break down where it's going"
• "Suggest max_tokens limits per component for this multi-turn tool-using agent"

Requests like these belong to a different skill, so it shouldn't answer them:

• "Exactly where should the cache_control checkpoints go in this prompt?"
• "Put spending caps and budget kill-switches on our fleet of autonomous agents"
• "Design the agent loop: when to stop, retry, and hand back to the user"

If another skill answers instead, ask for this one by name: "use token-budget-estimator".

Check what you get

A good result:

• Ranges over false precision. "~2,000–4,000 tokens" is more honest than "3,142 tokens" when you're working from a description. Use ranges when working from descriptions, tighter estimates when working from actual content.
• The table beats the total. A single "~50,000 tokens per session" is nearly useless — the table that shows context accumulation accounts for 40,000 of those gives the developer somewhere to act.
• Name the optimization target. Don't list five optimizations without ranking them. The one that saves 80% of the dominant component beats the one that shaves 5% off a small component.

Next

• SKILL.md, the instructions the agent reads
• Its page on the site
• Related: prompt-caching-advisor, agent-budget

Edit this page on GitHub · View source