Skip to content
Back to skills

Budget Tokens

ASecurity

Compute cost per request and right-size the context to fewest-high-precision chunks. Reach for this on a cost/context question.

  • 7 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added September 23, 2026
ai-agents

Security analysis

A100/100

Scanned September 23, 2026

npx -y skills add mcorbett51090/RavenClaude --skill budget-tokens --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Budget Tokens?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Budget Tokens
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/mcorbett51090-budget-tokens/badge)](https://www.skillsdirectory.com/skills/mcorbett51090-budget-tokens)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: budget-tokens
description: "Compute cost per request and right-size the context to fewest-high-precision chunks. Reach for this on a cost/context question."
---

# Skill: Budget tokens

More context is not better, and it costs tokens (§3 #5).

## Step 1 — Count the tokens
Input (context + prompt) + output tokens per request (§3 #5).

## Step 2 — Compute cost
Tokens × per-1k price × requests via `ai_rag_engineering_calc.py token-cost`; mark prices unverified (§3 #8).

## Step 3 — Right-size context
Fewest high-precision chunks — guard against lost-in-the-middle (§3 #5).

## Step 4 — Check the fit
Confirm chunk size × top-k fits the window via `ai_rag_engineering_calc.py chunk-budget` (§3 #5).

## Output
A token-cost read and a right-sized context recommendation with the monthly projection.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…