# tokentoll

> Use this tool when you need to estimate and manage costs associated with Large Language Model (LLM) API calls in your codebase. Tokentoll scans codebases to identify LLM API calls and provides monthly cost estimates, allowing you to compare costs between different git refs and catch cost regressions during code review. It takes code repositories as input and outputs estimated costs, helping you optimize your budget and prevent unexpected expenses.

Canonical page: https://skillsregistry.net/skills/jwrede-tokentoll  
JSON: https://api.skillsregistry.net/v1/skills/jwrede-tokentoll

## Description

Scan codebases for LLM API calls and estimate monthly costs. Compare costs between git refs to catch cost regressions during code review.

## Trust

- **Trust score (0–1):** 0.88
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** version-control
- **Updated:** 2026-09-19

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/hjfrc5802t)
- **Repository:** <https://github.com/Jwrede/tokentoll>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "jwrede-tokentoll"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/jwrede-tokentoll` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/jwrede-tokentoll/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt