# tallybook

> tallybook — magna-nz-tallybook. Use this tool when you need to track and compare costs of Claude Code and Codex sessions, or when you want to optimize expenses by identifying cheaper alternatives. It takes transcript data as input and provides detailed cost breakdowns and recommendations as output. Ideal for users who want to monitor and manage their AI session costs over time.

Canonical page: https://skillsregistry.net/skills/magna-nz-tallybook  
JSON: https://api.skillsregistry.net/v1/skills/magna-nz-tallybook

## Description

Prices your Claude Code and Codex sessions from the transcripts on disk, shows what each agent cost over any period, and tells you in plain English what would have been cheaper. CLI, Browser UI and MCP server.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/magna-nz/tallybook)

## 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": "magna-nz-tallybook"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/magna-nz-tallybook` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/magna-nz-tallybook/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