# tokenscope

> tokenscope — wartzar-bee-tokenscope. Use this tool when you need to analyze and optimize Claude Code session token usage and cost, solving problems of inefficient token allocation and unexpected expenses. It takes local session files as input and provides detailed breakdowns of cache-read, cache-write, and output costs, as well as context window consumption. Use tokenscope to identify areas of improvement and reduce token spend in your Claude Code applications.

Canonical page: https://skillsregistry.net/skills/wartzar-bee-tokenscope  
JSON: https://api.skillsregistry.net/v1/skills/wartzar-bee-tokenscope

## Description

Analyzes Claude Code session token usage and cost locally — where spend actually lands across cache-read, cache-write and output, and what is consuming the context window. Read-only and offline: it parses your own session files and exposes analyze_claude_cost, get_cost_benchmark and tokenscope_share_summary.

## Trust

- **Trust score (0–1):** 0.68
- **Verification tier:** scanned
- **Last scanned:** 2026-08-30

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** file-system
- **Updated:** 2026-08-30

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/vxkv2v70si)
- **Repository:** <https://github.com/wartzar-bee/tokenscope>

## 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": "wartzar-bee-tokenscope"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/wartzar-bee-tokenscope` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/wartzar-bee-tokenscope/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
