# contextburn

> contextburn — ai-arsentev-contextburn. Use this tool when you need to optimize coding agent performance by measuring the efficiency of paid tokens used for output generation. Contextburn solves the problem of wasted resources on redundant context re-reading, providing a share of tokens that contribute to actual output. It takes coding agent input and outputs an efficiency metric, helping you identify areas for improvement in coding workflows.

Canonical page: https://skillsregistry.net/skills/ai-arsentev-contextburn  
JSON: https://api.skillsregistry.net/v1/skills/ai-arsentev-contextburn

## Description

Run efficiency for coding agents: share of paid tokens that became output, not context re-reading.

## Trust

- **Trust score (0–1):** 0.92
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 0.2.1
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Updated:** 2026-09-19

## Source

- **Source listing:** [MCP Registry](https://registry.modelcontextprotocol.io/v0/servers/ai.arsentev%2Fcontextburn)
- **Repository:** <https://github.com/arsentev-ai/contextburn>

## 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": "ai-arsentev-contextburn"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/ai-arsentev-contextburn` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/ai-arsentev-contextburn/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