# agentburn

> Use this tool when you need to optimize AI agent performance and reduce costs. Agentburn enables self-auditing of token usage, providing burn reports, forensics, and optimization recommendations through the MCP interface. It solves token management problems, offering actionable insights to improve efficiency and reduce expenses.

Canonical page: https://skillsregistry.net/skills/socialpranker-agentburn  
JSON: https://api.skillsregistry.net/v1/skills/socialpranker-agentburn

## Description

Enables AI agents to self-audit their token usage and costs, providing burn reports, forensics, and optimization recommendations via MCP.

## Trust

- **Trust score (0–1):** 0.58
- **Verification tier:** scanned
- **Last scanned:** 2026-09-19

## Facts

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

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/q0w3ukva3c)
- **Repository:** <https://github.com/Socialpranker/agentburn>

## 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": "socialpranker-agentburn"
    }
  }
}
```

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