# kestrel

> kestrel — wearzdk-kestrel. Use this tool when you need to track errors in AI agents efficiently, as it provides a lightweight and native solution with a single Go binary and SQLite database. It solves the problem of monitoring AI agent errors without relying on dashboards, making it ideal for MCP-native environments. With a small footprint of less than 20 MB, it's a suitable choice for applications where resources are limited.

Canonical page: https://skillsregistry.net/skills/wearzdk-kestrel  
JSON: https://api.skillsregistry.net/v1/skills/wearzdk-kestrel

## Description

Error tracking built for AI agents, not dashboards. Single Go binary, SQLite-only, MCP-native. < 20 MB.  为 AI agent 而生的错误监控。单 Go 二进制 + SQLite，内置 MCP，< 20 MB。 WIP

## Trust

- **Trust score (0–1):** 0.51
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

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

## Source

- **Source listing:** [GitHub](https://github.com/wearzdk/kestrel)

## 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": "wearzdk-kestrel"
    }
  }
}
```

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