# sonde

> sonde — anishmoncivarghese-sonde. Use this tool when you need to generate structural code answers within a limited token budget, helping AI coding agents understand local code context. It solves problems related to code completion, debugging, and optimization by providing relevant code snippets and suggestions. Ideal for use cases involving git-based code repositories, where agents require concise and context-specific code information.

Canonical page: https://skillsregistry.net/skills/anishmoncivarghese-sonde  
JSON: https://api.skillsregistry.net/v1/skills/anishmoncivarghese-sonde

## Description

Local code-context engine for AI coding agents: structural answers within a token budget.

## Trust

- **Trust score (0–1):** 0.86
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** Apache-2.0
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/anishmoncivarghese/sonde)

## 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": "anishmoncivarghese-sonde"
    }
  }
}
```

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