# vs_claude_code

> vs_claude_code — firish-claude-code-vs. Use this tool when you need to integrate AI-powered code editing and debugging capabilities into Visual Studio 2026, allowing for seamless agent edits, live debugging, and testing. It solves problems related to code review, debugging, and testing by providing a unified interface for accepting or rejecting AI-generated code changes and utilizing advanced debugging features. The tool accepts code edits and debugging inputs, outputting results in Visual Studio's diff viewer and live debugger.

Canonical page: https://skillsregistry.net/skills/firish-claude-code-vs  
JSON: https://api.skillsregistry.net/v1/skills/firish-claude-code-vs

## Description

A native Visual Studio 2026 extension implementing Claude Code's IDE integration protocol: agent edits open in VS's diff viewer for accept/reject, and MCP servers expose the live debugger (stepping, data breakpoints, attach), Test Explorer runs, and Roslyn navigation with decompile to the agent.

## Trust

- **Trust score (0–1):** 0.60
- **Verification tier:** scanned
- **Last scanned:** 2026-09-03

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** api-integration
- **Updated:** 2026-09-03

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/bt0fnk4anv)
- **Repository:** <https://github.com/firish/claude_code_vs>

## 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": "firish-claude-code-vs"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/firish-claude-code-vs` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/firish-claude-code-vs/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