# agent-sidecar

> agent-sidecar — smarchetti-agent-sidecar. Use this tool when you need to create interactive and visual interfaces for coding agents, allowing users to interact with HTML elements in their browser and send feedback back into the conversation. It solves problems of limited user interaction and feedback in agent-based systems, enabling more intuitive and engaging experiences. Ideal for use cases requiring dynamic and responsive user interfaces, with inputs including user clicks and outputs including updated conversation flows.

Canonical page: https://skillsregistry.net/skills/smarchetti-agent-sidecar  
JSON: https://api.skillsregistry.net/v1/skills/smarchetti-agent-sidecar

## Description

A visual canvas for coding agents — your agent shows interactive HTML in your browser, your clicks flow back into the conversation

## Trust

- **Trust score (0–1):** 0.87
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

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

## Source

- **Source listing:** [GitHub](https://github.com/smarchetti/agent-sidecar)

## 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": "smarchetti-agent-sidecar"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/smarchetti-agent-sidecar` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/smarchetti-agent-sidecar/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