# forge

> forge — valtors-forge. Use this tool when you need to securely run and manage local-first agents with robust features like memory and sandboxing management, observation, and package management. It solves problems related to agent runtime, security, and dependency management, providing a single binary solution for streamlined agent deployment. Ideal for use cases requiring isolated and secure agent execution, with support for git integration for version control and collaboration.

Canonical page: https://skillsregistry.net/skills/valtors-forge  
JSON: https://api.skillsregistry.net/v1/skills/valtors-forge

## Description

local-first agent runtime. one binary. memory, sandboxing, observation, security, package management. agents run on top.

## Trust

- **Trust score (0–1):** 0.90
- **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/valtors/forge)

## 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": "valtors-forge"
    }
  }
}
```

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