# AgentEval (Julia)

> Use this tool when you need to evaluate and execute code persistently for AI agents, solving the "Time to First X" problem with secure and efficient STDIO transport. It provides a persistent Julia session with tools for code execution, session management, and package control, ideal for iterative development workflows. AgentEval is suitable for use cases requiring secure, auto-spawned, and network-port-free code evaluation with preserved variables and loaded packages across calls.

Canonical page: https://skillsregistry.net/skills/samtalki-agenteval  
JSON: https://api.skillsregistry.net/v1/skills/samtalki-agenteval

## Description

AgentEval.jl solves Julia's "Time to First X" (TTFX) problem for AI agents by providing persistent code evaluation through MCP STDIO transport. Unlike HTTP-based alternatives, it uses STDIO for security (no network ports), auto-spawns when needed, and maintains a persistent Julia session where variables, functions, and loaded packages survive across calls. The implementation provides tools for code execution, session reset, metadata access, and package management, making it ideal for iterative development workflows.

## Trust

- **Trust score (0–1):** 1.00
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-28

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/samtalki-agenteval)
- **Repository:** <https://github.com/samtalki/agentrepl.jl>

## 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": "samtalki-agenteval"
    }
  }
}
```

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