# curion

> curion — geanatz-curion. Use this tool when you need to enhance AI coding agents with a project-local memory layer, solving issues of context retention and code completion. It integrates with MCP clients like Claude Code, Codex, and OpenCode, accepting git inputs and providing informed code suggestions as output. Ideal for use cases requiring localized code knowledge and accelerated development workflows.

Canonical page: https://skillsregistry.net/skills/geanatz-curion  
JSON: https://api.skillsregistry.net/v1/skills/geanatz-curion

## Description

Curion is a project-local memory layer for AI coding agents, published as an MCP server for Claude Code, Codex, OpenCode, and other MCP clients.

## Trust

- **Trust score (0–1):** 0.88
- **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/geanatz/curion)

## 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": "geanatz-curion"
    }
  }
}
```

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