# locus

> locus — magnifico4625-locus. Use this tool when you need to retain project context and memory for AI coding tasks, solving problems of information loss and context switching across coding sessions. It integrates with AI coding tools like Codex and Claude Code, accepting project data as input and providing persistent memory as output. Ideal for use in collaborative coding projects managed through git.

Canonical page: https://skillsregistry.net/skills/magnifico4625-locus  
JSON: https://api.skillsregistry.net/v1/skills/magnifico4625-locus

## Description

Persistent project-aware memory for AI coding tools. Built on MCP. Works with Codex, Claude Code, and other MCP-compatible clients.

## Trust

- **Trust score (0–1):** 0.92
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** other
- **Updated:** 2026-09-20

## Source

- **Source listing:** [GitHub](https://github.com/Magnifico4625/locus)

## 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": "magnifico4625-locus"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/magnifico4625-locus` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/magnifico4625-locus/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