# agent-brain

> agent-brain — sandeep84397-agent-brain. Use this tool when you need to retain decision-making knowledge for AI coding agents, enabling persistent memory and informed coding decisions. It solves problems of knowledge loss and repeated coding mistakes by storing and retrieving decision data through a MCP server interface. Ideal for use with Claude Code, Cursor, and Cline, it accepts git inputs and outputs informed coding guidance.

Canonical page: https://skillsregistry.net/skills/sandeep84397-agent-brain  
JSON: https://api.skillsregistry.net/v1/skills/sandeep84397-agent-brain

## Description

Persistent decision memory for AI coding agents. MCP server for Claude Code, Cursor, Cline.

## Trust

- **Trust score (0–1):** 0.54
- **Verification tier:** scanned
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** other
- **Updated:** 2026-09-21

## Source

- **Source listing:** [GitHub](https://github.com/sandeep84397/agent-brain)

## 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": "sandeep84397-agent-brain"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/sandeep84397-agent-brain` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/sandeep84397-agent-brain/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