# shinobi

> Use this tool when you need to streamline AI coding tasks across multiple sessions, machines, and devices. Shinobi provides a shared brain for AI agents, enabling seamless task management, dead-end searching, and mobile approvals through a unified interface with local SQLite or remote streamable-HTTP connectivity. It solves problems of fragmented workflows and limited accessibility, making it ideal for collaborative AI coding projects.

Canonical page: https://skillsregistry.net/skills/numbererikson-shinobi  
JSON: https://api.skillsregistry.net/v1/skills/numbererikson-shinobi

## Description

Task spine + searched dead-ends + mobile approvals for AI coding agents — one shared brain across every session, machine, and device. Local SQLite or remote streamable-HTTP MCP, MIT.

## Trust

- **Trust score (0–1):** 0.66
- **Verification tier:** scanned
- **Last scanned:** 2026-08-31

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-08-31

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/a2zjsg3exz)
- **Repository:** <https://github.com/numbererikson/shinobi>

## 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": "numbererikson-shinobi"
    }
  }
}
```

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