# loom

> loom — ddevilz-loom. Use this tool when you need to efficiently store and manage AI agent understanding, reducing token usage by 51-1500x. Loom solves the problem of repeated code re-reads by creating a persistent code graph, taking input from Tree-sitter and outputting to SQLite and MCP. Ideal for use in development workflows, such as those involving git, to optimize agent performance and knowledge retention.

Canonical page: https://skillsregistry.net/skills/ddevilz-loom  
JSON: https://api.skillsregistry.net/v1/skills/ddevilz-loom

## Description

Persistent code graph for AI agents. Tree-sitter → SQLite → MCP. Agents store understanding once, skip re-reads forever. 51–1500x fewer tokens.

## Trust

- **Trust score (0–1):** 0.42
- **Verification tier:** scanned
- **Last scanned:** 2026-09-01

## Facts

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

## Source

- **Source listing:** [GitHub](https://github.com/ddevilz/loom)

## 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": "ddevilz-loom"
    }
  }
}
```

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