# selvedge

> selvedge — masondelan-selvedge. Use this tool when you need to understand the reasoning behind AI-coded changes in your codebase. Selvedge provides a long-term memory for AI agents, capturing their decision-making process in context, and allowing you to track the "why" behind each change. It integrates with git, offering a blame-like functionality for AI-driven code modifications.

Canonical page: https://skillsregistry.net/skills/masondelan-selvedge  
JSON: https://api.skillsregistry.net/v1/skills/masondelan-selvedge

## Description

Decision provenance for AI-coded codebases: the why, and what was already tried and rejected.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** database
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/masondelan/selvedge)

## 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": "masondelan-selvedge"
    }
  }
}
```

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