# scaffor

> scaffor — jlugagne-scaffor. Use this tool when you need to create structured and guided interactions for Large Language Model (LLM) agents, generating files and providing hints for next steps. It solves problems of agent uncertainty and disorganization by providing deterministic scaffolding, and is particularly useful for coding tasks with Claude Code and Cursor. The tool takes in templates and structured hints as inputs and outputs guided agent interactions, making it ideal for use cases requiring precise control over LLM agent behavior.

Canonical page: https://skillsregistry.net/skills/jlugagne-scaffor  
JSON: https://api.skillsregistry.net/v1/skills/jlugagne-scaffor

## Description

Deterministic scaffolding for LLM agents. Templates generate files, structured hints tell the agent what to do next. Built-in MCP server for Claude Code and Cursor.

## 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:** ai-ml
- **Updated:** 2026-09-21

## Source

- **Source listing:** [GitHub](https://github.com/JLugagne/scaffor)

## 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": "jlugagne-scaffor"
    }
  }
}
```

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