# rule-drift

> rule-drift — ri7in-rule-drift. Use this tool when you need to detect and prevent deviations from predefined rules in AI agent behavior, solving issues of model drift and ensuring compliance. It monitors AI decision-making processes and alerts when rules are not being followed, taking in model outputs and rule definitions as inputs. Ideal for use cases where adherence to rules and regulations is crucial, such as in high-stakes or regulated environments.

Canonical page: https://skillsregistry.net/skills/ri7in-rule-drift  
JSON: https://api.skillsregistry.net/v1/skills/ri7in-rule-drift

## Description

Catch the moment your AI agent drifts from its rules.

## Trust

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

## Facts

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

## Source

- **Source listing:** [GitHub](https://github.com/ri7in/rule-drift)

## 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": "ri7in-rule-drift"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/ri7in-rule-drift` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/ri7in-rule-drift/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