# guardrail-agent

> guardrail-agent — atamkeze-guardrail-agent. Use this tool when you need to enforce coding standards and prevent AI agents from introducing errors into your codebase. The guardrail-agent acts as a deterministic CI/CD gate, blocking harmful changes and ensuring compliance with architecture and linter rules. It integrates with git to provide a native MCP server, safeguarding your code against slopsquatting and other malicious activities.

Canonical page: https://skillsregistry.net/skills/atamkeze-guardrail-agent  
JSON: https://api.skillsregistry.net/v1/skills/atamkeze-guardrail-agent

## Description

Deterministic CI/CD gate and native MCP server to block AI coding agents from slopsquatting, breaking architecture, and bypassing linters.

## Trust

- **Trust score (0–1):** 0.88
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## 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/atamkeze/guardrail-agent)

## 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": "atamkeze-guardrail-agent"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/atamkeze-guardrail-agent` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/atamkeze-guardrail-agent/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