# agent47

> agent47 — bmdhodl-agent47. Use this tool when you need to prevent AI agents from exceeding budget thresholds or entering infinite loops, as it provides runtime cost guardrails with features like budget enforcement, loop detection, and a kill switch, accepting AI agent runtime inputs and outputting controlled execution. It solves problems of unexpected costs and resource waste, and is ideal for use cases where AI agents are deployed in production environments with limited resources. Use AgentGuard in contexts where AI agent autonomy and cost control are crucial, such as in cloud-based or edge computing deployments.

Canonical page: https://skillsregistry.net/skills/bmdhodl-agent47  
JSON: https://api.skillsregistry.net/v1/skills/bmdhodl-agent47

## Description

Python runtime checks for AI agents: budgets, loops, retries, and local traces. Zero runtime dependencies. MIT.

## Trust

- **Trust score (0–1):** 0.93
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

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

## Source

- **Source listing:** [GitHub](https://github.com/bmdhodl/agent47)

## 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": "bmdhodl-agent47"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/bmdhodl-agent47` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/bmdhodl-agent47/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