# csc-agent-guard-v1

> csc-agent-guard-v1 — fish121380-csc-agent-guard-v1. Use this tool when you need to ensure safe and compliant execution of AI agent actions, verifying tool calls against trusted evidence, policies, and WorldState to prevent unintended side effects. It provides a deterministic pre-execution safety gate, taking in proposed actions and WorldState as inputs and outputting verified or blocked actions. Ideal for use cases requiring strict adherence to policies and evidence-based decision-making.

Canonical page: https://skillsregistry.net/skills/fish121380-csc-agent-guard-v1  
JSON: https://api.skillsregistry.net/v1/skills/fish121380-csc-agent-guard-v1

## Description

Deterministic pre-execution safety gate for AI agents: verify tool calls against trusted evidence, policies, and WorldState before side effects.

## Trust

- **Trust score (0–1):** 0.86
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

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

## Source

- **Source listing:** [GitHub](https://github.com/Fish121380/csc-agent-guard-v1)

## 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": "fish121380-csc-agent-guard-v1"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/fish121380-csc-agent-guard-v1` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/fish121380-csc-agent-guard-v1/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