# agent-proof-kit

> agent-proof-kit — guillaumevele-agent-proof-kit. Use this tool when you need to ensure the integrity and security of AI agent interactions, providing deterministic proof gates and raw-byte write firewalls to prevent unauthorized access. It solves problems related to data tampering and unauthorized modifications, offering a secure interface through CLI, MCP, and in-toto receipts. Ideal for use cases involving git version control, Codex CLI, and Mistral Vibe, where secure and trustworthy interactions are crucial.

Canonical page: https://skillsregistry.net/skills/guillaumevele-agent-proof-kit  
JSON: https://api.skillsregistry.net/v1/skills/guillaumevele-agent-proof-kit

## Description

Deterministic proof gates and a raw-byte write firewall for AI agents — CLI, MCP, in-toto receipts, Codex CLI and Mistral Vibe.

## Trust

- **Trust score (0–1):** 0.62
- **Verification tier:** scanned
- **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/guillaumevele/agent-proof-kit)

## 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": "guillaumevele-agent-proof-kit"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/guillaumevele-agent-proof-kit` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/guillaumevele-agent-proof-kit/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