# flowproof

> flowproof — automators-com-flowproof. Use this tool when you need to ensure the reliability and consistency of business processes run by AI agents, by testing and validating their execution through automated replay and assertion of tool calls and arguments. It solves problems of process drift and unexpected behavior by providing a zero-LLM call testing solution. It takes a recorded run as input and outputs validation results, integrating with git for automated testing on every commit.

Canonical page: https://skillsregistry.net/skills/automators-com-flowproof  
JSON: https://api.skillsregistry.net/v1/skills/automators-com-flowproof

## Description

Agents are starting to run real business processes. flowproof tests them like anything else: record one real run, then replay it on every commit with zero LLM calls, asserting which tools were called, with which arguments, in which order, and which were not.

## Trust

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

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Updated:** 2026-09-25

## Source

- **Source listing:** [GitHub](https://github.com/automators-com/flowproof)

## 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": "automators-com-flowproof"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/automators-com-flowproof` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/automators-com-flowproof/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