# fable-flow

> fable-flow — jastfan-fable-flow. Use this tool when you need to decouple task contracts from worker subagents and verify invariants in multi-agent architectures, solving problems of adversarial failure and contract inconsistency. It takes in Claude code, cursor, and web inputs and outputs verified task contracts, with support for BYOK models like Claude 3.7 and GPT-4o. Ideal for use cases requiring robust and reliable multi-agent systems, such as git-based development workflows.

Canonical page: https://skillsregistry.net/skills/jastfan-fable-flow  
JSON: https://api.skillsregistry.net/v1/skills/jastfan-fable-flow

## Description

Fable 5.1 Multi-Agent Architect & Invariant Verification Gate for Claude Code, Cursor & Web. Decouples task contracts from worker subagents with adversarial failure injection testing. BYOK (Claude 3.7, GPT-4o, DeepSeek, Ollama).

## Trust

- **Trust score (0–1):** 0.84
- **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/jastfan/fable-flow)

## 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": "jastfan-fable-flow"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/jastfan-fable-flow` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/jastfan-fable-flow/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