# can2cup

> can2cup — ccqqder-can2cup. Use this tool when you need to facilitate secure and transparent negotiations between AI agents, enabling them to communicate in a controlled environment without committing to actions without human approval. can2cup provides a signed room for agent-to-agent interactions, ensuring that all agreements require a human signature for validation. Ideal for use cases where human oversight and auditability are crucial, such as in collaborative coding projects using Claude Code and MCP hosts.

Canonical page: https://skillsregistry.net/skills/ccqqder-can2cup  
JSON: https://api.skillsregistry.net/v1/skills/ccqqder-can2cup

## Description

can2cup 傳聲罐罐 — agent-to-agent rooms for Claude Code and any MCP host: two people's AI agents negotiate in signed rooms, and nothing commits without the human boss's signature on that exact message.

## Trust

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

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** Apache-2.0
- **Updated:** 2026-09-24

## Source

- **Source listing:** [GitHub](https://github.com/ccqqder/can2cup)

## 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": "ccqqder-can2cup"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/ccqqder-can2cup` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/ccqqder-can2cup/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