← Back to list
Agent Protocol Spec
Machine-readable role files enabling multi-agent coordination and tool interoperability.
7.9Overall rating
0Views
0Downloads
35Stars
Installation
🤖 Install via AI
Copy the prompt below and send it to your AI assistant (e.g. Claude Code) — it will follow the instructions and install automatically.
Install the "Agent Protocol Spec" skill by following the instructions at https://skill123.me/install/agent-protocol.
⌨️ Command line install
Run in your terminal — downloads and installs to ~/.claude/skills/.
curl -fsSL https://skill123.me/install/agent-protocol.sh | bash
📦 Download ZIP
Download the zip and extract it into your skills directory (e.g. ~/.claude/skills/), then restart your session.
⬇ Download v3.7.1 · 3 KB🛡 Dynamic test
—
Not live-tested yet — this skill is rated on static analysis only.
About this skill
The interop layer: makes MUSE role files readable by other agents. Most useful when running multiple agents on one codebase.
Documentation
The interop layer: makes MUSE role files readable by other agents. Most useful when running multiple agents on one codebase.
Score breakdown
Trigger
7.0
Narrow trigger: invoked when making role files machine-readable.
Structure
8.5
Why → Role File Spec v1.0 → Integration Points → Version History — proper spec document.
Workflow
7.5
Integration points show exactly how other agents consume the protocol.
Content
8.5
Full spec with examples, inspired by MemOS multi-agent memory.
Engineering
8.0
The spec itself is the artifact; includes bloat-check tooling hooks.
Security
8.0
Multi-agent isolation boundaries specified explicitly (MemOS-inspired).
The interop layer: makes MUSE role files readable by other agents. Most useful when running multiple agents on one codebase.
Assessment methodology
Assessment in progress
This skill has not been assessed yet — use with caution.
Version history
v3.7.1
2026-09-26
— Imported from GitHub myths-labs/muse