By groundnuty
Multi-Agent Coordination Framework — channel server, runtime skills, agent definitions, and hooks for coordinating Claude Code agents via mTLS and GitHub
Implements features, fixes bugs, writes tests, and maintains CI/CD. The primary engineering agent in a multi-agent MACF project.
Experimental code agent — same as code-agent but with no memory, no self-chaining, and no accumulated learning. For controlled experiments.
Experimental science agent (Condition B1) — has full code access. Files issues with exact file paths and function names.
Experimental science agent (Condition B2) — NO code access. Files issues with domain-level descriptions only.
Single-agent mode (Condition A) — handles both code and research autonomously. No coordination, no multi-agent overhead. Baseline for experiments.
Check pending GitHub issues assigned to this agent. Use this to find work that needs to be done.
List all registered agents with their health status. Use this to discover peers in the coordination network.
Ping a specific peer agent and show its detailed status
Show agent identity, channel endpoint, network peers, and coordination status. Use this when you need to check your own status or see which peers are online.
Admin access level
Server config contains admin-level keywords
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Claude Code plugin marketplace distributing the macf-agent plugin for the Multi-Agent Coordination Framework (MACF).
/plugin marketplace add groundnuty/macf-marketplace
/plugin install macf-agent@macf-marketplace
macf-agent — runtime component of MACF:
POST /notify, GET /health, and POST /sign/macf-status, /macf-peers, /macf-ping, /macf-issuesFloating major tags + immutable semver:
| Tag | Moves? | Recommended for |
|---|---|---|
v0 | Floats to latest v0.x.x | Pre-release testing |
v0.1 | Floats to latest v0.1.x | Patch-level stability |
v0.1.0 | Immutable | Maximum reproducibility |
Breaking changes = new major. Pre-1.0 (v0.x) is unstable — minor versions may break.
@macf/cli (installs from groundnuty/macf repo)npx claudepluginhub groundnuty/macf-marketplace --plugin macf-agentAgent configuration utilities - project assimilation, config auditing, teammate definitions, MCP management, and hooks configuration
Advanced multi-agent coordination platform with task orchestration, performance monitoring, and workflow optimization. Features hooks for agent lifecycle events and MCP server for state management.
AgenticFlow developer tools for Claude Code — build AI agents, deploy multi-agent workforces, and automate operations against the AgenticFlow platform via the `af` CLI.
Multi-agent coordination with agent-swarm MCP
Production ADK orchestrator for A2A protocol and multi-agent coordination on Vertex AI
Gives Claude Code a multi-agent coordination layer over MCP — an atomic shared blackboard (locked propose/validate/commit), permission gating with HMAC/Ed25519-signed tokens, federated token-budget tracking, and append-only audit-log queries. Backed by an orchestrator with 29 framework adapters (LangChain, AutoGen, CrewAI, and more).