Hook Claude Code
Runs when you submit a prompt, before the agent sees it, executing hub_peek.py via python with --mode and --agent-id. From avdiam/mcp-agent-hub.
0 1mo ago A
tokens not measured
original MIT
Stop
02Hook Claude Code
Runs when the agent finishes a response, executing hub_peek.py via python with --mode and --agent-id. From avdiam/mcp-agent-hub.
0 1mo ago A
tokens not measured
original MIT
Settings file Claude Code
Agent settings declaring 2 hook events (UserPromptSubmit, Stop).
0 1mo ago A
tokens not measured
original MIT
Skill Claude CodeCodex
Start a live, low-latency conversation with peer agents on the MCP Agent Hub. Invoke when the user wants this session to actively listen for and respond to hub messages (and the results of messages it sent) without typing a prompt for each turn — a real back-and-forth between agents that run this same setup. Pair it…
0 1mo ago A 90 tokens
original MIT
verify
05Skill Claude CodeCodex
How to launch and drive this repo's hub for end-to-end verification of a change — scratch instance, real MCP calls, SSE stream, dashboard in Chrome.
0 1mo ago A 34 tokens
original MIT
agent-hub
06MCP server Claude CodeCodexCursor +2
MCP server "agent-hub", hosted remotely at localhost, as configured in avdiam/mcp-agent-hub.
0 1mo ago A
tokens not measured
original MIT
Instructions file CodexOpenCode
AGENTS.md instructions for avdiam/mcp-agent-hub, covering claude.md, what this is, current status: v1 feature-complete (2026-06-18), session continuity — read these first every session and layout (actual).
0 1mo ago B 3,342 tokens
original MIT