claude

agent-protocol

Role skills for the multi-agent collaboration protocol: agent-core (shared normative references), owner-engine-agent, helper-builder-agent, orchestrator-agent, plus /sleep, /wake and /converge lifecycle commands

4 on GitHubby AIpandadreamsv1.11.0MITupdated 1 month ago
/

Plugin agent-protocol from marketplace multi-agent-protocol in AIpandadreams/multi-agent-protocol. Commands read from the repo's manifest — 1 month ago.

What it installs

Skills (5)

  • agent-core

    Shared normative core of the multi-agent collaboration protocol (PROTOCOL v3.2) — the channel rules, reviewer architecture, verdict contract, binding-slot glossary, memory discipline, and self-improvement protocol that the role skills (owner-engine-agent, helper-builder-agent, orchestrator-agent) al

  • helper-builder-agent

    Operate as the HELPER/BUILDER AGENT — the supporting side that owns source reads, censuses, QA passes, and advisory deliverables — in a two-agent collaboration with a peer "owner/engine" agent that owns the canonical repo/decisions, an independent reviewer gating every job, and a human principal hol

  • orchestrator-agent

    Operate as the ORCHESTRATOR AGENT — the principal's single plain-speech interface and traffic/state manager over a multi-agent collaboration (owner agent + helper/builder agent + independent reviewer, with the human principal holding all authorization gates). Use this skill when the session IS (or i

  • overnight-mode

    The principal's fleet-wide overnight launch directive — put every queued, approved, unblocked unit in flight across all teams while he sleeps, honoring any priority he names, with gates unchanged and a morning report. Invoke when the principal says "overnight mode" (with or without extra priorities)

  • owner-engine-agent

    Operate as the OWNER/ENGINE AGENT — the side that owns the canonical repo and decision surface — in a two-agent collaboration with a peer helper/builder agent, an independent reviewer gating every commit, and a human principal holding all authorization gates. Use this skill when the session IS (or i

Slash commands (3)

  • /agent-protocol:converge

    Run a multi-round convergence review of a committed artifact SET to a reviewer-declared stop

  • /agent-protocol:sleep

    Checkpoint this agent session (memory + commit + handover) and declare it safe to close

  • /agent-protocol:wake

    Wake an agent role in this session: bind, verify, resume from its workspace state

View source on GitHub

Maintain agent-protocol?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex pluginslisted