Autonomous meta-agent orchestrator: 5 phases (research with 5 Haiku brainstormer archetypes, NotebookLM-RAG planning, codex-swarm execution, binary quality gate, synthesis with plateau self-critique). Hard dependency: multi-model-orchestrator.
0 on GitHubby dynamic-domev1.2.3updated 5 months ago
/
Plugin agent-orchestrator from marketplace dynamic-dome-marketplace in dynamic-dome/claude-plugins-marketplace. Commands read from the repo's manifest — 1 month ago.
What it installs
Skills (1)
agent-orchestrator
Autonomer Meta-Agent-Orchestrator der komplexe Aufgaben in ein strukturiertes Multi-Agent-System zerlegt und autonom durchfuehrt. Empfaengt ein High-Level-Ziel vom User und orchestriert dann eigenstaendig: Haiku-Brainstormer fuer Research, NotebookLM als RAG-Wissensbasis, und Codex-Instanzen fuer Au
Subagents (5)
brainstormer-critic
Haiku-based critical brainstormer. Used as one of the 5 research agents in Phase 1 of the agent-orchestrator. Systematically attacks the task framing: what can go wrong, what is being assumed, what has been tried and failed before, what is the strongest counter-argument. Produces a risk-and-failure-
brainstormer-facts
Haiku-based facts-and-data brainstormer. Used as one of the 5 research agents in Phase 1 of the agent-orchestrator. Collects hard data, statistics, existing solutions, benchmarks, and authoritative sources. Returns a compact findings report with citations where available.
brainstormer-lateral
Haiku-based lateral-thinking brainstormer. Used as one of the 5 research agents in Phase 1 of the agent-orchestrator. Generates unconventional approaches, cross-domain analogies, and what-if ideas that no other brainstormer would produce. Permission to be weird.
brainstormer-user
Haiku-based user-perspective brainstormer. Used as one of the 5 research agents in Phase 1 of the agent-orchestrator. Thinks from the target audience's angle: needs, pain points, usage contexts, accessibility, friction. Produces a persona- and journey-oriented findings report.
brainstormer-visionary
Haiku-based visionary brainstormer. Used as one of the 5 research agents in Phase 1 of the agent-orchestrator. Sketches the ideal end-state without constraints: what would this look like at its absolute best, unrestricted by budget, time, technology, or politics? Produces a north-star specification.
Suite of 7 skills, 7 slash commands, and 5 read-only checker hooks that turns rough ideas into agentic workflow blueprints, runs adversarial review-fix-verify loops, audits ecosystems as dynamic graphs, curates raw inbox material into wiki pages, runs MCP/DCO actions safely, and gates skill promotion.
Multi-model agent team orchestration via tmux + git worktrees. Routes tasks to the best model (Claude plans/reviews, Codex implements). Includes codex-swarm (up to 5 parallel Codex agents with decompose + review).
Adapter-agnostic 4-role loop (Orchestrator/Researcher/Builder/Judge) with persistent state files per project under .loop/<run-id>/. /loop-run command, adapter catalog, offline demo.
Divergence generator for creative ideation. Four voices (first-principles-jester, labyrinth-librarian, systems-alchemist, radagast-brown) produce provocations, never advice. Single-run, chat mode, and browser lab for triage.
Companion plugin to agentic-os. One-way mirror of allowlisted identity files from .agent-memory/identity/ to Claude Code's native memory store. No auto-mirror, no reverse-import.
This plugin provides a specialized suite of skills for data engineers and database practitioners working on Google Cloud. It acts as an expert assistant, allowing you to use natural language prompts in your preferred coding agent to architect complex data pipelines, transform data with dbt, write Spark and BigQuery SQL notebooks, and orchestrate end-to-end workflows across GCP's data ecosystem.
Web scraping, Google search, structured data extraction, and MCP server integration powered by Bright Data. Includes 7 skills: scrape any webpage as markdown (with bot detection/CAPTCHA bypass), search Google with structured JSON results, extract data from 40+ websites (Amazon, LinkedIn, Instagram, TikTok, YouTube, and more), orchestrate Bright Data's 60+ MCP tools, built-in best practices for Web Unlocker, SERP API, Web Scraper API, and Browser API, Python SDK best practices for the brightda...
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.