Iterative self-improvement loop in 7 phases: orchestration, research (NotebookLM RAG), analysis (agentic-os patterns), TDD improvement, validation, circuit breaker, meta-improve.
Plugin self-improve-loop from marketplace dynamic-dome-marketplace in dynamic-dome/claude-plugins-marketplace. Commands read from the repo's manifest — 1 month ago.
No skills, commands, agents, hooks or MCP servers were found in the standard plugin folders.
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.
7 skills · 7 commands · hooks
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).
4 skills · 2 commands · 4 agents
Adversarial agent swarms with Devil's Advocate debate pattern: parallel scanners, two advocates debate findings, fixer acts only after consensus. Cross-provider script mode (Codex scanners + Sonnet advocates + Opus synthesis).
2 skills · 1 command · 4 agents
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.
1 skill · 5 agents
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.
2 skills · 1 command
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.
1 skill · 1 command
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Harness-native ECC operator layer - 71 agents, 314 skills, 98 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
200 skills · 98 commands · 71 agents · 1 MCP server · hooks
Interactive self-referential AI loops for iterative development. Claude works on the same task repeatedly, seeing its previous work, until completion.
3 commands · hooks
Production-grade engineering skills covering every phase of software development: spec, plan, build, verify, review, and ship.
25 skills · 4 agents
Agentic QE (external: maintained in proffesor-for-testing/agentic-qe, pinned to v3.15.17): a quality-engineering fleet with 11 QE agents, 9 skills, 9 commands, the agentic-qe MCP server pinned to the plugin version, and the aqe-mod guard that refuses destructive operations on AQE learning data
9 skills · 9 commands · 11 agents · 1 MCP server
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.