Orchestrated multi-agent loops with profile-based modes. Default: persistent Teams for complex implementation. Leanswarm: lean 4-concern variant of default for capable models. Deepplan: multi-agent planning with explore/synthesize/critique/deliver. Async: background agent orchestration for independent parallel tasks. Decomposes complex tasks into parallel subtasks, spawns agent teams, tracks progress via native TaskCreate/TaskList, and dynamically re-plans each iteration until verified completion.
Not in a marketplace yet, so it loads for one session with --plugin-dir.
Plugin swarm-loop in Und3rf10w/claude-litter. Commands read from the repo's manifest — 4 days ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
async-swarmAsync background-agent swarm loop (alias for /swarm-loop --mode async)
cancel-swarmCancel the active swarm loop
deepplanDeep multi-agent planning session (alias for /swarm-loop --mode deepplan)
swarm-helpExplain Swarm Loop plugin and available commands
swarm-loopStart an orchestrated multi-agent swarm loop
swarm-settingsConfigure swarm loop safety, teammates, and notification settings
swarm-statusView swarm loop progress and status
bash "${CLAUDE_PLUGIN_ROOT}/hooks/stop-hook.sh"
bash "${CLAUDE_PLUGIN_ROOT}/hooks/teammate-idle-gate.sh"
bash "${CLAUDE_PLUGIN_ROOT}/hooks/pre-compact.sh"
Two-mode deep-work tool: DESIGN mode produces an approved plan via a 5-archetype oppositional team (Falsifier/Coverage/Mechanism/Reframer/Critic); EXECUTE mode implements that plan gate-by-gate with hook-enforced citation, test-evidence, and reversibility gates.
11 skills · hooks
Design, execute and fanout runs as Claude Code workflows, with a mod that records every step, runs verify itself and lands only verified trees
7 skills · hooks
Multi-agent swarm management for Claude Code
1 skill · 4 commands · 1 MCP server
Interactive self-referential AI loops for iterative development. Claude works on the same task repeatedly, seeing its previous work, until completion.
3 commands · hooks
Neural trading strategies — self-learning LSTM/Transformer/N-BEATS models with Rust/NAPI backtesting
9 skills · 1 command · 4 agents
Interactive self-referential AI loops for iterative development, implementing the Ralph Wiggum technique. Claude works on the same task repeatedly, seeing its previous work, until completion.
3 commands · hooks
Turn any domain folder of skills into a bounded agentic loop: a manifest builder inventories a domain's skills/tools/checks, a goal compiler turns a goal into a verifiable task plan (refusing vague goals with forcing questions), and a JSON-backed loop controller drives execute->verify->close with retry caps, controller-run verification (no verification theater), human escalation on exhausted budgets, and a close gate that refuses while any task is unverified or unwaived. Ships 3 stdlib Python tools, 18 committed per-domain harness manifests + JSON schema, 3 references citing the 2024-2026 agent-harness canon (Anthropic long-running harnesses, verifier's law, SWE-agent, Ralph loop, Cognition), harness-runner agent + /cs-harness command. Use when an agent or subagent should pick up a goal, define its tasks, complete and verify them, and close the loop.
1 skill · 1 command · 1 agent
PRD generation and conversion skills for the Ralph autonomous agent loop
2 skills
Reusable agent skills maintained by YYLO. The canonical, independently versioned source for skills used by YYLO CLI and YYLO Ledger: ledger task management, wiki, workflow and artifact records, project understanding, planning, and the Ralph execution loop.
8 skills
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.