Design, execute and fanout runs as Claude Code workflows, with a mod that records every step, runs verify itself and lands only verified trees
Plugin litter from marketplace claude-litter 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.
amendRework one gate of a litter execute plan with a stated change, as a one-gate background run judged by the same independent critic and verified by the litter mod. Use it after a gate halted, or when one gate of the plan turned out to be wrong.
designRun a litter design in the background. Independent investigators, a reframer that challenges the goal, and a critic with the only veto iterate on a hard problem against a written bar agreed first. An approved plan comes back for review in plan mode.
executeImplement an approved plan, or reach a goal checked by a test command, gate by gate in a background litter run. An independent critic must pass each gate, and the litter mod commits a gate only after its own run of the verify command passes.
fanoutRun independent tasks in parallel in a background litter run, each task that changes files in its own git worktree. The litter mod merges the results and runs the verify command on the combination, and a verifier checks each task before anything lands.
rulesList, add, show, retire or import litter rules, the user's standing rules and bans that litter agents receive wherever they apply.
swarmDraft, start, lead and end a litter swarm, a tree of agents led from this session, where orchestrators each own part of the work and delegate to their own workers. Drafts the swarm's shape into the litter swarm builder, starts it after the user launches it there, and keeps the lead role while it run
wikiRebuild .claude/litter/WIKI.md, the project's index of litter runs and swarms and the decisions they produced, from every run folder on disk, then give a short recap or answer a question about past runs.
sh
sh
sh
sh
sh
sh
sh
sh
sh
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
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.
7 skills · hooks
Multi-agent swarm management for Claude Code
1 skill · 4 commands · 1 MCP server
Tenant-isolated AI teams that plan work, coordinate tasks, recall approved context, and return evidence-backed results
6 skills · 6 commands · 4 agents · 1 MCP server
Write accurate Pydantic AI code from the start. Up-to-date patterns, decision trees, and common gotchas for agents, tools, structured output, streaming, and multi-agent apps.
Orchestrate multi-agent teams for parallel code review, hypothesis-driven debugging, and coordinated feature development using Claude Code's Agent Teams
6 skills · 7 commands · 4 agents
Claude Code native multi-agent orchestration with intelligent model routing across agents and skills. Zero learning curve. Maximum power.
85 skills · 20 commands · 19 agents · 1 MCP server · hooks
Multi-agent collaboration — spawn N parallel subagents that compete on code optimization, content drafts, research approaches, or any task that benefits from diverse solutions. 7 slash commands (/hub-init, /agenthub:spawn, /hub-status, /agenthub:eval, /agenthub:merge, /agenthub:board, /hub-run), agent templates, DAG-based orchestration, LLM judge mode, message board coordination.
8 skills · 1 agent · hooks
Agent coordination and meta-programming - multi-agent orchestration, workflow automation, and safe refactor governance. Works best with other voltagent plugins installed.
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.