By Cheong43
Repo-level Claude Code plugin for structured planning plus registry-guided agent, task, team, and pipeline orchestration.
Handle a small bounded Spwnr task.
Create an approved Spwnr plan before execution.
Shared Spwnr planning and orchestration rules.
Execute an approved Spwnr plan.
Audit Spwnr worker readiness.
Matches all tools
Hooks run on every tool call, not just specific ones
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Spwnr is an open-source toolkit for packaging, injecting, and orchestrating multi-agent workers across coding hosts. Currently supporting Claude Code.
# Claude Code plugin install
/plugin marketplace add Cheong43/spwnr
/plugin install spwnr@spwnr
/reload-plugins
# spwnr cli install
npm i @spwnr/cli
# Edit Claude Code config on .Claude/setting.json
"env": {
"CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": 1
}
# Or Edit the env
export CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1
then activate the following skill commands in your agent
/using-spwnr # Main router: /spwnr-plan -> /spwnr-task -> implement
/spwnr-do # Directly handle a bounded small task with optional 1-3 workers
/spwnr-plan # Write plan
/spwnr-task # Route and execute the approved plan in pipeline/team mode
/spwnr-worker-audit # Check subagent template availability and recovery steps
A usage walkthrough lives in docs/guide/getting-started.md.
Spwnr now treats vendor/spwnr-registry as the community template registry source. The nested repository is the canonical place for:
templates/<name>/<version>/registry-index.jsonThis repository keeps a lightweight portal that mirrors the submodule snapshot and links users to the official registry site.
Initialize the nested repository after cloning:
git submodule update --init --recursive
validate, publish, install, list, info, inject, and sessionDeprecated internal runtime packages still exist in the repo for future experiments, but they are not part of the current product surface.
apps/
spwnr-cli/ CLI entry point and command handlers
packages/
adapters/ host adapters for Claude Code, Codex, Copilot, OpenCode
broker/ deprecated internal runtime seed
core-types/ shared manifest, host, and error types
injector/ static injection and session composition
manifest-schema/ manifest parsing and package validation
memory/ deprecated internal runtime seed
policy/ dormant policy extension interfaces
registry/ local registry, tarballs, package metadata
examples/
code-reviewer/ example agent package
general-*/ workflow worker subagent examples
docs/
guide/ usage walkthroughs
archive/ archived design notes
pnpm install
pnpm build
pnpm test
Run pnpm test after changes to verify the workspace and repo-level workflow smoke tests.
If you plan to use the repo-root Claude Code workflow plugin with multi-agent team mode, enable Claude Code agent teams before installation or use:
export CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1
Without this setting, /spwnr-task can still run pipeline, but it must report team as unavailable.
This repository now also carries a repo-root Claude Code plugin for dogfooding a plan-first Claude-native orchestration workflow:
.claude-plugin/plugin.jsonhooks/skills/npx claudepluginhub cheong43/spwnr --plugin spwnrThis skill should be used when the model's ROLE_TYPE is orchestrator and needs to delegate tasks to specialist sub-agents. Provides scientific delegation framework ensuring world-building context (WHERE, WHAT, WHY) while preserving agent autonomy in implementation decisions (HOW). Use when planning task delegation, structuring sub-agent prompts, or coordinating multi-agent workflows.
Intelligently compose and deploy Claude Code Agent Teams. Auto-selects optimal team composition from 24+ agents and 83+ skills across 5 scopes, generates task dependency graphs, and orchestrates multi-agent workflows with a single command.
Delegation system with workflow orchestration, specialized agents, and parallel execution for Claude Code
Multi-agent orchestrator for Claude Code. Use when user mentions gastown, gas town, gt commands, convoys, polecats, rigs, slinging work, multi-agent coordination.
Use Superset to spawn agents, create workspaces, manage tasks, and schedule automations from Claude Code.
High-intelligence Claude Code copilot with deep code reasoning, evidence-driven planning, orchestration-first execution, model routing, context budgeting, CI/CD integration, enterprise security, plugin development, prompt engineering, performance profiling, agent teams, channels (event-driven autonomy with CI webhook, mobile approval relay, Discord bridge, and fakechat dev profile), interactive tutorials, LSP integration, security-hardened hook script library, MCP Prompts coverage, common workflow packs, runtime selection guide, computer-use patterns, checkpointing, scheduled-task blueprints, repo bootstrap scanner, hook policy engine (8 installable packs), layered memory deployment, role-based subagent packs (implementer, debugger, migration-lead, dependency-auditor, release-coordinator), 5 agent-team topology kits, autonomy operating mode (4 profiles + 3 gates), and a queryable 15-tool MCP documentation server with autonomy advisor.