
Polyphony
- 3 installs
- 706 repo stars
- Updated July 14, 2026
- alinaqi/maggy
polyphony is a Claude Code skill for multi-agent orchestration that runs each agent session in its own Docker container on an independent git branch.
About
polyphony is a multi-agent orchestration skill that runs each agent session in its own Docker container with an independent git branch. It defines a supervisor loop that discovers tasks from GitHub Issues or a local queue, routes them by a five-dimension complexity score, provisions containers, runs the chosen agent, and lands PRs. A developer uses it to run parallel agents (Claude, Codex, or Kimi) without conflicts. It is the default for the /spawn-team command when Docker or OrbStack is available.
- Multi-agent orchestration with a Docker container and git branch per agent task
- A supervisor loop (discover, claim, route, provision, run, verify, land) with a task lifecycle state machine
- Router scores task complexity across 5 dimensions to pick Kimi, Codex, or Claude
Polyphony by the numbers
- 3 all-time installs (skills.sh)
- Ranked #13,657 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Data as of Aug 5, 2026 (Skillselion catalog sync)
polyphony capabilities & compatibility
Uses agent CLI subscriptions (not API keys); needs local Docker or OrbStack.
- Capabilities
- orchestration · agent routing · container isolation · task scheduling
- Works with
- docker · github
- Use cases
- orchestration
- Runs
- Runs locally
- Pricing
- Free
What polyphony says it does
Container-isolated workspaces for parallel agent execution. Each agent gets its own Docker container with a full git clone on its own branch.
**Orchestrator** — Supervisor loop: discover -> claim -> route -> provision -> run -> verify -> land
**0-3**: Delegate to Kimi solo
npx skills add https://github.com/alinaqi/maggy --skill polyphonyAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 3 |
|---|---|
| repo stars | ★ 706 |
| Last updated | July 14, 2026 |
| Repository | alinaqi/maggy ↗ |
What it does
Orchestrate parallel coding agents, each in its own Docker container and git branch, routing tasks to Claude, Codex, or Kimi by a complexity score.
Who is it for?
Running several coding agents in parallel on separate tasks with container isolation.
Skip if: Environments without Docker or OrbStack, or single-agent workflows.
When should I use this skill?
Always loaded when container isolation is available (Docker/OrbStack installed). Default for /spawn-team.
What you get
Each task runs in an isolated container with its own git clone and branch, so agents run in parallel without conflicts and produce clean PRs.
- ~/.polyphony/ config (config, identities, agents, routing)
- Per-task containers, branches, and routed runs
By the numbers
- 6-layer architecture
- 5-dimension complexity scoring (0-10)
- Routing thresholds: 0-3 Kimi, 4-6 Kimi+Codex, 7-10 Claude
Files
Polyphony — Multi-Agent Orchestration
Container-isolated workspaces for parallel agent execution. Each agent gets its own Docker container with a full git clone on its own branch. No conflicts, independent tests, clean PRs.
---
Architecture (6 Layers)
1. Work Source — Tasks from GitHub Issues (gh api) or local SQLite queue 2. Orchestrator — Supervisor loop: discover -> claim -> route -> provision -> run -> verify -> land 3. Router — Pure function: Task x Policy -> RunSpec (5-dimension complexity scoring) 4. Identity Broker — Resolves named credentials to volume mounts + env overlays 5. Workspace Manager — Per-task git clone --reference, branch checkout, cleanup 6. Worker Runtime — Docker container create/start/stop/logs lifecycle
---
Task Lifecycle
DISCOVERED -> CLAIMED -> ROUTED -> PROVISIONED -> RUNNING -> VERIFYING -> LANDED
| |
v v
FAILED --> BLOCKED
|
v
CLAIMED (retry)---
Prerequisites
- Docker or OrbStack installed and running
- At least one agent CLI available (Claude, Codex, or Kimi)
- CLI subscriptions configured (not API keys)
Check:
command -v docker &>/dev/null || command -v orbctl &>/dev/null---
Configuration
All config lives in ~/.polyphony/:
| File | Purpose |
|---|---|
config.yaml | Workspace root, poll interval, max concurrency |
identities.yaml | Named credential bundles with volume paths |
agents.yaml | Agent profiles (CLI commands, strengths) |
routing.yaml | Routing rules and fallback chains |
Initialize with: polyphony init
---
Routing Rules
Rules are evaluated top-down; first match wins. Each rule has a match predicate and an agent target.
rules:
- match: { task_type: docs, risk: low }
agent: kimi
- match: { task_type: bugfix }
agent: codex
- match: { risk: high }
agent: claude
default:
agent: claude
fallback: [codex, kimi]---
Complexity Scoring (5 Dimensions)
Each dimension scores 0-2. Total 0-10.
| Dimension | Source |
|---|---|
| Cyclomatic depth | LOC + scope size |
| Fan-out | Number of callers |
| Security boundary | Auth/PII keywords |
| Concurrency | Lock/transaction keywords |
| Domain invariants | Risk level + task type |
Routing thresholds:
- 0-3: Delegate to Kimi solo
- 4-6: Kimi + Codex review
- 7-10: Claude direct
---
Container Isolation
Each task gets:
- Its own Docker container from
polyphony-worker:latest - A full git clone at
/workspace(not a worktree) - Auth volumes mounted read-only (e.g.,
~/.claude:/home/worker/.claude:ro) - Independent test execution
- Its own branch for PRs
---
CLI Commands
polyphony init # Create ~/.polyphony/ with config templates
polyphony spawn "Fix auth bug" # Create and route a task
polyphony status # Show task states
polyphony cleanup # Remove completed workspaces---
Integration with Existing Skills
- cross-agent-delegation: Uses Polyphony's complexity scoring for routing decisions
- agent-teams: Uses Polyphony's workspace isolation instead of shared directories
- spawn-team: Uses Polyphony's container provisioning for feature agents
Related skills
FAQ
What isolation does each agent get?
Its own Docker container from polyphony-worker:latest, a full git clone at /workspace on its own branch, read-only auth volume mounts, and independent test execution.
How are tasks routed?
A pure router scores each task 0-10 across 5 dimensions; 0-3 goes to Kimi solo, 4-6 to Kimi plus Codex review, and 7-10 to Claude directly.