polyphony
Multi-agent orchestration with container-isolated workspaces — each agent session runs in its own Docker container with independent git branches
Skill by alinaqi
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/alinaqi-polyphony
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: devops, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/polyphony
What's inside
- Skill name
polyphony- Description
- Multi-agent orchestration with container-isolated workspaces — each agent session runs in its own Docker container with independent git branches
- License
- MIT
- Instructions
- 126 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- body: contains an absolute path from the author's machine
Files (1)
- SKILL.md
SKILL.md (first lines)
# 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:
```bash
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.
```yaml
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
```bash
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
```
---From alinaqi/maggy, MIT.
More from alinaqi/maggy
- 0.761score
model-routing
alinaqi
9-tier model routing system with cascading classifier fallback and result auto-evaluation
SkillAFreshness: A★ 711Claude Code +9 - 0.721score
dataforseo
alinaqi
Keyword & SERP research via the DataForSEO API — search volume, competition, CPC, keyword ideas for naming/SEO decisions
SkillBFreshness: B★ 711Claude Code +9 - 0.717score
visual-validation
alinaqi
Autonomous screenshot verification — captures, compares, and AI-evaluates UI changes for visual regressions
SkillBFreshness: B★ 711Claude Code +9 - 0.717score
build-in-public
alinaqi
Best practices for sharing engineering work publicly — what to post, what to withhold, and channel-specific guidance
SkillBFreshness: B★ 711Claude Code +9 - 0.717score
llm-patterns
alinaqi
AI-first application patterns, LLM testing, prompt management
SkillBFreshness: B★ 711Claude Code +9 - 0.717score
external-model-delegation
alinaqi
UserPromptSubmit hook pattern that classifies prompts into six cost tiers and delegates to external model CLIs
SkillBFreshness: B★ 711Claude Code +9 - 0.717score
autonomous-testing
alinaqi
AI-driven testing agent that auto-discovers, generates, executes, evaluates, and fixes tests for any project type
SkillBFreshness: B★ 711Claude Code +9 - 0.716score
security-audit
alinaqi
Structured, adversarial, multi-phase security audit of a codebase — recon → coverage-led hunting → finder≠validator validation → machine-readable findings →…
SkillBFreshness: B★ 711Claude Code +9 - 0.716score
verify-cascade
alinaqi
Verification-gated model escalation — run a cheap model, verify its output with decomposed per-field checks, and escalate to a strong model only when a flag…
SkillBFreshness: B★ 711Claude Code +9 - 0.713score
context-shunt
alinaqi
Offload large / multi-file reads to a cheap worker model so raw files never enter Claude's context (token savings)
SkillBFreshness: B★ 711Claude Code +9 - 0.708score
ms-teams-apps
alinaqi
Microsoft Teams bots and AI agents - Claude/OpenAI, Adaptive Cards, Graph API
SkillBFreshness: B★ 711Claude Code +9 - 0.708score
ai-models
alinaqi
Latest AI models reference - Claude, OpenAI, Gemini, Eleven Labs, Replicate
SkillBFreshness: B★ 711Claude Code +9
Signals
- Stars
- 711
- Forks
- 61
- Open issues
- 0
- Last commit (this folder)
- May 5, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/alinaqi/maggy
- Website
- www.srooter.ai/maggy
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from alinaqi
- 0.761score
model-routing
alinaqi
9-tier model routing system with cascading classifier fallback and result auto-evaluation
SkillAFreshness: A★ 711Claude Code +9 - 0.721score
dataforseo
alinaqi
Keyword & SERP research via the DataForSEO API — search volume, competition, CPC, keyword ideas for naming/SEO decisions
SkillBFreshness: B★ 711Claude Code +9 - 0.717score
external-model-delegation
alinaqi
UserPromptSubmit hook pattern that classifies prompts into six cost tiers and delegates to external model CLIs
SkillBFreshness: B★ 711Claude Code +9 - 0.717score
autonomous-testing
alinaqi
AI-driven testing agent that auto-discovers, generates, executes, evaluates, and fixes tests for any project type
SkillBFreshness: B★ 711Claude Code +9 - 0.717score
build-in-public
alinaqi
Best practices for sharing engineering work publicly — what to post, what to withhold, and channel-specific guidance
SkillBFreshness: B★ 711Claude Code +9 - 0.717score
llm-patterns
alinaqi
AI-first application patterns, LLM testing, prompt management
SkillBFreshness: B★ 711Claude Code +9
Cite this page
polyphony skill. Agent Mart. https://agentmart.dev/skills/alinaqi-polyphony (last updated 2026-10-24)