Multi-agent orchestration with container-isolated workspaces — each agent session runs in its own Docker container with independent git branches
54
68%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./skills/polyphony/SKILL.mdContainer-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.
gh api) or local SQLite queuegit clone --reference, branch checkout, cleanupDISCOVERED -> CLAIMED -> ROUTED -> PROVISIONED -> RUNNING -> VERIFYING -> LANDED
| |
v v
FAILED --> BLOCKED
|
v
CLAIMED (retry)Check:
command -v docker &>/dev/null || command -v orbctl &>/dev/nullAll 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
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]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:
Each task gets:
polyphony-worker:latest/workspace (not a worktree)~/.claude:/home/worker/.claude:ro)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 workspacesalinaqi/maggy
55aabe2
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.