Back to list
ReinaMacCredy

orchestrator

by ReinaMacCredy

Agent Skills (compatible with Claude Code, Codex, and more—for details visit: https://agentskills.io/home) with Conductor planning, Beads tracking, and TDD for AI-assisted development

23🍴 3📅 Jan 17, 2026

SKILL.md


name: orchestrator description: Multi-agent parallel execution with autonomous workers. Use when plan.md has Track Assignments section or user triggers /conductor-orchestrate, "run parallel", "spawn workers". MUST load maestro-core skill first for routing.

Orchestrator - Multi-Agent Parallel Execution

Spawn autonomous workers to execute tracks in parallel using Agent Mail coordination.

Agent Mail: CLI Primary, MCP Fallback

This skill uses a lazy-load pattern for Agent Mail:

PriorityToolWhen Available
Primarybun toolboxes/agent-mail/agent-mail.jsAlways (via Bash)
FallbackMCP tools (via mcp.json)When skill loaded + MCP server running

Detection flow:

1. Try CLI: bun toolboxes/agent-mail/agent-mail.js health-check
   ↓ success? → Use CLI for all Agent Mail operations
   ↓ fails?
2. Fallback: MCP tools (lazy-loaded via skills/orchestrator/mcp.json)

CLI benefits: Zero token cost until used, no MCP server dependency.

Core Principles

  • Load core first - Load maestro-core for routing table and fallback policies
  • CLI first - Use bun toolboxes/agent-mail/agent-mail.js CLI before falling back to MCP tools
  • Pre-register workers before spawning (Agent Mail validates recipients)
  • Workers own their beads - can bd claim/close directly (unlike sequential mode)
  • File reservations prevent conflicts - reserve before edit, release on complete
  • Summary before exit - all workers MUST send completion message
  • TDD by default - workers follow RED → GREEN → REFACTOR cycle (use --no-tdd to disable)

When to Use

TriggerCondition
Auto-routed/conductor-implement when plan has Track Assignments
File-scope/conductor-implement when ≥2 non-overlapping file groups detected
Direct/conductor-orchestrate or co
Phrase"run parallel", "spawn workers", "dispatch agents"
See alsoca for autonomous execution

Auto-Trigger Behavior

Parallel execution starts automatically when detected - no confirmation needed:

📊 Parallel execution detected:
- Track A: 2 tasks (src/api/)
- Track B: 2 tasks (lib/)
- Track C: 1 task (schemas/)

⚡ Spawning workers...

Quick Reference

ActionTool
Parse plan.mdRead("conductor/tracks/<id>/plan.md")
Initializebun toolboxes/agent-mail/agent-mail.js macro-start-session
Spawn workersTask() for each track
Monitorbun toolboxes/agent-mail/agent-mail.js fetch-inbox
Resolve blockersbun toolboxes/agent-mail/agent-mail.js reply-message
Completebun toolboxes/agent-mail/agent-mail.js send-message, bd close epic
Track threadsbun toolboxes/agent-mail/agent-mail.js summarize-thread
Auto-routingAuto-detect parallel via metadata.json.beads

8-Phase Orchestrator Protocol

  1. Preflight - Session identity, detect active sessions
  2. Read Plan - Parse Track Assignments from plan.md
  3. Validate - Health check Agent Mail CLI (HALT if unavailable)
  4. Initialize - ensure_project, register orchestrator + all workers
  5. Spawn Workers - Task() for each track (parallel)
  6. Monitor + Verify - fetch_inbox, verify worker summaries
    • Workers use track threads (TRACK_THREAD) for bead-to-bead context
  7. Resolve - reply_message for blockers
  8. Complete - Send summary, close epic, rb review

See references/workflow.md for full protocol.

Worker 4-Step Protocol

All workers MUST follow this exact sequence:

┌──────────────────────────────────────────────────────────────────────────────┐
│  STEP 1: INITIALIZE  - bun toolboxes/agent-mail/agent-mail.js macro-start-session   │
│  STEP 2: EXECUTE     - claim beads, do work, close beads                            │
│  STEP 3: REPORT      - bun toolboxes/agent-mail/agent-mail.js send-message          │
│  STEP 4: CLEANUP     - bun toolboxes/agent-mail/agent-mail.js release-file-reservations │
└──────────────────────────────────────────────────────────────────────────────┘
StepToolRequired
1bun toolboxes/agent-mail/agent-mail.js macro-start-session✅ FIRST
2bd update, bd close
3bun toolboxes/agent-mail/agent-mail.js send-message✅ LAST
4bun toolboxes/agent-mail/agent-mail.js release-file-reservations

Critical rules:

  • ❌ Never start work before macro-start-session
  • ❌ Never return without send-message to orchestrator
  • ❌ Never touch files outside assigned scope

See references/worker-prompt.md for full template.

Agent Routing

Intent KeywordsAgent TypeFile Reservation
research, find, locateResearchNone (read-only)
review, check, auditReviewNone (read-only)
plan, design, architectPlanningconductor/tracks/**
implement, build, createExecutionTask-specific scope
fix, debug, investigateDebugNone (read-only)

See references/intent-routing.md for mappings.

Anti-Patterns

❌ Don't✅ Do
Spawn workers without pre-registrationRegister all workers BEFORE spawning
Skip completion summaryAlways send_message before exit
Ignore file reservation conflictsWait or resolve before proceeding
Use orchestration for simple tasksUse sequential /conductor-implement

Lazy References

Load references only when needed:

PhaseTrigger ConditionReference
AlwaysOn skill loadSKILL.md (this file)
Phase 3 (Initialize)Setting up Agent Mail, project registrationagent-mail.md
Phase 4 (Spawn)Before dispatching worker agentsworker-prompt.md
Phase 6 (Handle Issues)Cross-track dependencies, blocker resolutionagent-coordination.md

All References

TopicFile
Full workflowworkflow.md
Architecturearchitecture.md
Coordination modescoordination-modes.md
Agent Mail protocolagent-mail.md
Agent Mail CLIagent-mail-cli.md
Worker prompt templateworker-prompt.md
Preflight/session brainpreflight.md
Intent routingintent-routing.md
Summary formatsummary-protocol.md
Auto-routingauto-routing.md
Track threadstrack-threads.md

Score

Total Score

75/100

Based on repository quality metrics

SKILL.md

SKILL.mdファイルが含まれている

+20
LICENSE

ライセンスが設定されている

+10
説明文

100文字以上の説明がある

+10
人気

GitHub Stars 100以上

0/15
最近の活動

1ヶ月以内に更新

+10
フォーク

10回以上フォークされている

0/5
Issue管理

オープンIssueが50未満

+5
言語

プログラミング言語が設定されている

+5
タグ

1つ以上のタグが設定されている

+5

Reviews

💬

Reviews coming soon