claude-code-orchestra
DeL-TaiseiOzaki/claude-code-orchestra
Claude Code Orchestra is a multi-agent AI development environment that coordinates Claude Code, Sonnet, Opus, and Codex CLI to handle complex software engineering tasks. It delegates routine and deep implementation work away from the main orchestrator to preserve context window quality and ensure rigorous verification.
190 34MITUpdated 2026-07-29
75
GreatOverview
This skill provides a shared operating contract and multi-agent topology designed to structure software development tasks across different AI CLI tools. Acting as an orchestrator, Claude Code routes sub-tasks to specialized subagents like general-purpose-sonnet, general-purpose-opus, codex-debugger, and Codex CLI based on strict delegation policies. It maintains project state, enforces quality gates, manages context conservation, and provides robust integration workflows for building and maintaining codebases efficiently.
Capabilities
- ▸Multi-agent task routing and delegation
- ▸Context window conservation and background execution
- ▸Codex CLI integration and job management
- ▸Automated project initialization and state tracking
- ▸Quality gate enforcement and diff inspection
Best for
Orchestrating complex multi-file software implementations using specialized sub-agents, Delegating routine coding tasks to Sonnet while reserving Opus and Codex for deep research, planning, and debugging, Maintaining pristine context windows in Claude Code by offloading long logs and cross-codebase investigations, Enforcing systematic quality gates, testing, and independent verification on all generated code changes
Works with
Claude CodeCodex
Evoa Score breakdown= Σ (score × weight)
75Task usefulness20%88 → +17.6
実タスクにどれだけ役立つか（機能の豊富さ・用途の明確さ）。 — AIによるcapabilities/use-cases解析
Code quality15%90 → +13.5
実装・指示の品質。 — AIによるSKILL.md/README解析
Maintenance15%100 → +15.0
リポジトリがどれだけ活発に保守されているか。 — GitHub 最終push日時の新しさ
Documentation12%49 → +5.9
ドキュメントの充実度・分かりやすさ。 — README/独自要約の情報量
Security15%50 → +7.5
危険・不審な挙動が無いか。 — AIによるセキュリティレビュー
Originality10%85 → +8.5
ありふれたラッパーではない独自性。 — AIによる独自性判定
Popularity8%60 → +4.8
コミュニティの採用度。 — GitHub Stars/Forks（対数スケール）
Compatibility5%50 → +2.5
対応AIエージェントの広さ。 — AIによる対応エージェント判定
Weighted total75.3 / 100
ライセンス不明/制限あり（Red）のSkillは総合スコアに0.85倍の補正を適用します。 ランキングはこのScoreのみで決まり、広告で変わりません。 算出方法の詳細 →
Security considerations
The environment executes subagent workflows and CLI commands across different AI runtimes. Ensure all scripts installed via the initialization hook are reviewed before running in production environments.
Categories
Summary and analysis are original content generated by AI Skills Rank. The skill's source text is not reproduced here — view it on the linked repository.