agentspan
agentspan-ai/agentspan
AGENTS.md guide for the Agentspan Python SDK, detailing architecture, compilation pipelines, testing standards, and development workflows for AI agents contributing to the codebase.
493 47MITUpdated 2026-08-12
85
GreatOverview
This instruction file outlines the developer guidelines, project layout, architecture principles, coding conventions, and validation checklists for AI agents working on the Agentspan SDK. Agentspan compiles Python agent definitions into durable Conductor workflows, ensuring high fault tolerance, server-first execution, and robust multi-agent orchestration.
Capabilities
- ▸Compile Python agent definitions into Conductor workflow JSON
- ▸Manage multi-agent strategies like handoff, sequential, parallel, and router
- ▸Implement guardrails, conversation memory, and semantic memory
- ▸Execute code safely across local, Docker, Jupyter, and serverless environments
- ▸Enforce strict linting, type checking, and testing practices
Best for
Providing context and rules for AI coding assistants working on the Agentspan repository, Understanding the compilation pipeline from Python agent definitions to Conductor JSON workflows, Writing and running unit and integration tests following strict non-flaky guidelines, Adding new tools, multi-agent strategies, and maintaining clean public APIs
Works with
Claude CodeCursorGitHub Copilot
Evoa Score breakdown= Σ (score × weight)
85Task 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%95 → +14.3
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%41 → +4.9
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%100 → +15.0
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%69 → +5.5
コミュニティの採用度。 — GitHub Stars/Forks（対数スケール）
Compatibility5%75 → +3.8
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 total84.5 / 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
Ensure no sensitive credentials or Conductor server tokens are exposed when running integration tests or configuring deployment 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.