{"id":48733795,"url":"https://github.com/sohei56/claude-scrum-team","last_synced_at":"2026-05-03T11:02:20.400Z","repository":{"id":342099935,"uuid":"1163084136","full_name":"sohei56/claude-scrum-team","owner":"sohei56","description":"Scrum development team powered by Claude Code Agent Teams. AI Scrum Master and Developers run Sprint cycles while you stay in the Product Owner seat.","archived":false,"fork":false,"pushed_at":"2026-04-11T10:44:12.000Z","size":2981,"stargazers_count":3,"open_issues_count":1,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2026-04-11T12:24:15.380Z","etag":null,"topics":["agile","ai-agents","automation","claude","claude-agent-teams","claude-code","developer-tools","multi-agent","python3","scrum"],"latest_commit_sha":null,"homepage":"","language":"Shell","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/sohei56.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":".github/CODEOWNERS","security":"SECURITY.md","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-02-21T04:21:44.000Z","updated_at":"2026-03-31T03:23:37.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/sohei56/claude-scrum-team","commit_stats":null,"previous_names":["sohei56/claude-scrum-team"],"tags_count":2,"template":false,"template_full_name":null,"purl":"pkg:github/sohei56/claude-scrum-team","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sohei56%2Fclaude-scrum-team","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sohei56%2Fclaude-scrum-team/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sohei56%2Fclaude-scrum-team/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sohei56%2Fclaude-scrum-team/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/sohei56","download_url":"https://codeload.github.com/sohei56/claude-scrum-team/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sohei56%2Fclaude-scrum-team/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31702582,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-11T21:17:31.016Z","status":"online","status_checked_at":"2026-04-12T02:00:06.763Z","response_time":58,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agile","ai-agents","automation","claude","claude-agent-teams","claude-code","developer-tools","multi-agent","python3","scrum"],"created_at":"2026-04-12T03:04:16.346Z","updated_at":"2026-05-03T11:02:20.392Z","avatar_url":"https://github.com/sohei56.png","language":"Shell","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cp align=\"center\"\u003e\n  \u003cimg alt=\"claude-scrum-team\" src=\"images/claude-scrum-team.png\" width=\"700\"\u003e\n\u003c/p\u003e\n\n\u003ch1 align=\"center\"\u003eclaude-scrum-team\u003c/h1\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003cstrong\u003eAI-Powered Scrum Team for Claude Code — a full Scrum workflow driven by multi-agent coordination via Agent Teams\u003c/strong\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://github.com/sohei56/claude-scrum-team/blob/main/LICENSE\"\u003e\u003cimg src=\"https://img.shields.io/github/license/sohei56/claude-scrum-team?style=flat-square\u0026color=blue\" alt=\"License\"\u003e\u003c/a\u003e\n  \u003cimg src=\"https://img.shields.io/badge/python-3.9%2B-3776AB?style=flat-square\u0026logo=python\u0026logoColor=white\" alt=\"Python 3.9+\"\u003e\n  \u003cimg src=\"https://img.shields.io/badge/bash-3.2%2B-4EAA25?style=flat-square\u0026logo=gnubash\u0026logoColor=white\" alt=\"Bash 3.2+\"\u003e\n  \u003cimg src=\"https://img.shields.io/badge/Claude_Code-Agent_Teams-D97706?style=flat-square\u0026logo=anthropic\u0026logoColor=white\" alt=\"Claude Code Agent Teams\"\u003e\n  \u003cimg src=\"https://img.shields.io/badge/TUI-Textual-7C3AED?style=flat-square\" alt=\"Textual TUI\"\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"#why\"\u003eWhy?\u003c/a\u003e \u0026bull;\n  \u003ca href=\"#demo\"\u003eDemo\u003c/a\u003e \u0026bull;\n  \u003ca href=\"#features\"\u003eFeatures\u003c/a\u003e \u0026bull;\n  \u003ca href=\"#quick-start\"\u003eQuick Start\u003c/a\u003e \u0026bull;\n  \u003ca href=\"#architecture\"\u003eArchitecture\u003c/a\u003e \u0026bull;\n  \u003ca href=\"#development\"\u003eDevelopment\u003c/a\u003e\n\u003c/p\u003e\n\n---\n\nRun `scrum-start.sh` in any project directory and a full AI Scrum team takes over — a **Scrum Master** coordinates **Developer** agents through Sprint cycles while you act as the **Product Owner**, approving goals and reviewing the working product.\n\n## Why?\n\nVibe coding is fast but chaotic. Spec-Driven Development (SDD) is disciplined but demands everything upfront. Most real projects live in between — requirements are fuzzy and need to be shaped as you go.\n\n**claude-scrum-team** brings Scrum's inspect-and-adapt loop to Claude Code, giving you structured iteration without requiring a complete specification on day one. You stay in the Product Owner seat — describing what you want, approving Sprint Goals, and reviewing working software each Sprint — while a team of AI agents handles the rest.\n\n## Demo\n\n\u003cp align=\"center\"\u003e\n  \u003cimg alt=\"scrum-start.sh demo\" src=\"images/demo.gif\" width=\"800\"\u003e\n\u003c/p\u003e\n\nOne command sets up agents, skills, and hooks — then launches Claude Code with a Scrum Master agent alongside a real-time TUI dashboard in tmux.\n\n### What a session looks like\n\n1. **You describe your project** — the Scrum Master spawns a Developer to elicit requirements and write `requirements.md`\n2. **Backlog Refinement** — the SM creates and refines PBIs from your requirements\n3. **Sprint Planning** — the SM proposes a Sprint Goal; you approve or adjust\n4. **Design + Implementation + Cross-Review** — Developers design and implement their PBIs in parallel, then review each other's work (no self-review)\n5. **Sprint Review** — the SM launches the app and demos every completed PBI; you confirm each works\n6. **Retrospective** — the team reflects and records improvements for the next Sprint\n7. **Repeat** until the Product Goal is achieved, then an **Integration Sprint** runs automated tests and a final UAT\n\n## Features\n\n- **14 ceremony skills** covering the full Scrum lifecycle: requirements elicitation, backlog refinement, sprint planning, design, implementation, cross-review, sprint review, retrospective, and integration testing\n- **Multi-agent coordination** — Scrum Master (Delegate mode) orchestrates up to 6 parallel Developer agents per Sprint\n- **Real-time TUI dashboard** — Textual-based four-panel display (Sprint Overview, PBI Progress Board, Communication Log, Work Log) with watchdog filesystem monitoring\n- **Design document governance** — immutable catalog (`catalog.md`) with editable enablement config (`catalog-config.json`), enforced by phase-gate hooks\n- **Quality enforcement hooks** — phase gates (source code restrictions), completion gates (exit criteria), quality gates (Definition of Done), dashboard events, and session context restoration\n- **State persistence** — all state in `.scrum/` JSON files for full session resume capability\n- **Automated testing** — Integration Sprints run smoke tests, unit tests, and E2E via Playwright\n- **Retrospective-driven improvement** — improvements from past Sprints are applied automatically\n\n### AI-Specific Adaptations\n\nThis is not a carbon copy of human Scrum — it adapts the framework to how AI agents actually work.\n\n**Extensions leveraging AI strengths:**\n\n- **Dynamic team sizing** — the number of Developer agents is optimized per Sprint based on PBI count and complexity\n- **Independent cross-review** — the Scrum Master spawns project-managed reviewer sub-agents (`code-reviewer`, `security-reviewer`, `codex-code-reviewer`) for unbiased, design-driven code review that checks implementation against requirements and design docs\n\n**Constraints addressing AI weaknesses:**\n\n- **Mandatory Requirements Sprint** — the first Sprint is dedicated solely to requirements elicitation, preventing the team from charging ahead without a map\n- **No work without a PBI** — all development must be tied to a backlog item, stopping the Scrum Master from drifting into ad-hoc fixes mid-conversation\n- **Controlled document creation** — only document types listed in the design catalog may be created, curbing the AI tendency to produce sprawling, unstructured documentation\n- **PO-driven Sprint scope** — Sprint boundaries are set by meaningful review checkpoints rather than velocity estimates, since AI agents have no stable velocity baseline\n\n### Sprint Lifecycle\n\n```\n ┌─────────────────────────────────────────────────────────────┐\n │  Requirements Sprint (Sprint 0)                             │\n │  Requirements Elicitation ──▶ Initial Product Backlog       │\n └──────────────────────────────┬──────────────────────────────┘\n                                ▼\n ┌─────────────────────────────────────────────────────────────┐\n │  Sprint N                                                   │\n │                                                             │\n │  1. Backlog Refine    PBIs: draft ──▶ refined               │\n │          ▼                                                  │\n │  2. Planning          PO approves Sprint Goal               │\n │          ▼                                                  │\n │  3. Scaffold Specs    Create design doc stubs from catalog  │\n │          ▼                                                  │\n │  4. Spawn Teammates   Launch Developer agents for PBIs      │\n │          ▼                                                  │\n │  5. Design            Write design specs (parallel)         │\n │          ▼                                                  │\n │  6. Implementation    Build features with TDD (parallel)    │\n │          ▼                                                  │\n │  7. Cross-Review      Devs review each other's work         │\n │          ▼                                                  │\n │  8. Sprint Review     Demo to PO, accept/reject PBIs        │\n │          ▼                                                  │\n │  9. Retrospective     Record improvements for next Sprint   │\n └──────────┬──────────────────────────┬───────────────────────┘\n            │                          │\n            ▼                          ▼\n     Next Sprint N+1   ┌───────────────────────────────────────┐\n                       │  Integration Sprint                   │\n                       │  Smoke Tests ──▶ UAT ──▶ Release      │\n                       └───────────────────────────────────────┘\n```\n\n## Quick Start\n\n```bash\n# Clone the repository\ngit clone git@github.com:sohei56/claude-scrum-team.git\n\n# In your project directory:\ncd /path/to/your/project\n\n# Launch the Scrum team (auto-installs Python dependencies if needed)\nsh /path/to/claude-scrum-team/scrum-start.sh\n```\n\nThe script validates prerequisites (auto-installing `textual` and `watchdog` if missing), copies agent definitions, Skills, hooks, and the design catalog to your project's `.claude/` directory, and launches a tmux session with Claude Code (Scrum Master) and the TUI dashboard.\n\nFor detailed setup instructions, see [quickstart.md](docs/quickstart.md).\n\n### Prerequisites\n\n- **Claude Code CLI** installed and on PATH\n- **Python 3.9+** with `textual` and `watchdog`\n- **tmux** (recommended) for side-by-side dashboard layout\n\n### Your role as Product Owner\n\n| You do | The AI team does |\n|--------|-----------------|\n| Describe what you want to build | Elicit and write detailed requirements |\n| Approve Sprint Goals | Plan Sprints and assign PBIs |\n| Review demos in the running app | Design, implement, and cross-review code |\n| Report defects during UAT | Fix defects and re-test automatically |\n| Make release decisions | Run automated test suites |\n\n## Architecture\n\n| Component | Description |\n|-----------|-------------|\n| `scrum-start.sh` | Entry point — validates prereqs, copies agents/skills, launches tmux |\n| `agents/` | Scrum Master (Delegate mode) and Developer agent definitions |\n| `skills/` | 14 ceremony Skills with mandatory Inputs/Outputs |\n| `hooks/` | Phase gates, completion gates, quality gates, dashboard events, session context |\n| `dashboard/app.py` | Textual TUI with real-time panels |\n| `scripts/` | Status line, user setup, contributor setup |\n| `.scrum/` | Runtime state (JSON, gitignored) |\n| `docs/design/` | Design documents governed by `catalog.md` (read-only) + `catalog-config.json` (enabled list) |\n| `agents/` sub-agents | Project-managed specialist sub-agents: `code-reviewer`, `security-reviewer`, `codex-code-reviewer`, plus PBI Pipeline sub-agents (`pbi-designer`, `pbi-implementer`, `pbi-ut-author`, `codex-design-reviewer`, `codex-impl-reviewer`, `codex-ut-reviewer`) |\n| `.mcp-servers/` | MCP server implementations (OpenAI/Codex bridge for cross-model review) |\n\n## Development\n\nSee [CONTRIBUTING.md](CONTRIBUTING.md) for development setup and workflow.\n\n## License\n\n[MIT](LICENSE)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsohei56%2Fclaude-scrum-team","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsohei56%2Fclaude-scrum-team","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsohei56%2Fclaude-scrum-team/lists"}