{
  "markdown": "<!-- mcp-name: io.github.bobbyrgoldsmith/quarterback -->\n\n# Quarterback\n\n**Read the field. Call the play.**\n\nStrategic task prioritization and agent orchestration for multi-project operators.\n\n[![PyPI](https://img.shields.io/pypi/v/quarterback)](https://pypi.org/project/quarterback/)\n[![Python](https://img.shields.io/pypi/pyversions/quarterback)](https://pypi.org/project/quarterback/)\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)\n[![CI](https://github.com/bobbyrgoldsmith/quarterback/actions/workflows/ci.yml/badge.svg)](https://github.com/bobbyrgoldsmith/quarterback/actions/workflows/ci.yml)\n[![bobbyrgoldsmith/quarterback MCP server](https://glama.ai/mcp/servers/bobbyrgoldsmith/quarterback/badges/score.svg)](https://glama.ai/mcp/servers/bobbyrgoldsmith/quarterback)\n\n---\n\nEvery other AI task manager breaks down **one project** into subtasks. Quarterback helps you decide which of your **ten projects** to prioritize right now — using a 5-factor weighted scoring engine, organizational context, and time-aware planning. It runs locally, costs nothing, and works as both a standalone CLI and an MCP server for Claude.\n\n## What Makes Quarterback Different\n\n| Feature | Quarterback | TaskMaster AI | Shrimp Task Manager |\n|---------|-------------|---------------|---------------------|\n| **Multi-project prioritization** | 5-factor weighted engine | Single-project breakdown | Single-project |\n| **Advisory document system** | Analyze articles against your goals | No | No |\n| **Agent orchestration** | Autonomy levels + webhooks | No | No |\n| **Time-aware planning** | Working hours, lunch, buffer time | No | No |\n| **Organizational context** | Goals, constraints, workflows | No | No |\n| **Knowledge wiki (Playbook)** | LLM-maintained wiki for cross-session consistency | No | No |\n| **Conflict detection** | Cross-project scheduling conflicts | No | No |\n| **Standalone CLI** | Full CLI without AI runtime | Requires AI | Requires AI |\n| **Cost** | Free (MIT) | Free | Free |\n\n## Quick Start\n\n```bash\n# Install\npip install quarterback\n\n# Initialize (creates ~/.quarterback/)\nquarterback init\n\n# Interactive setup wizard — walks you through org, goals, workflows, projects, constraints\nquarterback setup\n\n# Add your first project and tasks\nquarterback add \"Launch landing page\" --project \"My Startup\" --priority 4 --effort 3 --impact 5\nquarterback add \"Write blog post\" --project \"Content\" --priority 3 --effort 2 --impact 3\n\n# See what to work on\nquarterback priorities\n\n# Find quick wins\nquarterback quick-wins\n\n# Plan your day with time awareness\nquarterback plan-day\n```\n\n### LLM-Powered Setup (via MCP)\n\nWhen using Quarterback as an MCP server, ask your LLM: *\"Set up Quarterback for me\"* — it will call the `setup_quarterback` tool, interview you conversationally about your business, goals, workflows, projects, constraints, and knowledge base (Playbook), then write all config files and database records in one shot. No manual YAML editing required.\n\n## MCP Server\n\nQuarterback works with **any MCP-compatible client** — Claude Desktop, Claude Code, Cursor, Windsurf, Cline, OpenAI agents, and others. All 23 tools use standard MCP protocol (JSON-RPC over stdio) with no LLM-specific dependencies.\n\n```bash\n# Install with MCP support\npip install quarterback[mcp]\n```\n\nAdd to your Claude Desktop config (`~/Library/Application Support/Claude/claude_desktop_config.json`):\n\n```json\n{\n  \"mcpServers\": {\n    \"quarterback\": {\n      \"command\": \"quarterback-server\"\n    }\n  }\n}\n```\n\nOr for Claude Code (`~/.claude/settings.json`):\n\n```json\n{\n  \"mcpServers\": {\n    \"quarterback\": {\n      \"command\": \"quarterback-server\"\n    }\n  }\n}\n```\n\nThe same `quarterback-server` command works with any MCP client — just add it to your client's server configuration.\n\nThen ask your LLM: *\"What should I work on today?\"* — it will use all 23 Quarterback tools to analyze your priorities.\n\n## Features\n\n### 5-Factor Prioritization Engine\n\nEvery task is scored across five dimensions:\n\n| Factor | Weight | What it measures |\n|--------|--------|-----------------|\n| **Impact** | 30% | Task impact + project revenue/strategic value |\n| **Urgency** | 25% | Due date proximity + blocking status |\n| **Strategic** | 25% | Project priority + milestone status |\n| **Effort** | 15% | Inverted effort score (quick tasks score higher) |\n| **Quick Win** | 5% | High impact + low effort bonus |\n\n### Advisory Document System\n\nAnalyze external articles, books, and advice against your organizational context:\n\n```bash\n# Import and auto-analyze an article\nquarterback advisory-add --title \"Growth Strategy\" --url https://example.com/article\n\n# Review the analysis\nquarterback advisory-view --id 1\n\n# Approve recommendations (optionally create tasks)\nquarterback advisory-approve --id 1 --approve 1,3,5 --create-tasks\n```\n\nThe analyzer checks every recommendation against your goals and constraints, flagging conflicts and synergies.\n\n### Agent Orchestration\n\nMark tasks for autonomous agent execution with configurable autonomy:\n\n- **Draft**: Agent creates a draft for your review\n- **Checkpoint**: Agent pauses at key decisions for approval\n- **Autonomous**: Agent runs to completion\n\nWebhooks notify your automation layer (n8n, Zapier, custom) when tasks are ready.\n\n### Playbook — Knowledge Wiki\n\nPlaybook is Quarterback's compiled knowledge layer. It's an LLM-maintained markdown wiki that gives every session — local CLI, MCP, or autonomous agent — the same canonical context about your projects, decisions, and strategies.\n\n**The problem it solves:** Without Playbook, each AI session starts fresh and re-derives your organizational context from sparse signals. Two sessions running the same query can produce different results because they reconstruct understanding independently. Playbook provides accumulated knowledge that all sessions read from.\n\n**How it works:**\n\n```\n~/playbook/                          (or ~/.quarterback/playbook/)\n├── CLAUDE.md                        # Schema — how the LLM reads/writes pages\n├── raw/                             # Drop zone for source material\n└── wiki/\n    ├── index.md                     # Master catalog — read this first\n    ├── entities/                    # Companies, products, clients, tools\n    ├── concepts/                    # Patterns, strategies, recurring themes\n    ├── decisions/                   # Decisions with rationale and alternatives\n    ├── compiled/                    # QB-compatible files for task scoring\n    │   ├── goals.md                 # Read by QB's prioritization engine\n    │   └── constraints.md           # Read by QB's conflict detection\n    └── log.md                       # Append-only operations record\n```\n\n**Setup:** Playbook is created automatically during `quarterback setup` (or the MCP setup wizard). The interview asks about your key entities, concepts, and decisions, then seeds initial wiki pages.\n\n**Without Playbook:** Quarterback works exactly as before — reading goals and constraints from `~/.quarterback/org-context/` files. Playbook is opt-in.\n\n**With Playbook:** Quarterback reads `compiled/goals.md` and `compiled/constraints.md` from Playbook first, falling back to `org-context/` files if Playbook isn't initialized. Your LLM reads `wiki/index.md` for full organizational context.\n\n```bash\n# Check Playbook status\nquarterback playbook status\n\n# Browse the index\nquarterback playbook index\n\n# List pages by category\nquarterback playbook list --category entities\n\n# Read a specific page\nquarterback playbook read entities/my-product.md\n\n# Search across all pages\nquarterback playbook search \"budget\"\n```\n\n**Obsidian integration (optional):** During setup, you can opt to configure Playbook as an Obsidian vault. Open the Playbook folder in Obsidian for graph visualization and visual editing. Install an [Obsidian MCP server](https://github.com/iansinnott/obsidian-claude-code-mcp) for programmatic access. No Obsidian dependency required — Playbook works as plain markdown files.\n\n### CI/CD Pipeline Integration\n\nQuarterback's CLI and webhook system make it a natural fit for automated pipelines — update task status, log deliverables, and trigger downstream work without a human in the loop.\n\n#### Direct CLI in pipelines\n\nAdd Quarterback commands to any CI/CD step. The CLI is stateless and scriptable:\n\n```yaml\n# GitHub Actions example: auto-update task on deploy\n- name: Mark deploy task complete\n  run: |\n    pip install quarterback\n    export QUARTERBACK_HOME=${{ runner.temp }}/.quarterback\n    quarterback update 42 --status completed --notes \"Deployed via CI, SHA: ${{ github.sha }}\"\n```\n\n```yaml\n# After test suite passes, log results to a task\n- name: Report test results\n  run: |\n    quarterback update 38 --notes \"Tests passed: 106/106, coverage 87%. Build #${{ github.run_number }}\"\n```\n\n```yaml\n# Nightly: check for overdue deliverables and alert\n- name: Nightly priority check\n  run: |\n    quarterback alert-check\n    quarterback priorities today --limit 5\n```\n\n#### Agentic CI/CD with webhooks\n\nRegister a webhook and let your automation layer react to task events in real time:\n\n```bash\n# Register a webhook pointing at your n8n/Zapier/custom endpoint\nquarterback-server  # MCP tools available, or use CLI:\n```\n\n```python\n# In your automation script: mark a task agent-ready after PR merge\nimport subprocess\nsubprocess.run([\n    \"quarterback\", \"update\", \"55\",\n    \"--status\", \"completed\",\n    \"--notes\", f\"PR #{pr_number} merged. Deployed to staging.\"\n])\n```\n\n**Use cases:**\n\n| Pipeline event | Quarterback action | What happens |\n|---------------|-------------------|--------------|\n| PR merged | `update_task` status=completed | Task marked done, webhook fires to Slack |\n| Deploy succeeds | `update_task` with SHA + environment notes | Deliverable tracked with audit trail |\n| Nightly cron | `get_priorities` + `alert-check` | Team gets daily summary of what's overdue |\n| Test suite fails | `add_task` with failure details | Bug auto-filed, linked to project |\n| Sprint starts | `get_priorities` + `detect_conflicts` | Surface scheduling conflicts before work begins |\n| Agent completes work | `update_agent_status` status=completed | Webhook notifies orchestrator, next task dispatched |\n| Release tagged | `advisory-add` with release notes | Changelog analyzed against project goals |\n\n#### Shared database across environments\n\nPoint multiple environments at the same Quarterback instance:\n\n```bash\n# All CI runners share one database via mounted volume or network path\nexport QUARTERBACK_HOME=/shared/quarterback\n\n# Or per-environment with migration\nquarterback migrate /path/to/source\n```\n\nThis lets your local CLI, CI pipelines, and MCP-connected agents all read and write to the same task graph — giving you a single source of truth across manual and automated workflows.\n\n### Time-Aware Planning\n\n```bash\nquarterback plan-day\n```\n\nConsiders your working hours, lunch break, buffer time for meetings, and current time to suggest tasks that actually fit in your remaining day.\n\n## Configuration\n\n### Organizational Context\n\nAfter `quarterback init`, run `quarterback setup` for an interactive wizard, or ask Claude to run the setup wizard via MCP. You can also manually configure your context in `~/.quarterback/org-context/`:\n\n```\n~/.quarterback/org-context/\n├── goals.md          # Your strategic, workflow, and project goals\n├── projects.yaml     # Active projects with metadata\n├── workflows.yaml    # Groups of related projects\n└── constraints.md    # Time, budget, and strategic boundaries\n```\n\nExample templates are included — copy from `.example` files and customize.\n\nIf you enable Playbook during setup, `goals.md` and `constraints.md` are auto-maintained from the wiki's `compiled/` directory. You can still manually edit the org-context files — Playbook is additive, not required.\n\n### Alert Configuration\n\nConfigure notifications in `~/.quarterback/config/alerts.yaml`:\n\n- Quiet hours (no notifications at night)\n- Priority thresholds (only notify for P4+ tasks)\n- Time-sensitive projects (always notify for Bills, Tax, etc.)\n- Working hours and lunch break settings\n\n## CLI Commands\n\n| Command | Description |\n|---------|-------------|\n| `quarterback init` | Initialize Quarterback |\n| `quarterback setup` | Interactive setup wizard |\n| `quarterback migrate <dir>` | Migrate from task-manager |\n| `quarterback priorities [today\\|week\\|all]` | Prioritized task list |\n| `quarterback add \"task\" [options]` | Add a task |\n| `quarterback update <id> [options]` | Update a task |\n| `quarterback list [-s status]` | List tasks |\n| `quarterback quick-wins` | Find quick wins |\n| `quarterback conflicts` | Detect priority conflicts |\n| `quarterback projects` | List projects |\n| `quarterback summary` | Organizational summary |\n| `quarterback plan-day` | Time-aware daily plan |\n| `quarterback advisory-add` | Add advisory document |\n| `quarterback advisory-list` | List advisory documents |\n| `quarterback advisory-view --id N` | View document details |\n| `quarterback advisory-analyze --id N` | Analyze document |\n| `quarterback advisory-approve --id N` | Approve/reject recommendations |\n| `quarterback alert-check` | Check for alerts |\n| `quarterback alert-summary` | Send daily summary |\n| `quarterback playbook status` | Playbook initialization status |\n| `quarterback playbook index` | Show Playbook master catalog |\n| `quarterback playbook list` | List wiki pages (with `--category` filter) |\n| `quarterback playbook read <path>` | Read a wiki page |\n| `quarterback playbook search <query>` | Full-text search across pages |\n\n## MCP Tools (27 total)\n\nWhen used as an MCP server, Quarterback exposes these tools to Claude:\n\n**Task Management**: `get_priorities`, `add_task`, `update_task`, `get_quick_wins`, `detect_conflicts`, `assess_task_value`, `get_blocking_tasks`\n\n**Project Management**: `add_project`, `list_projects`, `update_project`, `get_organizational_summary`\n\n**Advisory System**: `add_advisory_document`, `list_advisory_documents`, `get_advisory_document`, `analyze_advisory_document`, `discuss_advisory_recommendations`, `adopt_advisory_recommendations`\n\n**Playbook**: `playbook_read`, `playbook_write`, `playbook_search`, `playbook_ingest`\n\n**Webhooks**: `register_webhook`, `list_webhooks`, `update_webhook`, `delete_webhook`\n\n**Agent Orchestration**: `mark_task_agent_ready`, `get_agent_ready_tasks`, `update_agent_status`\n\n**Setup**: `setup_quarterback`\n\n## Environment Variables\n\n| Variable | Default | Description |\n|----------|---------|-------------|\n| `QUARTERBACK_HOME` | `~/.quarterback` | Data directory |\n| `PLAYBOOK_PATH` | `~/.quarterback/playbook` | Playbook wiki location (or set in `config/playbook.yaml`) |\n| `QUARTERBACK_API_URL` | None | Reserved for Pro features |\n\n## Contributing\n\nSee [CONTRIBUTING.md](CONTRIBUTING.md) for development setup, code style, and PR process.\n\n## License\n\nMIT - see [LICENSE](LICENSE)\n\n---\n\nBuilt by [NodeBridge Automation Solutions](https://nodebridge.dev) | [GitHub Sponsors](https://github.com/sponsors/bobbyrgoldsmith)\n",
  "bytes": 15091,
  "sha": "3b146058d65f2ef4e0242bf6b8e0e6aa5a97609e9dc30adae84c8b90ae2ce131",
  "repo_slug": "bobbyrgoldsmith/quarterback",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_bobbyrgoldsmith_quarterback_ee0d16a7/readme"
}