Quarterback
Enables automated task updates, deliverable logging, and priority checking directly within CI/CD pipelines using the Quarterback CLI.
Triggers automated workflows in n8n via webhooks when tasks are updated, completed, or marked as ready for autonomous agent execution.
Sends real-time notifications and task updates to Slack channels when orchestration events or status changes occur.
Integrates with Zapier webhooks to automate downstream tasks and notifications based on project management events and priority shifts.
Quarterback
Read the field. Call the play.
Strategic task prioritization and agent orchestration for multi-project operators.
Every 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.
What Makes Quarterback Different
Feature | Quarterback | TaskMaster AI | Shrimp Task Manager |
Multi-project prioritization | 5-factor weighted engine | Single-project breakdown | Single-project |
Advisory document system | Analyze articles against your goals | No | No |
Agent orchestration | Autonomy levels + webhooks | No | No |
Time-aware planning | Working hours, lunch, buffer time | No | No |
Organizational context | Goals, constraints, workflows | No | No |
Knowledge wiki (Playbook) | LLM-maintained wiki for cross-session consistency | No | No |
Conflict detection | Cross-project scheduling conflicts | No | No |
Standalone CLI | Full CLI without AI runtime | Requires AI | Requires AI |
Cost | Free (MIT) | Free | Free |
Related MCP server: MCP GitHub Project Manager
Quick Start
# Install
pip install quarterback
# Initialize (creates ~/.quarterback/)
quarterback init
# Interactive setup wizard — walks you through org, goals, workflows, projects, constraints
quarterback setup
# Add your first project and tasks
quarterback add "Launch landing page" --project "My Startup" --priority 4 --effort 3 --impact 5
quarterback add "Write blog post" --project "Content" --priority 3 --effort 2 --impact 3
# See what to work on
quarterback priorities
# Find quick wins
quarterback quick-wins
# Plan your day with time awareness
quarterback plan-dayLLM-Powered Setup (via MCP)
When 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.
MCP Server
Quarterback 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.
# Install with MCP support
pip install quarterback[mcp]Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"quarterback": {
"command": "quarterback-server"
}
}
}Or for Claude Code (~/.claude/settings.json):
{
"mcpServers": {
"quarterback": {
"command": "quarterback-server"
}
}
}The same quarterback-server command works with any MCP client — just add it to your client's server configuration.
Then ask your LLM: "What should I work on today?" — it will use all 23 Quarterback tools to analyze your priorities.
Features
5-Factor Prioritization Engine
Every task is scored across five dimensions:
Factor | Weight | What it measures |
Impact | 30% | Task impact + project revenue/strategic value |
Urgency | 25% | Due date proximity + blocking status |
Strategic | 25% | Project priority + milestone status |
Effort | 15% | Inverted effort score (quick tasks score higher) |
Quick Win | 5% | High impact + low effort bonus |
Advisory Document System
Analyze external articles, books, and advice against your organizational context:
# Import and auto-analyze an article
quarterback advisory-add --title "Growth Strategy" --url https://example.com/article
# Review the analysis
quarterback advisory-view --id 1
# Approve recommendations (optionally create tasks)
quarterback advisory-approve --id 1 --approve 1,3,5 --create-tasksThe analyzer checks every recommendation against your goals and constraints, flagging conflicts and synergies.
Agent Orchestration
Mark tasks for autonomous agent execution with configurable autonomy:
Draft: Agent creates a draft for your review
Checkpoint: Agent pauses at key decisions for approval
Autonomous: Agent runs to completion
Webhooks notify your automation layer (n8n, Zapier, custom) when tasks are ready.
Playbook — Knowledge Wiki
Playbook 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.
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.
How it works:
~/playbook/ (or ~/.quarterback/playbook/)
├── CLAUDE.md # Schema — how the LLM reads/writes pages
├── raw/ # Drop zone for source material
└── wiki/
├── index.md # Master catalog — read this first
├── entities/ # Companies, products, clients, tools
├── concepts/ # Patterns, strategies, recurring themes
├── decisions/ # Decisions with rationale and alternatives
├── compiled/ # QB-compatible files for task scoring
│ ├── goals.md # Read by QB's prioritization engine
│ └── constraints.md # Read by QB's conflict detection
└── log.md # Append-only operations recordSetup: 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.
Without Playbook: Quarterback works exactly as before — reading goals and constraints from ~/.quarterback/org-context/ files. Playbook is opt-in.
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.
# Check Playbook status
quarterback playbook status
# Browse the index
quarterback playbook index
# List pages by category
quarterback playbook list --category entities
# Read a specific page
quarterback playbook read entities/my-product.md
# Search across all pages
quarterback playbook search "budget"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 for programmatic access. No Obsidian dependency required — Playbook works as plain markdown files.
CI/CD Pipeline Integration
Quarterback'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.
Direct CLI in pipelines
Add Quarterback commands to any CI/CD step. The CLI is stateless and scriptable:
# GitHub Actions example: auto-update task on deploy
- name: Mark deploy task complete
run: |
pip install quarterback
export QUARTERBACK_HOME=${{ runner.temp }}/.quarterback
quarterback update 42 --status completed --notes "Deployed via CI, SHA: ${{ github.sha }}"# After test suite passes, log results to a task
- name: Report test results
run: |
quarterback update 38 --notes "Tests passed: 106/106, coverage 87%. Build #${{ github.run_number }}"# Nightly: check for overdue deliverables and alert
- name: Nightly priority check
run: |
quarterback alert-check
quarterback priorities today --limit 5Agentic CI/CD with webhooks
Register a webhook and let your automation layer react to task events in real time:
# Register a webhook pointing at your n8n/Zapier/custom endpoint
quarterback-server # MCP tools available, or use CLI:# In your automation script: mark a task agent-ready after PR merge
import subprocess
subprocess.run([
"quarterback", "update", "55",
"--status", "completed",
"--notes", f"PR #{pr_number} merged. Deployed to staging."
])Use cases:
Pipeline event | Quarterback action | What happens |
PR merged |
| Task marked done, webhook fires to Slack |
Deploy succeeds |
| Deliverable tracked with audit trail |
Nightly cron |
| Team gets daily summary of what's overdue |
Test suite fails |
| Bug auto-filed, linked to project |
Sprint starts |
| Surface scheduling conflicts before work begins |
Agent completes work |
| Webhook notifies orchestrator, next task dispatched |
Release tagged |
| Changelog analyzed against project goals |
Shared database across environments
Point multiple environments at the same Quarterback instance:
# All CI runners share one database via mounted volume or network path
export QUARTERBACK_HOME=/shared/quarterback
# Or per-environment with migration
quarterback migrate /path/to/sourceThis 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.
Time-Aware Planning
quarterback plan-dayConsiders your working hours, lunch break, buffer time for meetings, and current time to suggest tasks that actually fit in your remaining day.
Configuration
Organizational Context
After 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/:
~/.quarterback/org-context/
├── goals.md # Your strategic, workflow, and project goals
├── projects.yaml # Active projects with metadata
├── workflows.yaml # Groups of related projects
└── constraints.md # Time, budget, and strategic boundariesExample templates are included — copy from .example files and customize.
If 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.
Alert Configuration
Configure notifications in ~/.quarterback/config/alerts.yaml:
Quiet hours (no notifications at night)
Priority thresholds (only notify for P4+ tasks)
Time-sensitive projects (always notify for Bills, Tax, etc.)
Working hours and lunch break settings
CLI Commands
Command | Description |
| Initialize Quarterback |
| Interactive setup wizard |
| Migrate from task-manager |
| Prioritized task list |
| Add a task |
| Update a task |
| List tasks |
| Find quick wins |
| Detect priority conflicts |
| List projects |
| Organizational summary |
| Time-aware daily plan |
| Add advisory document |
| List advisory documents |
| View document details |
| Analyze document |
| Approve/reject recommendations |
| Check for alerts |
| Send daily summary |
| Playbook initialization status |
| Show Playbook master catalog |
| List wiki pages (with |
| Read a wiki page |
| Full-text search across pages |
MCP Tools (27 total)
When used as an MCP server, Quarterback exposes these tools to Claude:
Task Management: get_priorities, add_task, update_task, get_quick_wins, detect_conflicts, assess_task_value, get_blocking_tasks
Project Management: add_project, list_projects, update_project, get_organizational_summary
Advisory System: add_advisory_document, list_advisory_documents, get_advisory_document, analyze_advisory_document, discuss_advisory_recommendations, adopt_advisory_recommendations
Playbook: playbook_read, playbook_write, playbook_search, playbook_ingest
Webhooks: register_webhook, list_webhooks, update_webhook, delete_webhook
Agent Orchestration: mark_task_agent_ready, get_agent_ready_tasks, update_agent_status
Setup: setup_quarterback
Environment Variables
Variable | Default | Description |
|
| Data directory |
|
| Playbook wiki location (or set in |
| None | Reserved for Pro features |
Contributing
See CONTRIBUTING.md for development setup, code style, and PR process.
License
MIT - see LICENSE
Built by NodeBridge Automation Solutions | GitHub Sponsors
Available Tools
24 toolsadd_advisory_documentC
Add a new advisory document for review and analysis.
Inputs: title (required), content (required), source, source_type, +5 more.
add_projectD
Add a new project.
Inputs: name (required), path, workflow_name, description, +2 more.
add_taskC
Add a new task with full metadata.
Inputs: description (required), project_name, priority, effort, +3 more.
adopt_advisory_recommendationsC
Approve or reject recommendations, optionally creating tasks.
Inputs: document_id (required), approved_recommendation_ids, rejected_recommendation_ids, create_tasks, +1 more.
analyze_advisory_documentC
Analyze an advisory document against organizational context.
Inputs: document_id (required).
assess_task_valueC
Assess whether a proposed task aligns with organizational goals.
Inputs: task_description (required).
delete_webhookC
Delete a registered webhook.
Inputs: webhook_id (required).
detect_conflictsC
Detect conflicting priorities and resource constraints.
Inputs: no named parameters.
discuss_advisory_recommendationsD
Facilitate discussion about advisory recommendations.
Inputs: document_id (required), recommendation_ids, user_feedback.
get_advisory_documentC
Get full details of a specific advisory document.
Inputs: document_id (required).
get_agent_ready_tasksC
Get tasks queued for agent execution.
Inputs: agent_type, limit.
get_blocking_tasksC
Get tasks that are blocking other work.
Inputs: project_name.
get_organizational_summaryC
Get comprehensive organizational state summary.
Inputs: no named parameters.
get_prioritiesC
Get prioritized list of tasks based on organizational context.
Inputs: timeframe, project_name, status, limit.
get_quick_winsC
Identify quick win tasks (high impact, low effort).
Inputs: project_name, limit.
list_advisory_documentsC
List advisory documents with filtering.
Inputs: status, project_name, workflow_name, source_type, +1 more.
list_projectsD
List all projects.
Inputs: status.
list_webhooksB
List all registered webhooks.
Inputs: no named parameters.
mark_task_agent_readyC
Mark a task for autonomous agent execution.
Inputs: task_id (required), agent_config (required).
register_webhookC
Register a webhook endpoint to receive task events.
Inputs: name (required), url (required), events (required), secret.
update_agent_statusC
Update agent execution status of a task.
Inputs: task_id (required), agent_status (required), agent_output.
update_projectD
Update a project's properties.
Inputs: name (required), status, priority, description, +1 more.
update_taskD
Update an existing task.
Inputs: task_id (required), status, priority, effort, +2 more.
update_webhookD
Update a webhook configuration.
Inputs: webhook_id (required), name, url, events, +2 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 24 tools
Tools are well-differentiated across distinct domains: advisory document workflows (analyze/discuss/adopt), task intelligence (assess/value vs. priorities vs. quick wins), and agent orchestration (mark ready vs. update status). While several tools operate on tasks, their purposes—assessment, prioritization, blocking detection, and agent handoff—are clearly distinct.
Follows verb_noun convention consistently (add_task, analyze_advisory_document, detect_conflicts). Minor deviations exist: register_webhook breaks the add_* pattern used for other resources, and mark_task_agent_ready uses 'mark' instead of 'update' compared to update_agent_status, but these are readable exceptions rather than chaos.
With 24 tools, this pushes into the 'heavy' category (16-25 range) for a single server. While the domain (project orchestration + advisory workflows + agent execution + webhooks) justifies complexity, the surface area is large enough that agents may struggle to navigate the full set without careful prompting.
Strong coverage of advisory document lifecycles and agent orchestration, but notable gaps in basic CRUD: missing get_project and get_task (forcing reliance on list operations with filtering), and no delete operations for projects, tasks, or advisory documents. Webhooks also lack individual retrieval.
Maintenance
Related MCP Connectors
A Model Context Protocol (MCP) application for automated GitHub PR analysis and issue management.…
Project board for ChatGPT, Claude and coding agents, with scoped MCP access to projects and tasks.
Independent directory of agentic AI tools — search, compare & recommend via MCP. Read-only.
Project management for humans and AI agents: goals, metrics, projects, and issues.
Related MCP Servers
- AlicenseNot gradedqualityAmaintenanceTurns GitHub Projects v2 into an agentic project management layer where AI coding agents register, atomically claim and track tasks, heartbeat, review each other's work, and operate within token budgets, all backed by GitHub-native storage with no external infrastructure. It also gives humans AI-powered PRD generation, PRD-to-issues pipelines, sprint planning, triage, roadmap creation, and requirements traceability across 20 compound tools exposing 169 actions, plus MCP resources, prompts, and sampling support.272 npmMIT
- AlicenseNot gradedqualityAmaintenanceEnables AI agents and project managers to turn GitHub Projects v2 into an autonomous project-management layer, handling task checkout, atomic claims, heartbeats, reviews, token budgets, and AI-powered PRD, sprint, triage, and roadmap workflows. It also provides GitHub Actions, Releases, Branches, MCP Resources, and MCP Prompts support with GitHub-native storage.272 npmMIT
- AlicenseNot gradedqualityAmaintenanceEnables AI coding agents and human managers to coordinate work on GitHub Projects v2 through 20 tools and 169 actions for autonomous task checkout, heartbeats, reviews, token budgets, PRD generation, sprint planning, issue triage, and PRD-to-issues pipelines, backed by GitHub-native storage and MCP resources/prompts.272 npmMIT
- AlicenseNot gradedqualityAmaintenanceTurns GitHub Projects v2 into an autonomous agentic task substrate where AI coding agents register, atomically claim tasks, heartbeat, submit and review work products, and operate under per-agent token budgets — all stored natively in GitHub issues, fields, and comments with no external infrastructure. It also gives humans AI-powered PRD generation, task breakdown and materialization, sprint planning, issue triage, and requirements traceability across 20 compound tools exposing 169 actions, plus MCP resources and prompts.272 npmMIT