sprintpilot

Engage autonomous story execution for BMad Method with git workflow integration. Implements stories end-to-end with automatic branching (git worktrees), commits, linting, and PR creation. Uses standard git worktree commands for story isolation — works with any coding agent. Falls back to stock BMad behavior when git is disabled. Use when user says "/sprint-autopilot-on" or "start autopilot".

Build (or refresh) the Sprintpilot sprint plan at _bmad-output/implementation-artifacts/sprint-plan.yaml. Infers per-epic + cross-epic dependencies from epics.md + architecture.md + sprint-status.yaml, presents the DAG, lets the user curate which stories belong in the active plan, and persists the result. Triggered by /sprintpilot-plan-sprint, by the autopilot when a stale plan is detected, or by `replan_sprint` mid-flight. Replaces the manual `infer-dependencies.js` workflow for end users.

Render the sprint dependency graph from sprint-plan.yaml in a chosen format. Accepts mermaid (default), graphviz, text (topological tree), layers (parallel-eligible groups), or json (raw nodes + edges). Use when you want to visualize or programmatically inspect the DAG without manually calling resolve-dag.js. Optionally narrow to a single epic with an epic argument.

Parallel 5-stream codebase analysis for brownfield projects. Launches Stack Analyzer, Architecture Mapper, Quality Assessor, Concerns Hunter, and Integration Mapper simultaneously. Produces structured, evidence-based analysis optimized for downstream planning agents. Run before bmad-create-architecture or bmad-create-prd on existing codebases. Inspired by GSD map-codebase (https://github.com/gsd-build/get-shit-done).

Synthesize current sprint execution progress with LLM-layered judgment. Reads sprint-plan.yaml, sprint-status.yaml, and the autopilot ledger via `autopilot progress`; highlights stalls, repeated verify failures, retry loops, and stuck phases; suggests the next action (continue, narrow to a specific story, reorder, replan, abort). Use when you want a quick health check between autopilot sessions without scrolling through the raw ledger.

Check for Sprintpilot updates and install the latest version. Use when user says "/sprintpilot-update" or "update sprintpilot" or "check for sprintpilot updates".

Extract architecture from existing code (bottom-up) via 3 parallel agents. Produces BMad Method-compatible architecture document from Component Mapper, Data Flow Tracer, and Pattern Extractor. Use on brownfield projects where no architecture doc exists. Run after sprintpilot-codebase-map.

Disengage autonomous story execution mode with git status report. Reports sprint position, completed work, git branch/PR status, and next steps. Releases the autopilot lock file. Use when user says "/sprint-autopilot-off" or "stop autopilot" or "pause autopilot".

Tech debt, dependency audit, and migration assessment via 3 parallel agents. Runs after sprintpilot-codebase-map. Produces actionable findings with confidence levels, effort estimates, and a prioritized brownfield-assessment.md. Use for brownfield projects before sprint planning.

Full-lifecycle legacy migration planning. 12-step workflow with 4 parallel subagent fan-outs. Takes a brownfield codebase from current stack to target stack. Consumes sprintpilot-codebase-map and sprintpilot-assess outputs. Produces migration-plan.md, migration-epics.md (compatible with BMad Method epics), and migration-tracking.yaml.

Multi-agent research fan-out. Launch parallel research agents for technical, domain, and market topics simultaneously. Each agent uses WebSearch/WebFetch for live research. Collects and synthesizes results into a unified research report. Use when you need to research multiple topics quickly.