open-up-for-ai-agents

One-command project setup for OpenUP - interactive initialization wizard

Mark a task as complete, update roadmap, commit changes, and prepare traceability logs

Execute an already-claimed lane's Operations boxes with script/judgment classification — script steps run directly with zero self-brief, judgment steps self-brief and execute. Handles only pick/resume; every other resolve path routes to /openup-next.

Run OpenUP Assess Results at iteration end — check evaluation criteria, demo only completed acceptance-tested work, feed discovered work back, and trigger the milestone review at a phase boundary

Run the phase milestone go/no-go — prepare derived evidence, pause for the human decision via an input-request, and record the milestone (never advance the phase itself)

Begin a new OpenUP iteration with proper phase context and task selection

Run ONE OpenUP delivery cycle — resume the active iteration if one stopped mid-work, else claim the top READY lane, else promote the next pending roadmap task and start it. Always advances; only no-ops when nothing is left to do. The sequential continue-loop.

Initialize and manage Construction phase activities - build the system incrementally

Initialize and manage Elaboration phase activities - establish architecture baseline

Initialize and manage Inception phase activities - define scope, vision, and feasibility

Initialize and manage Transition phase activities - deploy to users

Generate or update architecture documentation from template

Plan iteration based on current state and roadmap

Create or update risk assessment document from template

Produce a REASONS-Canvas task spec from a roadmap line or feature description, ready for developer-role consumption

Generate test cases and test plan from use cases and requirements

Create a use case specification from template

Generate a vision document from template

Transform a high-level use case into detailed scenarios with test cases

Sanctioned pre-iteration mode — think through ideas, investigate problems, sketch options before committing to delivery

Create traceability logs (markdown + JSONL) for the current agent run

Generate iteration plan and roadmap entry for a feature idea

Fast iteration mode for small changes - simplified workflow with minimal overhead

Compute the change-folder dependency DAG and print READY/BLOCKED/collision report for PM intake

Generate iteration retrospective with feedback and action items

Create shared technical vision for team alignment

Back-propagate pure refactors to stale artifacts; classify the diff, refuse behaviour-changes, propose targeted edits for approval (read-only by default)

Dispatch one background subagent per collision-free READY lane, then collect their ≤6-bullet summaries. The caller's interactive session remains free. Requires T-060 heartbeat+reaper and T-059 sentinel output.

Read-only project health check — framework/manifest drift, .openup/state.json integrity, and aggregation of existing --check validators

Create an input request document for asynchronous stakeholder communication

Create a pull request with proper description linking to roadmap task context

Rubric-based readiness assessment before task completion or phase transition

Generate human-readable documentation from code and artifacts

Produce a handoff brief (acceptance criteria, test cases, troubleshooting, open questions) for a change, so the next owner can pick it up cold

Deploy an OpenUP agent team to work on the current iteration

Run a full orchestrated iteration — PM decomposes the goal, delegates to specialist roles, collects outputs, and synthesizes results

Guide Test-Driven Development cycle adapted for AI agents with a pragmatic approach