@openlife/cli 1.7.3

package/dist-templates/squad-template/task-template.md

@@ -0,0 +1,36 @@
+# {{TASK_NAME}}
+
+> Task definition for {{SQUAD_NAME}} squad
+> Owner: {{OWNER_AGENT}}
+
+## Purpose
+
+{{PURPOSE}}
+
+## Inputs
+
+- {{INPUT_1}}
+- {{INPUT_2}}
+
+## Outputs
+
+- {{OUTPUT_1}}
+- {{OUTPUT_2}}
+
+## Procedure
+
+1. {{STEP_1}}
+2. {{STEP_2}}
+3. {{STEP_3}}
+
+## Validation
+
+- {{VALIDATION_1}}
+- {{VALIDATION_2}}
+
+## Notes
+
+{{NOTES}}
+
+---
+*Generated by OpenLife SquadCreator.*

package/dist-templates/workflows/PORTED_WORKFLOWS.md

@@ -0,0 +1,60 @@
+# Ported Workflows — Notes
+
+The four workflows in this directory are **OpenLife-adapted ports** of
+community workflow patterns for story-driven development. They are
+read-only reference material once shipped; OpenLife runtime loads them
+through `CompositeWorkflowProvider`, which also reads
+`.catalog/workflows/` for local overrides.
+
+## What was kept verbatim
+
+- The four-phase shape of `story-development-cycle` (Create → Validate → Implement → QA).
+- The Bootstrap → Discovery → Sharding → Dev Cycle backbone of `greenfield-fullstack`.
+- The 10-phase outline of `brownfield-discovery` (3 data-collection + 3 review + QA gate + 3 finalization).
+- The 5-iteration cap of `qa-loop`.
+- Standard agent slots (`@analyst`, `@pm`, `@architect`, `@ux-design-expert`, `@dev`, `@qa`, `@po`, `@sm`, `@devops`, `@data-engineer`).
+
+## What was removed during the port
+
+| Upstream field/concept | Why removed |
+|---|---|
+| Refs to upstream-specific config files | OpenLife uses `.openlife/` for runtime state; the references would mislead operators. Replaced with `.openlife/config.yaml` etc. |
+| `optional_steps: [brainstorming-session, market-research-prompt, …]` blocks | Carried over as `optional_steps` field on the host step. Upstream surfaces these as guided sub-prompts; OpenLife v1.2 just lists them — execution of the sub-prompts is operator-driven. |
+| Inline `condition: user_wants_ai_generation` with complex expression syntax | OpenLife v1.2 supports only literal boolean flags via run context (`ctx[step.condition] === true`). Anything compound stays out of scope until v1.3 adds an expression evaluator. |
+| Long inline `notes:` blocks repeating reference material | Pruned to operator-actionable guidance only. The KB is reference; the workflow is execution. |
+| Upstream QA-loop auto-decision (`verdict_blocked` → automatic escalate) | OpenLife v1.2 engine does not yet support conditional short-circuit. The loop is unrolled into 5 explicit iterations; escalation runs as the final phase after the loop budget exhausts. Replaced when v1.3 adds `condition: !qa_approved`. |
+
+## What was added (OpenLife-specific extensions)
+
+| Extension | Where | Rationale |
+|---|---|---|
+| `squad: <id>` on `qa-gate` step | story-development-cycle, brownfield-discovery | Lets the gate delegate to the qa-loop squad as a unit, not just `@qa` solo. The upstream schema had no squad slot at the step level. |
+| `idempotent: true` flag | All review-and-fix loop steps | Engine resume after partial-run crash respects this — non-idempotent steps are skipped on resume to avoid double side-effects; idempotent steps may re-execute once. |
+| `creates` paths rooted in `docs/` and `.openlife/` | All workflows | Aligns with OpenLife's runtime/state layering. |
+
+## Validation
+
+All four files parse clean against `WorkflowSchema` via
+`openlife workflow validate <file>`. Verified by Story 4.4 AC #1.
+
+```bash
+openlife workflow list
+openlife workflow validate dist-templates/workflows/story-development-cycle.yaml
+openlife workflow validate dist-templates/workflows/greenfield-fullstack.yaml
+openlife workflow validate dist-templates/workflows/brownfield-discovery.yaml
+openlife workflow validate dist-templates/workflows/qa-loop.yaml
+```
+
+## Extension contract
+
+Operators may add their own workflows under:
+
+1. `dist-templates/workflows/<id>.yaml` — ships with the npm package (preferred for community-distributed templates)
+2. `.catalog/workflows/<id>.yaml` — local override / project-specific
+
+`CompositeWorkflowProvider` reads from both, with the local catalog taking
+precedence when an id collides.
+
+> Reference: `WorkflowSchema.ts` for the strict schema and stable error codes;
+> `WorkflowEngine.ts` for execution semantics including elicit pause, resume,
+> and abort.

package/dist-templates/workflows/brownfield-discovery.yaml

@@ -0,0 +1,137 @@
+workflow:
+  id: brownfield-discovery
+  name: Brownfield Technical Debt Discovery
+  description: >-
+    Ten-phase technical-debt assessment for existing codebases. Three data-
+    collection phases feed three review phases feed three finalization phases,
+    gated by a QA review at Phase 7. Output: epic + stories ready for the
+    development cycle.
+  type: brownfield
+  version: "1.0"
+
+  metadata:
+    elicit: false
+    confirmation_required: true
+
+  phases:
+    - phase_1: System Architecture
+    - phase_2: Schema (if DB exists)
+    - phase_3: Frontend Spec
+    - phase_4: Draft Assessment
+    - phase_5: DB Specialist Review
+    - phase_6: UX Specialist Review
+    - phase_7: QA Gate
+    - phase_8: Final Assessment
+    - phase_9: Executive Report
+    - phase_10: Epic + Stories
+
+  sequence:
+    - phase: 1
+      name: System Architecture
+    - id: arch-system-architecture
+      agent: architect
+      action: document-system-architecture
+      creates:
+        - docs/audit/system-architecture.md
+      duration_estimate: "1-2 days"
+
+    - phase: 2
+      name: Schema (skip if no DB)
+    - id: data-schema-audit
+      agent: data-engineer
+      action: audit-schema
+      creates:
+        - docs/audit/SCHEMA.md
+        - docs/audit/DB-AUDIT.md
+      optional: true
+      condition: db_exists
+      duration_estimate: "1 day"
+
+    - phase: 3
+      name: Frontend Spec
+    - id: ux-frontend-spec
+      agent: ux-design-expert
+      action: document-frontend
+      creates:
+        - docs/audit/frontend-spec.md
+      duration_estimate: "1 day"
+
+    - phase: 4
+      name: Draft Assessment
+    - id: arch-draft-assessment
+      agent: architect
+      action: draft-technical-debt
+      creates:
+        - docs/audit/technical-debt-DRAFT.md
+      requires: arch-system-architecture
+      duration_estimate: "1-2 days"
+
+    - phase: 5
+      name: DB Specialist Review
+    - id: data-specialist-review
+      agent: data-engineer
+      action: review-db
+      creates:
+        - docs/audit/db-specialist-review.md
+      requires: arch-draft-assessment
+      optional: true
+      condition: db_exists
+      duration_estimate: "1 day"
+
+    - phase: 6
+      name: UX Specialist Review
+    - id: ux-specialist-review
+      agent: ux-design-expert
+      action: review-ux
+      creates:
+        - docs/audit/ux-specialist-review.md
+      requires: arch-draft-assessment
+      duration_estimate: "1 day"
+
+    - phase: 7
+      name: QA Gate
+    - id: qa-gate
+      squad: qa-loop
+      action: qa-gate
+      creates:
+        - docs/audit/qa-review.md
+      requires: arch-draft-assessment
+      duration_estimate: "1 day"
+      notes: |
+        Gate decision APPROVED or NEEDS WORK. On NEEDS WORK, loop back to
+        arch-draft-assessment (manual re-trigger; v1.2 engine does not yet
+        support automatic phase loops — that arrives with conditional
+        expressions in v1.3).
+
+    - phase: 8
+      name: Final Assessment
+    - id: arch-final-assessment
+      agent: architect
+      action: finalize-technical-debt
+      creates:
+        - docs/audit/technical-debt-assessment.md
+      requires: qa-gate
+      duration_estimate: "1 day"
+
+    - phase: 9
+      name: Executive Report
+    - id: analyst-executive-report
+      agent: analyst
+      action: write-executive-report
+      creates:
+        - docs/audit/TECHNICAL-DEBT-REPORT.md
+      requires: arch-final-assessment
+      duration_estimate: "0.5 day"
+
+    - phase: 10
+      name: Epic + Stories
+    - id: pm-create-epic-and-stories
+      agent: pm
+      action: create-epic-and-stories
+      creates:
+        - docs/stories/epic-brownfield-debt/
+      requires: arch-final-assessment
+      duration_estimate: "0.5-1 day"
+      notes: |
+        Epic + initial story set ready for `openlife workflow run
+        story-development-cycle`.

package/dist-templates/workflows/greenfield-fullstack.yaml

@@ -0,0 +1,132 @@
+workflow:
+  id: greenfield-fullstack
+  name: Greenfield Full-Stack Application Development
+  description: >-
+    End-to-end workflow for building a new full-stack application from concept
+    to shippable stories. Bootstrap → Discovery → Sharding → Development Cycle.
+    Each story produced in the Sharding phase can then be driven through
+    story-development-cycle.
+  type: greenfield
+  version: "1.0"
+  project_types:
+    - web-app
+    - saas
+    - enterprise-app
+    - prototype
+    - mvp
+
+  metadata:
+    elicit: true
+    confirmation_required: true
+
+  phases:
+    - phase_0: Environment Bootstrap
+    - phase_1: Discovery & Planning
+    - phase_2: Document Sharding
+    - phase_3: Development Cycle
+
+  sequence:
+    - phase: 0
+      name: Environment Bootstrap
+      description: Setup tools, repo, CI before any planning starts
+
+    - id: devops-environment-bootstrap
+      agent: devops
+      action: environment_bootstrap
+      task: environment-bootstrap.md
+      creates:
+        - .openlife/config.yaml
+        - .openlife/environment-report.json
+        - .gitignore
+        - README.md
+        - package.json
+      duration_estimate: "15-30 min"
+      idempotent: true
+      notes: |
+        Verifies/installs CLIs (git, gh, node).
+        Authenticates to GitHub.
+        Creates local repo + GitHub remote.
+        Re-run if switching machines or team members join.
+
+    - phase: 1
+      name: Discovery & Planning
+      description: Create all planning artifacts (brief, PRD, spec, architecture)
+
+    - id: analyst-project-brief
+      agent: analyst
+      action: create-project-brief
+      task: create-project-brief.md
+      creates:
+        - docs/project-brief.md
+      requires: devops-environment-bootstrap
+      duration_estimate: "30-60 min"
+      optional_steps:
+        - brainstorming-session
+        - market-research-prompt
+
+    - id: pm-create-prd
+      agent: pm
+      action: create-prd
+      task: create-prd.md
+      creates:
+        - docs/prd.md
+      requires: analyst-project-brief
+      duration_estimate: "30-60 min"
+
+    - id: ux-create-frontend-spec
+      agent: ux-design-expert
+      action: create-frontend-spec
+      task: create-front-end-spec.md
+      creates:
+        - docs/front-end-spec.md
+      requires: pm-create-prd
+      duration_estimate: "30-45 min"
+
+    - id: architect-create-architecture
+      agent: architect
+      action: create-fullstack-architecture
+      task: create-fullstack-architecture.md
+      creates:
+        - docs/fullstack-architecture.md
+      requires: pm-create-prd
+      duration_estimate: "30-60 min"
+      notes: |
+        Reads PRD + front-end spec. May suggest PRD changes — those
+        feed back via the optional pm-update-prd step below.
+
+    - id: pm-update-prd
+      agent: pm
+      action: update-prd
+      task: update-prd.md
+      updates:
+        - docs/prd.md
+      requires: architect-create-architecture
+      condition: architecture_suggests_prd_changes
+      optional: true
+      duration_estimate: "15-30 min"
+
+    - phase: 2
+      name: Document Sharding
+      description: PO shards PRD + architecture into per-epic context bundles
+
+    - id: po-shard-docs
+      agent: po
+      action: shard-doc
+      task: shard-doc.md
+      creates:
+        - docs/prd-shards/
+        - docs/architecture-shards/
+      requires: architect-create-architecture
+      duration_estimate: "15-30 min"
+
+    - phase: 3
+      name: Development Cycle
+      description: Each story runs through story-development-cycle. Marker only.
+
+    - id: handoff-to-sdc
+      agent: sm
+      action: handoff-to-sdc
+      requires: po-shard-docs
+      notes: |
+        Marker step. The next runner picks the first story from the
+        sharded epic and triggers `openlife workflow run story-development-cycle`.

package/dist-templates/workflows/qa-loop.yaml

@@ -0,0 +1,125 @@
+workflow:
+  id: qa-loop
+  name: QA Iterative Review Loop
+  description: >-
+    Automated review-fix-review cycle for a story that hit CONCERNS or FAIL on
+    its first qa-gate. Hard-capped at 5 iterations to prevent runaway loops;
+    after that, escalation is automatic. Each iteration runs
+    review → verdict → fix → re-review.
+  type: qa-loop
+  version: "1.0"
+
+  metadata:
+    elicit: false
+    confirmation_required: false
+
+  phases:
+    - phase_1: Initial QA Review
+    - phase_2: Fix + Re-review (loop)
+    - phase_3: Escalation gate
+
+  sequence:
+    - phase: 1
+      name: Initial QA Review
+
+    - id: qa-initial-review
+      agent: qa
+      action: review-story
+      duration_estimate: "20-40 min"
+      notes: |
+        Reads the story file and produces a structured verdict:
+        APPROVE → workflow exits via qa-loop-approved (skip remaining).
+        REJECT → continue to dev-fix-1.
+        BLOCKED → escalate-immediately.
+
+    - phase: 2
+      name: Fix + Re-review (loop iterations; engine v1.2 unrolls explicitly)
+
+    # Iteration 1
+    - id: dev-fix-1
+      agent: dev
+      action: apply-qa-feedback
+      requires: qa-initial-review
+      duration_estimate: "1-3 hours"
+      idempotent: true
+
+    - id: qa-review-1
+      agent: qa
+      action: review-story
+      requires: dev-fix-1
+      duration_estimate: "20-40 min"
+      idempotent: true
+
+    # Iteration 2
+    - id: dev-fix-2
+      agent: dev
+      action: apply-qa-feedback
+      requires: qa-review-1
+      duration_estimate: "1-3 hours"
+      idempotent: true
+
+    - id: qa-review-2
+      agent: qa
+      action: review-story
+      requires: dev-fix-2
+      duration_estimate: "20-40 min"
+      idempotent: true
+
+    # Iteration 3
+    - id: dev-fix-3
+      agent: dev
+      action: apply-qa-feedback
+      requires: qa-review-2
+      duration_estimate: "1-3 hours"
+      idempotent: true
+
+    - id: qa-review-3
+      agent: qa
+      action: review-story
+      requires: dev-fix-3
+      duration_estimate: "20-40 min"
+      idempotent: true
+
+    # Iteration 4
+    - id: dev-fix-4
+      agent: dev
+      action: apply-qa-feedback
+      requires: qa-review-3
+      duration_estimate: "1-3 hours"
+      idempotent: true
+
+    - id: qa-review-4
+      agent: qa
+      action: review-story
+      requires: dev-fix-4
+      duration_estimate: "20-40 min"
+      idempotent: true
+
+    # Iteration 5 (final budget)
+    - id: dev-fix-5
+      agent: dev
+      action: apply-qa-feedback
+      requires: qa-review-4
+      duration_estimate: "1-3 hours"
+      idempotent: true
+
+    - id: qa-review-5
+      agent: qa
+      action: review-story
+      requires: dev-fix-5
+      duration_estimate: "20-40 min"
+      idempotent: true
+
+    - phase: 3
+      name: Escalation gate (max_iterations_reached)
+
+    - id: escalate-loop
+      agent: pm
+      action: escalate-qa-loop
+      requires: qa-review-5
+      duration_estimate: "10-20 min"
+      notes: |
+        Reached after 5 unsuccessful iterations. Engineering manager
+        and product owner triage manually. Loop closes here in v1.2.
+        Future: short-circuit by `condition: !qa_approved` on each
+        review step once conditional expressions land in v1.3.

package/dist-templates/workflows/story-development-cycle.yaml

@@ -0,0 +1,80 @@
+workflow:
+  id: story-development-cycle
+  name: Story Development Cycle (SDC)
+  description: >-
+    Four-phase workflow for shipping a single story end-to-end: @sm creates,
+    @po validates, @dev implements, @qa gates. The primary workflow for all
+    OpenLife story work, with squad-level dispatch at each phase.
+  type: story-cycle
+  version: "1.0"
+
+  metadata:
+    elicit: true
+    confirmation_required: false
+
+  phases:
+    - phase_1: Create
+    - phase_2: Validate
+    - phase_3: Implement
+    - phase_4: QA Gate
+
+  sequence:
+    - phase: 1
+      name: Create
+      description: Scrum Master drafts a story from the epic context
+
+    - id: sm-draft-story
+      agent: sm
+      action: create-next-story
+      task: create-next-story.md
+      creates:
+        - docs/stories/{epicNum}.{storyNum}.story.md
+      duration_estimate: "15-30 min"
+      notes: |
+        Pulls from sharded PRD + epic context.
+        Output status: Draft. Status field literally `Draft` in the story file.
+
+    - phase: 2
+      name: Validate
+      description: Product Owner runs the 10-point validation checklist
+
+    - id: po-validate-story
+      agent: po
+      action: validate-next-story
+      task: validate-next-story.md
+      requires: sm-draft-story
+      duration_estimate: "10-20 min"
+      idempotent: true
+      notes: |
+        10-point checklist. Decision GO (>=7) or NO-GO.
+        On GO @po MUST update Status: Draft → Ready in the story file.
+
+    - phase: 3
+      name: Implement
+      description: Developer executes the story
+
+    - id: dev-develop-story
+      agent: dev
+      action: develop-story
+      task: dev-develop-story.md
+      requires: po-validate-story
+      duration_estimate: "1-3 days"
+      notes: |
+        Modes: Interactive (default) / YOLO / Pre-Flight.
+        Updates File List + checkboxes as work progresses.
+        CodeRabbit self-healing max 2 iterations on CRITICAL/HIGH.
+        Status: Ready → InProgress → InReview.
+
+    - phase: 4
+      name: QA Gate
+      description: Test Architect runs the 7-quality-check gate
+
+    - id: qa-gate
+      squad: qa-loop
+      action: qa-gate
+      task: qa-gate.md
+      requires: dev-develop-story
+      duration_estimate: "30-60 min"
+      notes: |
+        7 quality checks. Verdict PASS / CONCERNS / FAIL / WAIVED.
+        On PASS status moves InReview → Done; @devops takes git push.

package/docs/CHANGELOG_FEATURE_ROLLOUT_DESIGNMD.md

@@ -0,0 +1,43 @@
+# OpenLife Feature Rollout Changelog (Dual Mode + Reversa + DesignMD)
+
+## Completed in this cycle
+
+### Core execution
+- Dual mode persisted in mission lifecycle (`task` default, `service` explicit)
+- Formal job lifecycle with events (`enqueued/claimed/started/completed/failed/blocked`)
+- Destructive guardrails enforced (delete/remove/erase requires explicit consent)
+
+### Service operations
+- CLI operations: `service status/pause/resume/events`
+- Task introspection: `task status`
+- Budget hard-stop -> service paused + event log
+
+### Workspace foundations
+- Workspace-aware artifacts path under `.artifacts/workspaces/<workspaceId>/...`
+- Service state/events now namespaced by workspace
+
+### Runtime and orchestration
+- Runtime registry probe/list baseline
+- Teammate board baseline (owner/status/blockers/comments)
+- Learning loop baseline (governed skill candidates)
+
+### Reversa and DesignMD
+- Reversa state now supports mode metadata (`default` | `designmd`)
+- New mode setter in Reversa (`setMode`)
+- New `DesignMdMode` manager to apply/design profile and write root `DESIGN.md`
+- CLI surface:
+  - `reversa mode --set <default|designmd> --profile <id>`
+  - `designmd status`
+  - `designmd apply <profileId> <source> <title> <designPath>`
+  - `aiobuilder mode --set <default|designmd> --profile <id>`
+
+## Validation status
+- TypeScript build: passing
+- Automated tests passing for dual mode, guardrails, lifecycle, runtime, reversa-lite, service CLI, teammate/learning
+
+## Next integration step (pending your references/models)
+1. Add importer for Awesome DESIGN.md catalog profile manifests
+2. Add profile templates bundle under `design/profiles/`
+3. Wire Reversa generation phase to enforce active DesignMD profile tokens
+4. Wire AIOBUILDER scaffolding prompts to DesignMD profile context
+5. Add regression tests for DesignMD profile switching and output consistency

package/docs/EXTERNAL_SOURCES_AND_SECURITY_GUARD.md

@@ -0,0 +1,33 @@
+# OpenLife External Sources & Security Guard
+
+## New source catalog commands
+- `openlife sources list`
+- `openlife sources guard-check <url>`
+- `openlife sources scaffold <type> <id> --notes "..."`
+
+## Autonomous creation baselines (local)
+- `openlife agents create <id> --role <role> --notes "..."`
+- `openlife squads create <id> --domain <domain> --notes "..."`
+- `openlife skills create <id> --notes "..."`
+- `openlife mcp create <id> --transport <stdio|http> --entry "..."`
+
+Created artifacts:
+- `.catalog/agents/<id>/AGENT.md`
+- `.catalog/squads/<id>/SQUAD.md`
+- `.catalog/skills/<id>/SKILL.md`
+- `.catalog/mcps/<id>/mcp.json`
+
+## Default reference sources configured
+- https://skills.sh/
+- https://clawhub.ai/
+- https://mcpmarket.com/
+- https://mcpservers.org/
+- https://github.com/ (import-allowed with guard)
+
+## Cybersecurity guard (mandatory pre-download)
+1. Validate source URL trust.
+2. Scan file list / extracted directory for blocked patterns.
+3. Reject package when blocked files are present.
+
+Active enforcement:
+- `designmd import` runs guard before import and blocks when malicious patterns exist.