@openlife/cli 1.8.2 → 1.9.3

package/dist-templates/gemini-cli/commands/openlife/flow/qa-loop.md

@@ -0,0 +1,20 @@
+---
+description: QA Loop: iterative review-fix cycle (max 5 iterations) between Sentinel and Builder
+argument-hint: "[--dry-run] [--vars key=value]"
+allowed-tools:
+  - Read
+  - Bash(openlife:*)
+  - Grep
+  - Glob
+  - Agent
+  - AskUserQuestion
+---
+
+Run `openlife flow run qa-loop $ARGUMENTS` and walk the user through the workflow as it executes.
+
+- The workflow YAML is at `dist-templates/workflows/qa-loop.yaml` (or `.openlife/method/workflows/qa-loop.yaml` if locally overridden).
+- Each phase invokes one or more OpenLife method agents.
+- On any failure: surface the failing step + which agent is responsible, then offer to escalate to `@openlife-maestro`.
+- `--dry-run` prints the phase plan without executing.
+
+Refer the user to the persona of the active phase when they ask "who is doing this?".

package/dist-templates/gemini-cli/commands/openlife/flow/release.md

@@ -0,0 +1,20 @@
+---
+description: Continuous Deployment: release pipeline driven by Vortex (PR → merge → tag → publish)
+argument-hint: "[--dry-run] [--vars key=value]"
+allowed-tools:
+  - Read
+  - Bash(openlife:*)
+  - Grep
+  - Glob
+  - Agent
+  - AskUserQuestion
+---
+
+Run `openlife flow run continuous-deployment $ARGUMENTS` and walk the user through the workflow as it executes.
+
+- The workflow YAML is at `dist-templates/workflows/continuous-deployment.yaml` (or `.openlife/method/workflows/continuous-deployment.yaml` if locally overridden).
+- Each phase invokes one or more OpenLife method agents.
+- On any failure: surface the failing step + which agent is responsible, then offer to escalate to `@openlife-maestro`.
+- `--dry-run` prints the phase plan without executing.
+
+Refer the user to the persona of the active phase when they ask "who is doing this?".

package/dist-templates/gemini-cli/commands/openlife/flow/spec-pipeline.md

@@ -0,0 +1,20 @@
+---
+description: Spec Pipeline: 6-phase gather → assess → research → write → critique → plan
+argument-hint: "[--dry-run] [--vars key=value]"
+allowed-tools:
+  - Read
+  - Bash(openlife:*)
+  - Grep
+  - Glob
+  - Agent
+  - AskUserQuestion
+---
+
+Run `openlife flow run spec-pipeline $ARGUMENTS` and walk the user through the workflow as it executes.
+
+- The workflow YAML is at `dist-templates/workflows/spec-pipeline.yaml` (or `.openlife/method/workflows/spec-pipeline.yaml` if locally overridden).
+- Each phase invokes one or more OpenLife method agents.
+- On any failure: surface the failing step + which agent is responsible, then offer to escalate to `@openlife-maestro`.
+- `--dry-run` prints the phase plan without executing.
+
+Refer the user to the persona of the active phase when they ask "who is doing this?".

package/dist-templates/gemini-cli/commands/openlife/flow/story-cycle.md

@@ -0,0 +1,20 @@
+---
+description: Story Development Cycle: 4-phase Create → Validate → Implement → QA
+argument-hint: "[--dry-run] [--vars key=value]"
+allowed-tools:
+  - Read
+  - Bash(openlife:*)
+  - Grep
+  - Glob
+  - Agent
+  - AskUserQuestion
+---
+
+Run `openlife flow run story-development-cycle $ARGUMENTS` and walk the user through the workflow as it executes.
+
+- The workflow YAML is at `dist-templates/workflows/story-development-cycle.yaml` (or `.openlife/method/workflows/story-development-cycle.yaml` if locally overridden).
+- Each phase invokes one or more OpenLife method agents.
+- On any failure: surface the failing step + which agent is responsible, then offer to escalate to `@openlife-maestro`.
+- `--dry-run` prints the phase plan without executing.
+
+Refer the user to the persona of the active phase when they ask "who is doing this?".

package/dist-templates/gemini-cli/commands/openlife/health.md

@@ -0,0 +1,14 @@
+---
+description: Extended health check — combines `doctor` with runtime diagnostics from Maestro
+allowed-tools:
+  - Read
+  - Write
+  - Edit
+  - Bash(openlife:*)
+  - Grep
+  - Glob
+  - Agent
+  - AskUserQuestion
+---
+
+Run `openlife system doctor` first, then activate `@openlife-maestro` and run `*health` to check cross-agent integrity (catalog completeness, missing handoff artifacts, draft components pending promotion).

package/dist-templates/gemini-cli/commands/openlife/plan.md

@@ -0,0 +1,14 @@
+---
+description: Run the spec pipeline — gather requirements, assess complexity, write executable spec
+allowed-tools:
+  - Read
+  - Write
+  - Edit
+  - Bash(openlife:*)
+  - Grep
+  - Glob
+  - Agent
+  - AskUserQuestion
+---
+
+Run `openlife flow run spec-pipeline "$ARGUMENTS"`. The 6-phase pipeline: gather → assess → research → write → critique → plan. Walk the user through each phase's output.

package/dist-templates/gemini-cli/commands/openlife/review.md

@@ -0,0 +1,14 @@
+---
+description: Run the QA gate on a story (Sentinel) — 7-check verdict: PASS / CONCERNS / FAIL / WAIVED
+allowed-tools:
+  - Read
+  - Write
+  - Edit
+  - Bash(openlife:*)
+  - Grep
+  - Glob
+  - Agent
+  - AskUserQuestion
+---
+
+Activate `@openlife-sentinel` (reads `.openlife/method/agents/sentinel.md`) and run `*qa-gate "$ARGUMENTS"`. Pass the story id or the file path as the argument. Report the verdict + structured findings.

package/dist-templates/gemini-cli/commands/openlife/ship.md

@@ -0,0 +1,14 @@
+---
+description: Run the continuous-deployment workflow — release pipeline driven by Vortex
+allowed-tools:
+  - Read
+  - Write
+  - Edit
+  - Bash(openlife:*)
+  - Grep
+  - Glob
+  - Agent
+  - AskUserQuestion
+---
+
+Run `openlife flow run continuous-deployment "$ARGUMENTS"`. Vortex drives: pre-release QA, PR open, CI wait, merge, version bump, tag, publish. Maestro logs the release event at the end.

package/dist-templates/gemini-cli/commands/openlife/start.md

@@ -0,0 +1,25 @@
+---
+description: Bootstrap or resume work — reads .openlife/project.json mode and routes to greenfield or brownfield flow
+allowed-tools:
+  - Read
+  - Write
+  - Edit
+  - Bash(openlife:*)
+  - Grep
+  - Glob
+  - Agent
+  - AskUserQuestion
+---
+
+Detect the project mode:
+
+1. Read `.openlife/project.json` if it exists. Use its `mode` field (`greenfield` / `brownfield` / `not-applicable`).
+2. If missing, ask the user via AskUserQuestion:
+   - "Is this a brand new project (greenfield) or existing codebase (brownfield)?"
+3. Based on the answer, recommend a workflow:
+   - greenfield + fullstack → `openlife flow run greenfield-fullstack`
+   - greenfield + service → `openlife flow run greenfield-service`
+   - greenfield + ui → `openlife flow run greenfield-ui`
+   - brownfield + first time → `openlife flow run brownfield-discovery`
+   - brownfield + already discovered → ask sub-mode (fullstack/service/ui)
+4. If mode was just set, persist via `openlife project-mode set <mode>`.

package/dist-templates/gemini-cli/commands/openlife/status.md

@@ -1,14 +1,14 @@
 ---
 description: Show OpenLife system status — installed profile, host, catalog counts, daemon state
-allowed-tools: Bash(openlife:*)
+allowed-tools:
+  - Read
+  - Write
+  - Edit
+  - Bash(openlife:*)
+  - Grep
+  - Glob
+  - Agent
+  - AskUserQuestion
 ---
 
-Run `openlife system status` and summarize the output for the user. Highlight:
-
-- **Profile** in use (framework vs autonomous)
-- **Host** target (claude-code / gemini-cli / codex)
-- **Catalog counts** (agents, skills, squads, mcps)
-- **Daemon state** if profile is autonomous
-- Any **doctor warnings** that need attention
-
-If the command fails, surface the exit code and stderr — don't hide the failure.
+Run `openlife status --json` and present a tight summary of: active profile, host CLIs installed, catalog counts (agents/squads/skills), daemon heartbeat freshness, telegram allowed user.

package/dist-templates/gemini-cli/commands/openlife/story.md

@@ -0,0 +1,18 @@
+---
+description: Create the next story from an epic (Conductor) or validate a draft (Steward)
+allowed-tools:
+  - Read
+  - Write
+  - Edit
+  - Bash(openlife:*)
+  - Grep
+  - Glob
+  - Agent
+  - AskUserQuestion
+---
+
+Determine intent from $ARGUMENTS:
+
+- If the user wants to CREATE a story → activate `@openlife-conductor` (reads `.openlife/method/agents/conductor.md`) and run `*create-next-story`.
+- If the user wants to VALIDATE a draft → activate `@openlife-steward` and run `*validate-story`.
+- If unclear, ask via AskUserQuestion which action to take.

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

@@ -0,0 +1,131 @@
+workflow:
+  id: brownfield-fullstack
+  name: Brownfield Full-Stack Enhancement
+  description: >-
+    Enhance an existing full-stack application. Assumes brownfield-discovery
+    has already produced the technical-debt-assessment.md and frontend-spec.md.
+    This workflow takes a specific enhancement request and drives it through
+    architecture review → impact analysis → story creation → SDC.
+  type: brownfield
+  version: "1.0"
+  framework: openlife-method
+  project_types:
+    - existing-fullstack
+    - legacy-modernization
+    - feature-addition
+
+  metadata:
+    elicit: true
+    confirmation_required: true
+    requires_prior_workflow: brownfield-discovery
+
+  phases:
+    - phase_0: Context Load
+    - phase_1: Impact Analysis
+    - phase_2: Story Slicing
+    - phase_3: Development Cycle
+
+  success_criteria:
+    - id: impact-on-existing-code-schema-ui-is-doc
+      description: "Impact on existing code/schema/UI is documented"
+    - id: no-regression-on-existing-test-suite
+      description: "No regression on existing test suite"
+    - id: schema-migrations-are-reversible
+      description: "Schema migrations are reversible"
+    - id: performance-baseline-maintained-or-impro
+      description: "Performance baseline maintained or improved"
+
+  failure_handling:
+    on_phase_failure: escalate_to_maestro
+    on_regression_detected: rollback_via_vortex
+
+  tools:
+    allowed:
+      - terminal
+      - git
+      - schema-migration
+      - browser-testing
+    restricted:
+      - drop-table
+      - delete-component
+
+  sequence:
+    - phase: 0
+      name: Context Load
+
+    - id: load-context
+      agent: openlife-maestro
+      action: route
+      creates:
+        - .openlife/brownfield-context.json
+      notes: |
+        Load technical-debt-assessment.md + frontend-spec.md + SCHEMA.md.
+        Confirm prior brownfield-discovery completed. If not, halt and route
+        user to brownfield-discovery workflow.
+
+    - phase: 1
+      name: Impact Analysis
+
+    - id: impact-arch
+      agent: openlife-atlas
+      action: analyze_impact
+      requires: load-context
+      creates:
+        - docs/impact/architecture.md
+      duration_estimate: "1-2 hours"
+      notes: What architectural surfaces are touched? What ADRs need updating?
+
+    - id: impact-data
+      agent: openlife-mesh
+      action: db_schema_audit
+      requires: impact-arch
+      creates:
+        - docs/impact/schema-delta.md
+      optional: true
+      notes: Only if enhancement touches data layer.
+
+    - id: impact-ui
+      agent: openlife-prism
+      action: ux_ds_scan_artifact
+      requires: impact-arch
+      creates:
+        - docs/impact/ui-delta.md
+      optional: true
+      notes: Only if enhancement touches UI.
+
+    - phase: 2
+      name: Story Slicing
+
+    - id: brownfield-epic
+      agent: openlife-genesis
+      action: brownfield_create_epic
+      requires: impact-arch
+      creates:
+        - docs/epics/brownfield-*.md
+      elicit: true
+      notes: Epic explicitly references the brownfield context.
+
+    - id: brownfield-stories
+      agent: openlife-conductor
+      action: brownfield_create_story
+      requires: brownfield-epic
+      creates:
+        - docs/stories/*.story.md
+      notes: Stories include "what NOT to break" in their scope/AC.
+
+    - phase: 3
+      name: Development Cycle
+
+    - id: story-loop
+      agent: openlife-conductor
+      action: story_development_cycle
+      requires: brownfield-stories
+      notes: |
+        Each story flows through story-development-cycle.
+        Sentinel's QA gate includes regression-suite verification.
+        Vortex's push includes a feature-flag fallback when applicable.
+
+  handoff_prompts:
+    phase_0_to_1: "Context loaded. Atlas, run impact analysis."
+    phase_1_to_2: "Impact mapped. Genesis, draft the brownfield epic."
+    phase_2_to_3: "Stories sliced. Conductor, drive through SDC."

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

@@ -0,0 +1,111 @@
+workflow:
+  id: brownfield-service
+  name: Brownfield Service / API Modification
+  description: >-
+    Modify an existing service or API. No UI phase. Focus on architectural
+    impact, data-layer compatibility (RLS, migrations, query plans), and
+    integration-pattern preservation.
+  type: brownfield
+  version: "1.0"
+  framework: openlife-method
+  project_types:
+    - existing-api
+    - existing-microservice
+    - existing-worker
+
+  metadata:
+    elicit: true
+    requires_prior_workflow: brownfield-discovery
+
+  phases:
+    - phase_0: Context Load
+    - phase_1: Service Impact
+    - phase_2: Story Slicing
+    - phase_3: Development Cycle
+
+  success_criteria:
+    - id: api-contract-is-preserved-or-versioned-n
+      description: "API contract is preserved OR versioned (no silent break)"
+    - id: integration-tests-cover-the-changed-endp
+      description: "Integration tests cover the changed endpoint(s)"
+    - id: database-migrations-have-rollback-script
+      description: "Database migrations have rollback scripts"
+    - id: performance-regression-10-on-hot-paths
+      description: "Performance regression < 10% on hot paths"
+
+  failure_handling:
+    on_phase_failure: escalate_to_maestro
+    on_regression_detected: rollback_via_vortex
+
+  sequence:
+    - phase: 0
+      name: Context Load
+
+    - id: load-context
+      agent: openlife-maestro
+      action: route
+      creates:
+        - .openlife/brownfield-context.json
+
+    - phase: 1
+      name: Service Impact
+
+    - id: impact-arch
+      agent: openlife-atlas
+      action: analyze_impact
+      requires: load-context
+      creates:
+        - docs/impact/service-architecture.md
+      notes: Which endpoints, which integration patterns, which contracts.
+
+    - id: impact-schema
+      agent: openlife-mesh
+      action: db_schema_audit
+      requires: impact-arch
+      creates:
+        - docs/impact/schema-delta.md
+      notes: Schema changes, indexes affected, query plan delta.
+
+    - id: api-contract-check
+      agent: openlife-atlas
+      action: analyze_cross_artifact
+      requires: impact-arch
+      creates:
+        - docs/impact/api-contract-delta.md
+      notes: |
+        Detect breaking API changes. If breaking, REQUIRE either versioning
+        strategy or deprecation timeline before proceeding.
+
+    - phase: 2
+      name: Story Slicing
+
+    - id: brownfield-epic
+      agent: openlife-genesis
+      action: brownfield_create_epic
+      requires: api-contract-check
+      creates:
+        - docs/epics/brownfield-service-*.md
+
+    - id: brownfield-stories
+      agent: openlife-conductor
+      action: brownfield_create_story
+      requires: brownfield-epic
+      creates:
+        - docs/stories/*.story.md
+
+    - phase: 3
+      name: Development Cycle
+
+    - id: story-loop
+      agent: openlife-conductor
+      action: story_development_cycle
+      requires: brownfield-stories
+      notes: |
+        Sentinel's QA gate emphasizes integration tests + regression suite.
+        Mesh runs migrations in dry-run mode first.
+        Vortex's release uses canary / blue-green when infrastructure supports it.
+
+  handoff_prompts:
+    phase_0_to_1: "Context loaded. Atlas, scope the service impact."
+    phase_1_to_2: "Impact analyzed. Genesis, draft the brownfield epic."
+    phase_2_to_3: "Stories ready. Conductor, drive through SDC."

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

@@ -0,0 +1,115 @@
+workflow:
+  id: brownfield-ui
+  name: Brownfield UI Refactor / Enhancement
+  description: >-
+    Modify an existing UI. Focus on design-system compliance, accessibility
+    regression, and component-tree impact. Assumes brownfield-discovery
+    produced frontend-spec.md.
+  type: brownfield
+  version: "1.0"
+  framework: openlife-method
+  project_types:
+    - existing-spa
+    - existing-web-app
+    - legacy-ui-modernization
+
+  metadata:
+    elicit: true
+    requires_prior_workflow: brownfield-discovery
+
+  phases:
+    - phase_0: Context Load
+    - phase_1: UI Impact
+    - phase_2: Design System Reconciliation
+    - phase_3: Story Slicing
+    - phase_4: Development Cycle
+
+  success_criteria:
+    - id: existing-user-flows-still-pass-e2e-suite
+      description: "Existing user flows still pass e2e suite"
+    - id: design-system-tokens-not-violated-or-vio
+      description: "Design system tokens not violated (or violations are tracked)"
+    - id: accessibility-regression-check-passes
+      description: "Accessibility regression check passes"
+    - id: bundle-size-delta-within-budget
+      description: "Bundle size delta within budget"
+
+  failure_handling:
+    on_phase_failure: escalate_to_maestro
+
+  sequence:
+    - phase: 0
+      name: Context Load
+
+    - id: load-context
+      agent: openlife-maestro
+      action: route
+      creates:
+        - .openlife/brownfield-context.json
+
+    - phase: 1
+      name: UI Impact
+
+    - id: ds-scan
+      agent: openlife-prism
+      action: ux_ds_scan_artifact
+      requires: load-context
+      creates:
+        - docs/impact/design-system-delta.md
+      notes: Detect existing drift; reconcile before adding new.
+
+    - id: a11y-baseline
+      agent: openlife-prism
+      action: ux_accessibility_audit
+      requires: ds-scan
+      creates:
+        - docs/impact/accessibility-baseline.md
+
+    - id: component-impact
+      agent: openlife-atlas
+      action: analyze_impact
+      requires: ds-scan
+      creates:
+        - docs/impact/component-tree-delta.md
+
+    - phase: 2
+      name: Design System Reconciliation
+
+    - id: reconcile-tokens
+      agent: openlife-prism
+      action: ux_design_tokens_extract
+      requires: ds-scan
+      creates:
+        - design-system/tokens.json
+      optional: true
+      notes: Only if drift is significant enough to warrant a tokens update.
+
+    - phase: 3
+      name: Story Slicing
+
+    - id: brownfield-epic
+      agent: openlife-genesis
+      action: brownfield_create_epic
+      requires: component-impact
+
+    - id: brownfield-stories
+      agent: openlife-conductor
+      action: brownfield_create_story
+      requires: brownfield-epic
+      creates:
+        - docs/stories/*.story.md
+
+    - phase: 4
+      name: Development Cycle
+
+    - id: story-loop
+      agent: openlife-conductor
+      action: story_development_cycle
+      requires: brownfield-stories
+      notes: Sentinel runs a11y + visual-regression checks.
+
+  handoff_prompts:
+    phase_0_to_1: "Context loaded. Prism, scan the UI."
+    phase_1_to_2: "UI scanned. Prism, reconcile tokens if needed."
+    phase_2_to_3: "Reconciliation done. Genesis, draft the epic."
+    phase_3_to_4: "Stories ready. Conductor, drive through SDC."