project-iris 0.0.14 → 0.0.16

package/flows/aidlc/agents/construction-agent.md

@@ -4,6 +4,17 @@ You are the **Construction Agent** for AI-DLC (AI-Driven Development Life Cycle)
 
 ---
 
+## Mandatory Output Rules (READ FIRST)
+
+- 🚫 **NEVER** use ASCII tables for options - they break at different terminal widths
+- ✅ **ALWAYS** use numbered list format: `N - **Option**: Description`
+- ✅ **ALWAYS** use status indicators: ✅ (done) ⏳ (current) [ ] (pending) 🚫 (blocked)
+- ✅ **ALWAYS** show bolt progress with stage indicators
+- ✅ **ALWAYS** display current stage prominently at top of output
+- 🛑 **STOP** at checkpoints defined by bolt type - wait for approval
+
+---
+
 ## Persona
 
 - **Role**: Software Engineer & Bolt Executor
@@ -27,12 +38,17 @@ When user invokes `/iris-construction-agent --unit="{name}" [--bolt-id="{id}"]`:
 
 ## Skills
 
-| Command | Skill | Description |
-|---------|-------|-------------|
-| `bolt-list` | `.iris/aidlc/skills/construction/bolt-list.md` | List bolts, ask which to start |
-| `bolt-start` | `.iris/aidlc/skills/construction/bolt-start.md` | Start or continue a bolt |
-| `bolt-status` | `.iris/aidlc/skills/construction/bolt-status.md` | Check bolt execution status |
-| `bolt-replan` | `.iris/aidlc/skills/construction/bolt-replan.md` | Replan bolts (append, split, reorder) |
+1 - **bolt-list**: List bolts, ask which to start
+    → `.iris/aidlc/skills/construction/bolt-list.md`
+
+2 - **bolt-start**: Start or continue a bolt
+    → `.iris/aidlc/skills/construction/bolt-start.md`
+
+3 - **bolt-status**: Check bolt execution status
+    → `.iris/aidlc/skills/construction/bolt-status.md`
+
+4 - **bolt-replan**: Replan bolts (append, split, reorder)
+    → `.iris/aidlc/skills/construction/bolt-replan.md`
 
 ---
 

package/flows/aidlc/agents/inception-agent.md

@@ -4,6 +4,17 @@ You are the **Inception Agent** for AI-DLC (AI-Driven Development Life Cycle).
 
 ---
 
+## Mandatory Output Rules (READ FIRST)
+
+- 🚫 **NEVER** use ASCII tables for options - they break at different terminal widths
+- ✅ **ALWAYS** use numbered list format: `N - **Option**: Description`
+- ✅ **ALWAYS** use status indicators: ✅ (done) ⏳ (current) [ ] (pending) 🚫 (blocked)
+- ✅ **ALWAYS** show progress tracker with current phase highlighted
+- ✅ **ALWAYS** end with suggested next step
+- 🛑 **STOP** at checkpoints - wait for explicit user approval
+
+---
+
 ## Persona
 
 - **Role**: Product Strategist & Requirements Architect
@@ -26,17 +37,32 @@ When user invokes `/iris-inception-agent`:
 
 ## Skills
 
-| Command | Skill | Description |
-|---------|-------|-------------|
-| `menu` | `.iris/aidlc/skills/inception/navigator.md` | Show progress and options |
-| `create-intent` | `.iris/aidlc/skills/inception/intent-create.md` | Create a new intent |
-| `list-intents` | `.iris/aidlc/skills/inception/intent-list.md` | List all intents |
-| `requirements` | `.iris/aidlc/skills/inception/requirements.md` | Gather requirements |
-| `context` | `.iris/aidlc/skills/inception/context.md` | Define system context |
-| `units` | `.iris/aidlc/skills/inception/units.md` | Decompose into units |
-| `stories` | `.iris/aidlc/skills/inception/story-create.md` | Create user stories |
-| `bolt-plan` | `.iris/aidlc/skills/inception/bolt-plan.md` | Plan construction bolts |
-| `review` | `.iris/aidlc/skills/inception/review.md` | Review and complete |
+1 - **menu**: Show progress and options
+    → `.iris/aidlc/skills/inception/navigator.md`
+
+2 - **create-intent**: Create a new intent
+    → `.iris/aidlc/skills/inception/intent-create.md`
+
+3 - **list-intents**: List all intents
+    → `.iris/aidlc/skills/inception/intent-list.md`
+
+4 - **requirements**: Gather requirements
+    → `.iris/aidlc/skills/inception/requirements.md`
+
+5 - **context**: Define system context
+    → `.iris/aidlc/skills/inception/context.md`
+
+6 - **units**: Decompose into units
+    → `.iris/aidlc/skills/inception/units.md`
+
+7 - **stories**: Create user stories
+    → `.iris/aidlc/skills/inception/story-create.md`
+
+8 - **bolt-plan**: Plan construction bolts
+    → `.iris/aidlc/skills/inception/bolt-plan.md`
+
+9 - **review**: Review and complete
+    → `.iris/aidlc/skills/inception/review.md`
 
 ---
 
@@ -81,14 +107,23 @@ Only stop at designated checkpoints (1-4 above).
 
 ## Artifacts Created
 
-| Artifact | Location | Template |
-|----------|----------|----------|
-| Requirements | `{intent}/requirements.md` | `templates/inception/requirements-template.md` |
-| System Context | `{intent}/system-context.md` | `templates/inception/system-context-template.md` |
-| Units | `{intent}/units.md` | `templates/inception/units-template.md` |
-| Unit Brief | `{intent}/units/{unit}/unit-brief.md` | `templates/inception/unit-brief-template.md` |
-| Stories | `{intent}/units/{unit}/stories/` | `templates/inception/stories-template.md` |
-| Bolt Instances | `memory-bank/bolts/bolt-{unit}-{N}/bolt.md` | `templates/construction/bolt-template.md` |
+- **Requirements** → `{intent}/requirements.md`
+  Template: `templates/inception/requirements-template.md`
+
+- **System Context** → `{intent}/system-context.md`
+  Template: `templates/inception/system-context-template.md`
+
+- **Units** → `{intent}/units.md`
+  Template: `templates/inception/units-template.md`
+
+- **Unit Brief** → `{intent}/units/{unit}/unit-brief.md`
+  Template: `templates/inception/unit-brief-template.md`
+
+- **Stories** → `{intent}/units/{unit}/stories/`
+  Template: `templates/inception/stories-template.md`
+
+- **Bolt Instances** → `memory-bank/bolts/bolt-{unit}-{N}/bolt.md`
+  Template: `templates/construction/bolt-template.md`
 
 ---
 

package/flows/aidlc/agents/master-agent.md

@@ -4,6 +4,16 @@ You are the **Master Orchestrator Agent** for AI-DLC (AI-Driven Development Life
 
 ---
 
+## Mandatory Output Rules (READ FIRST)
+
+- 🚫 **NEVER** use ASCII tables for options - they break at different terminal widths
+- ✅ **ALWAYS** use numbered list format: `N - **Option**: Description`
+- ✅ **ALWAYS** use status indicators: ✅ (done) ⏳ (current) [ ] (pending) 🚫 (blocked)
+- ✅ **ALWAYS** start output with context header showing current state
+- ✅ **ALWAYS** end with suggested next step
+
+---
+
 ## Persona
 
 - **Role**: AI-DLC Flow Orchestrator & Project Navigator
@@ -29,13 +39,20 @@ When user invokes `/iris-master-agent`:
 
 ## Skills
 
-| Command | Skill | Description |
-|---------|-------|-------------|
-| `init`, `project-init` | `.iris/aidlc/skills/master/project-init.md` | Initialize project with standards |
-| `analyze` | `.iris/aidlc/skills/master/analyze-context.md` | Analyze project state |
-| `route` | `.iris/aidlc/skills/master/route-request.md` | Route to specialist agent |
-| `explain` | `.iris/aidlc/skills/master/explain-flow.md` | Explain AI-DLC methodology |
-| `answer` | `.iris/aidlc/skills/master/answer-question.md` | Answer questions |
+1 - **init** / **project-init**: Initialize project with standards
+    → `.iris/aidlc/skills/master/project-init.md`
+
+2 - **analyze**: Analyze project state
+    → `.iris/aidlc/skills/master/analyze-context.md`
+
+3 - **route**: Route to specialist agent
+    → `.iris/aidlc/skills/master/route-request.md`
+
+4 - **explain**: Explain AI-DLC methodology
+    → `.iris/aidlc/skills/master/explain-flow.md`
+
+5 - **answer**: Answer questions
+    → `.iris/aidlc/skills/master/answer-question.md`
 
 ---
 

package/flows/aidlc/agents/operations-agent.md

@@ -4,6 +4,17 @@ You are the **Operations Agent** for AI-DLC (AI-Driven Development Life Cycle).
 
 ---
 
+## Mandatory Output Rules (READ FIRST)
+
+- 🚫 **NEVER** use ASCII tables for options - they break at different terminal widths
+- ✅ **ALWAYS** use numbered list format: `N - **Option**: Description`
+- ✅ **ALWAYS** use status indicators: ✅ (done) ⏳ (current) [ ] (pending) 🚫 (blocked)
+- ✅ **ALWAYS** show environment progression (Dev → Staging → Production)
+- ⚠️ **ALWAYS** display warnings prominently for production actions
+- 🛑 **STOP** at every deployment checkpoint - require explicit approval
+
+---
+
 ## Persona
 
 - **Role**: DevOps Engineer & Deployment Orchestrator
@@ -27,14 +38,23 @@ When user invokes `/iris-operations-agent --unit="{name}"`:
 
 ## Skills
 
-| Command | Skill | Description |
-|---------|-------|-------------|
-| `menu` | `.iris/aidlc/skills/operations/menu.md` | Show deployment status and options |
-| `build` | `.iris/aidlc/skills/operations/build.md` | Build deployment artifacts |
-| `deploy` | `.iris/aidlc/skills/operations/deploy.md` | Deploy to environment |
-| `verify` | `.iris/aidlc/skills/operations/verify.md` | Verify deployment success |
-| `monitor` | `.iris/aidlc/skills/operations/monitor.md` | Setup monitoring and observability |
-| `rollback` | `.iris/aidlc/skills/operations/rollback.md` | Rollback to previous version |
+1 - **menu**: Show deployment status and options
+    → `.iris/aidlc/skills/operations/navigator.md`
+
+2 - **build**: Build deployment artifacts
+    → `.iris/aidlc/skills/operations/build.md`
+
+3 - **deploy**: Deploy to environment
+    → `.iris/aidlc/skills/operations/deploy.md`
+
+4 - **verify**: Verify deployment success
+    → `.iris/aidlc/skills/operations/verify.md`
+
+5 - **monitor**: Setup monitoring and observability
+    → `.iris/aidlc/skills/operations/monitor.md`
+
+6 - **rollback**: Rollback to previous version
+    → `.iris/aidlc/skills/operations/rollback.md`
 
 ---
 

package/flows/aidlc/skills/construction/bolt-list.md

@@ -2,11 +2,35 @@
 
 ---
 
-## Checkpoints in This Skill
+## Mandatory Output Rules (READ FIRST)
 
-| Checkpoint | Purpose | Wait For |
-|------------|---------|----------|
-| Checkpoint 1 | Which bolt to work on? | User selection |
+- 🚫 **NEVER** use ASCII tables for options - they break at different terminal widths
+- ✅ **ALWAYS** use numbered list format: `N - **Option**: Description`
+- ✅ **ALWAYS** use status indicators: ✅ (done) ⏳ (current) [ ] (pending) 🚫 (blocked)
+- ✅ **ALWAYS** group bolts by status (Active → Planned → Blocked → Completed)
+- ✅ **ALWAYS** show summary counts at bottom
+- 🛑 **NEVER** auto-select a bolt - always ask user which to work on
+
+## Success Metrics
+
+- ✅ Bolts grouped by status with clear headers
+- ✅ Each bolt shows: ID, unit, type, progress percentage
+- ✅ Summary with counts at bottom
+- ✅ Clear call-to-action for bolt selection
+
+## Failure Modes
+
+- ❌ Using ASCII table for bolt list
+- ❌ Auto-selecting a bolt without asking
+- ❌ Missing status indicators
+- ❌ No summary section
+
+---
+
+## Checkpoints
+
+**Checkpoint 1**: Which bolt to work on?
+- Wait for: User selection
 
 ---
 

package/flows/aidlc/skills/construction/bolt-replan.md

@@ -2,6 +2,31 @@
 
 ---
 
+## Mandatory Output Rules (READ FIRST)
+
+- 🚫 **NEVER** use ASCII tables for options - they break at different terminal widths
+- ✅ **ALWAYS** use numbered list format: `N - **Option**: Description`
+- ✅ **ALWAYS** use status indicators: ✅ (done) ⏳ (current) [ ] (pending) 🚫 (blocked)
+- ✅ **ALWAYS** show current bolt status before proposing changes
+- ✅ **ALWAYS** show dependency graph after modifications
+- 💾 **ALWAYS** update construction log after any replanning action
+
+## Success Metrics
+
+- ✅ Current state shown before any changes
+- ✅ Clear options for replanning actions
+- ✅ Dependency graph displayed after changes
+- ✅ Construction log updated
+
+## Failure Modes
+
+- ❌ Using ASCII table for bolt list
+- ❌ Modifying bolts without showing current state first
+- ❌ Not updating construction log
+- ❌ Breaking dependency chain
+
+---
+
 ## Role
 
 Utility skill to modify bolt plans during Construction - add, split, or reorder bolts.

package/flows/aidlc/skills/construction/bolt-start.md

@@ -2,6 +2,33 @@
 
 ---
 
+## Mandatory Output Rules (READ FIRST)
+
+- 🚫 **NEVER** use ASCII tables for options - they break at different terminal widths
+- ✅ **ALWAYS** use numbered list format: `N - **Option**: Description`
+- ✅ **ALWAYS** use status indicators: ✅ (done) ⏳ (current) [ ] (pending) 🚫 (blocked)
+- ✅ **ALWAYS** show current stage prominently at top of output
+- ✅ **ALWAYS** display stage progress (e.g., "Stage 2/4")
+- 📖 **ALWAYS** read bolt type definition before executing any stage
+- 💾 **ALWAYS** update bolt file status before starting work
+- 🛑 **STOP** at checkpoints defined by bolt type - wait for approval
+
+## Success Metrics
+
+- ✅ Current stage shown at top with progress
+- ✅ Activities listed with completion status
+- ✅ Artifacts created listed with paths
+- ✅ Checkpoint prompts clear and actionable
+
+## Failure Modes
+
+- ❌ Using ASCII table for activities or stories
+- ❌ Starting stage work without updating bolt file status
+- ❌ Skipping checkpoints defined by bolt type
+- ❌ Not reading bolt type definition first
+
+---
+
 ## Bolt Type Execution
 
 Stages, activities, outputs, and checkpoints come from the bolt type definition:

package/flows/aidlc/skills/construction/bolt-status.md

@@ -2,6 +2,31 @@
 
 ---
 
+## Mandatory Output Rules (READ FIRST)
+
+- 🚫 **NEVER** use ASCII tables for options - they break at different terminal widths
+- ✅ **ALWAYS** use numbered list format: `N - **Option**: Description`
+- ✅ **ALWAYS** use status indicators: ✅ (done) ⏳ (current) [ ] (pending) 🚫 (blocked)
+- ✅ **ALWAYS** show visual progress bar or percentage
+- ✅ **ALWAYS** display stage breakdown with artifacts
+- ✅ **ALWAYS** end with next action suggestion
+
+## Success Metrics
+
+- ✅ Overview section with key metadata
+- ✅ Visual progress indicator (bar or percentage)
+- ✅ Stage breakdown with status indicators
+- ✅ Clear next action with command
+
+## Failure Modes
+
+- ❌ Using ASCII table for stage list
+- ❌ Missing progress visualization
+- ❌ No next action suggested
+- ❌ Blockers not prominently displayed
+
+---
+
 ## Role
 
 Informational skill to display detailed status of a specific bolt.

package/flows/aidlc/skills/construction/navigator.md

@@ -2,6 +2,31 @@
 
 ---
 
+## Mandatory Output Rules (READ FIRST)
+
+- 🚫 **NEVER** use ASCII tables for options - they break at different terminal widths
+- ✅ **ALWAYS** use numbered list format: `N - **Option**: Description`
+- ✅ **ALWAYS** use status indicators: ✅ (done) ⏳ (current) [ ] (pending) 🚫 (blocked)
+- ✅ **ALWAYS** show active bolt context prominently at top
+- ✅ **ALWAYS** display stage progress (e.g., "Stage 2/4: Technical Design")
+- ✅ **ALWAYS** end with suggested next step and call-to-action
+
+## Success Metrics
+
+- ✅ Active bolt/unit shown at top with stage info
+- ✅ Progress shown with visual indicator or fraction
+- ✅ Options as numbered list (not table)
+- ✅ Clear suggested next step
+
+## Failure Modes
+
+- ❌ Using ASCII table for options
+- ❌ Missing active bolt context when one exists
+- ❌ No stage progress indicator
+- ❌ Missing call-to-action prompt
+
+---
+
 ## Role
 
 Entry point for Construction Agent. Routes to appropriate skill based on state.

package/flows/aidlc/skills/inception/bolt-plan.md

@@ -2,6 +2,32 @@
 
 ---
 
+## Mandatory Output Rules (READ FIRST)
+
+- 🚫 **NEVER** use ASCII tables for options - they break at different terminal widths
+- ✅ **ALWAYS** use numbered list format: `N - **Option**: Description`
+- ✅ **ALWAYS** use status indicators: ✅ (done) ⏳ (current) [ ] (pending) 🚫 (blocked)
+- ✅ **ALWAYS** show dependency graph after creating bolts
+- ✅ **ALWAYS** list created directories/files with ✅ markers
+- 💾 **ALWAYS** create actual bolt.md files - not just documentation
+- 🚫 **NEVER** create bolt-plan.md summary doc - create individual bolt directories
+
+## Success Metrics
+
+- ✅ Bolt directories created with bolt.md files
+- ✅ Dependency graph shown visually
+- ✅ All stories assigned to bolts
+- ✅ Complexity assessment included in each bolt
+
+## Failure Modes
+
+- ❌ Using ASCII table for story complexity
+- ❌ Creating bolt-plan.md instead of individual bolt.md files
+- ❌ Missing dependency tracking in frontmatter
+- ❌ Stories not assigned to any bolt
+
+---
+
 ## Progress Display
 
 Show at start of this skill:

package/flows/aidlc/skills/inception/context.md

@@ -2,6 +2,31 @@
 
 ---
 
+## Mandatory Output Rules (READ FIRST)
+
+- 🚫 **NEVER** use ASCII tables for options - they break at different terminal widths
+- ✅ **ALWAYS** use numbered list format: `N - **Option**: Description`
+- ✅ **ALWAYS** use status indicators: ✅ (done) ⏳ (current) [ ] (pending)
+- ✅ **ALWAYS** include C4 Context diagram (Mermaid)
+- ✅ **ALWAYS** list actors, external systems, and data flows
+- ✅ **ALWAYS** show artifact created with path
+
+## Success Metrics
+
+- ✅ Actors identified with types (Human/System)
+- ✅ External systems listed with integration details
+- ✅ Data flows documented (Inbound/Outbound)
+- ✅ C4 Context diagram included
+
+## Failure Modes
+
+- ❌ Using ASCII table for actors or systems
+- ❌ Missing context diagram
+- ❌ Not identifying external dependencies
+- ❌ Incomplete data flow documentation
+
+---
+
 ## Progress Display
 
 Show at start of this skill:

package/flows/aidlc/skills/inception/intent-create.md

@@ -2,6 +2,31 @@
 
 ---
 
+## Mandatory Output Rules (READ FIRST)
+
+- 🚫 **NEVER** use ASCII tables for options - they break at different terminal widths
+- ✅ **ALWAYS** use numbered list format: `N - **Option**: Description`
+- ✅ **ALWAYS** use status indicators: ✅ (done) ⏳ (current) [ ] (pending)
+- ✅ **ALWAYS** show files created with paths
+- ✅ **ALWAYS** end with numbered actions and suggested next step
+- 📖 **ALWAYS** read project.yaml for context-aware suggestions
+
+## Success Metrics
+
+- ✅ Intent directory created with correct naming ({NNN}-{name})
+- ✅ requirements.md and inception-log.md initialized
+- ✅ Confirmation shows created files with paths
+- ✅ Clear next step suggestion
+
+## Failure Modes
+
+- ❌ Using ASCII table for suggestions
+- ❌ Missing numeric prefix on intent name
+- ❌ Not reading existing intents for context
+- ❌ Multiple action lists in output
+
+---
+
 ## Progress Display
 
 Show at start of this skill:

package/flows/aidlc/skills/inception/intent-list.md

@@ -2,6 +2,31 @@
 
 ---
 
+## Mandatory Output Rules (READ FIRST)
+
+- 🚫 **NEVER** use ASCII tables for options - they break at different terminal widths
+- ✅ **ALWAYS** use numbered list format: `N - **Option**: Description`
+- ✅ **ALWAYS** use status indicators: ✅ (done) ⏳ (current) [ ] (pending)
+- ✅ **ALWAYS** group intents (Active vs Completed)
+- ✅ **ALWAYS** show summary counts
+- ✅ **ALWAYS** suggest action for most urgent intent
+
+## Success Metrics
+
+- ✅ Intents grouped by status
+- ✅ Each intent shows: name, phase, progress
+- ✅ Summary with counts
+- ✅ Suggested next step for highest priority intent
+
+## Failure Modes
+
+- ❌ Using ASCII table for intent list
+- ❌ No grouping of intents
+- ❌ Missing summary section
+- ❌ No suggested next step
+
+---
+
 ## Role
 
 Utility skill to view all intents and their status.

package/flows/aidlc/skills/inception/navigator.md

@@ -2,6 +2,31 @@
 
 ---
 
+## Mandatory Output Rules (READ FIRST)
+
+- 🚫 **NEVER** use ASCII tables for options - they break at different terminal widths
+- ✅ **ALWAYS** use numbered list format: `N - **Option**: Description`
+- ✅ **ALWAYS** use status indicators: ✅ (done) ⏳ (current) [ ] (pending)
+- ✅ **ALWAYS** show progress tracker with `← current` marker on active step
+- ✅ **ALWAYS** make suggested next step Option 1
+- ✅ **ALWAYS** end with: `**Type 1 to continue, or a number for other actions.**`
+
+## Success Metrics
+
+- ✅ Progress shown with status indicators (not plain text)
+- ✅ Options presented as numbered list (not table)
+- ✅ Suggested next step is Option 1
+- ✅ Clear call-to-action at bottom
+
+## Failure Modes
+
+- ❌ Using ASCII table for options
+- ❌ Plain list without status indicators (e.g., "Done: Step 1")
+- ❌ Missing call-to-action prompt
+- ❌ Suggested step not in position 1
+
+---
+
 ## Role
 
 Entry point for Inception Agent. Routes to appropriate skill based on state.
@@ -41,15 +66,13 @@ Build menu dynamically using the Output sections below based on current state.
 
 Scan artifacts **in order** - first missing item is the suggested next step:
 
-| Check (in order)              | If missing → Suggest     |
-|-------------------------------|--------------------------|
-| No intent folder exists       | Create Intent            |
-| `requirements.md`             | Gather Requirements      |
-| `system-context.md`           | Define Context           |
-| `units.md`                    | Decompose Units          |
-| `story-index.md`              | Create Stories           |
-| `bolt-plan.md`                | Plan Bolts               |
-| All complete                  | Review & Complete        |
+1. No intent folder exists → **Create Intent**
+2. `requirements.md` missing → **Gather Requirements**
+3. `system-context.md` missing → **Define Context**
+4. `units.md` missing → **Decompose Units**
+5. `story-index.md` missing → **Create Stories**
+6. `bolt-plan.md` missing → **Plan Bolts**
+7. All complete → **Review & Complete**
 
 **CRITICAL**: The suggested step becomes **Option 1** in the menu.
 

package/flows/aidlc/skills/inception/requirements.md

@@ -2,6 +2,31 @@
 
 ---
 
+## Mandatory Output Rules (READ FIRST)
+
+- 🚫 **NEVER** use ASCII tables for options - they break at different terminal widths
+- ✅ **ALWAYS** use numbered list format: `N - **Option**: Description`
+- ✅ **ALWAYS** use status indicators: ✅ (done) ⏳ (current) [ ] (pending)
+- ✅ **ALWAYS** show progress tracker at checkpoint moments
+- ✅ **ALWAYS** present FULL requirements at Checkpoint 2 (no summaries)
+- 🛑 **STOP** at Checkpoint 1 (questions) and Checkpoint 2 (approval)
+
+## Success Metrics
+
+- ✅ Clarifying questions asked before generating
+- ✅ Full requirements shown at review (not summarized)
+- ✅ Each requirement has: Description, Acceptance Criteria, Priority
+- ✅ Clear approval prompt at Checkpoint 2
+
+## Failure Modes
+
+- ❌ Using ASCII table for checkpoints
+- ❌ Generating requirements without asking questions first
+- ❌ Summarizing requirements at review instead of full details
+- ❌ Not waiting for approval at checkpoints
+
+---
+
 ## Progress Display
 
 Show at start of this skill:

package/flows/aidlc/skills/inception/review.md

@@ -2,6 +2,31 @@
 
 ---
 
+## Mandatory Output Rules (READ FIRST)
+
+- 🚫 **NEVER** use ASCII tables for options - they break at different terminal widths
+- ✅ **ALWAYS** use numbered list format: `N - **Option**: Description`
+- ✅ **ALWAYS** use status indicators: ✅ (done) ⏳ (current) [ ] (pending) 🚫 (blocked)
+- ✅ **ALWAYS** show progress tracker at checkpoint moments
+- ✅ **ALWAYS** present complete artifact summary at Checkpoint 3
+- 🛑 **STOP** at Checkpoint 3 (artifacts review) and Checkpoint 4 (construction ready)
+
+## Success Metrics
+
+- ✅ All artifacts verified with ✅ or 🚫 status
+- ✅ Gaps clearly identified with recommended actions
+- ✅ Final summary shows counts (requirements, units, stories, bolts)
+- ✅ Clear transition to Construction Agent
+
+## Failure Modes
+
+- ❌ Using ASCII table for checkpoints
+- ❌ Not verifying all artifact types
+- ❌ Skipping gap identification
+- ❌ Not updating inception-log.md on completion
+
+---
+
 ## Progress Display
 
 Show at start of this skill:

package/flows/aidlc/skills/inception/story-create.md

@@ -2,6 +2,31 @@
 
 ---
 
+## Mandatory Output Rules (READ FIRST)
+
+- 🚫 **NEVER** use ASCII tables for options - they break at different terminal widths
+- ✅ **ALWAYS** use numbered list format: `N - **Option**: Description`
+- ✅ **ALWAYS** use status indicators: ✅ (done) ⏳ (current) [ ] (pending)
+- ✅ **ALWAYS** create individual story files (one per story, not one combined file)
+- ✅ **ALWAYS** list created files with ✅ markers
+- 💾 **ALWAYS** update story-index.md immediately after each story file creation
+
+## Success Metrics
+
+- ✅ Individual story files created (not a combined stories.md)
+- ✅ Each story has: User Story format, Acceptance Criteria, Priority
+- ✅ story-index.md updated with ✅ GENERATED markers
+- ✅ Unit-brief.md updated with story summary
+
+## Failure Modes
+
+- ❌ Creating single stories.md instead of individual files
+- ❌ Missing acceptance criteria in stories
+- ❌ Not updating story-index.md
+- ❌ Stories without INVEST criteria validation
+
+---
+
 ## Progress Display
 
 Show at start of this skill:

package/flows/aidlc/skills/inception/units.md

@@ -2,6 +2,31 @@
 
 ---
 
+## Mandatory Output Rules (READ FIRST)
+
+- 🚫 **NEVER** use ASCII tables for options - they break at different terminal widths
+- ✅ **ALWAYS** use numbered list format: `N - **Option**: Description`
+- ✅ **ALWAYS** use status indicators: ✅ (done) ⏳ (current) [ ] (pending)
+- ✅ **ALWAYS** show dependency graph after creating units
+- ✅ **ALWAYS** list created directories/files with ✅ markers
+- 📖 **ALWAYS** read project.yaml and catalog.yaml for project type configuration
+
+## Success Metrics
+
+- ✅ Unit directories created with unit-brief.md files
+- ✅ Dependency graph shown visually
+- ✅ All FRs mapped to exactly one unit
+- ✅ Frontend unit included if enabled in project type
+
+## Failure Modes
+
+- ❌ Using ASCII table for unit listing
+- ❌ Not reading project type configuration
+- ❌ FRs not mapped to units
+- ❌ Missing unit-brief.md files
+
+---
+
 ## Progress Display
 
 Show at start of this skill:

package/flows/aidlc/skills/master/analyze-context.md

@@ -2,6 +2,31 @@
 
 ---
 
+## Mandatory Output Rules (READ FIRST)
+
+- 🚫 **NEVER** use ASCII tables for options - they break at different terminal widths
+- ✅ **ALWAYS** use numbered list format: `N - **Option**: Description`
+- ✅ **ALWAYS** use status indicators: ✅ (done) ⏳ (current) [ ] (pending) 🚫 (blocked)
+- ✅ **ALWAYS** show summary at top (Phase, Active Intent/Unit/Bolt)
+- ✅ **ALWAYS** end with suggested next step and call-to-action
+- 📖 **ALWAYS** read memory-bank.yaml before analyzing
+
+## Success Metrics
+
+- ✅ Summary block at top with current phase
+- ✅ Evidence listed with counts
+- ✅ Options as numbered list (not table)
+- ✅ Clear suggested next step with specific command
+
+## Failure Modes
+
+- ❌ Using ASCII table for options
+- ❌ Missing phase determination
+- ❌ No suggested next step
+- ❌ Vague recommendations without specific commands
+
+---
+
 ## Role
 
 Diagnostic skill to determine current project state by inspecting memory bank artifacts.
@@ -116,12 +141,16 @@ If inconsistencies found, report them:
 ```markdown
 ## ⚠️ Status Inconsistencies Detected
 
-| Artifact | Current Status | Expected Status | Reason |
-|----------|----------------|-----------------|--------|
-| unit-brief: file-watcher | draft | complete | All bolts complete |
-| requirements: 011-vscode-extension | units-defined | construction | Has in-progress units |
+- **unit-brief: file-watcher**
+  Current: `draft` → Expected: `complete`
+  Reason: All bolts complete
+
+- **requirements: 011-vscode-extension**
+  Current: `units-defined` → Expected: `construction`
+  Reason: Has in-progress units
 
 ### Actions
+
 1 - **fix**: Update all statuses to expected values
 2 - **skip**: Continue without fixing
 3 - **review**: Show details for each inconsistency

package/flows/aidlc/skills/master/answer-question.md

@@ -2,6 +2,30 @@
 
 ---
 
+## Mandatory Output Rules (READ FIRST)
+
+- 🚫 **NEVER** use ASCII tables for options - they break at different terminal widths
+- ✅ **ALWAYS** use numbered list format: `N - **Option**: Description`
+- ✅ **ALWAYS** cite source files with paths
+- ✅ **ALWAYS** acknowledge if information not found with search paths tried
+- ✅ **ALWAYS** suggest next actions after answering
+
+## Success Metrics
+
+- ✅ Direct answer provided at top
+- ✅ Source file cited with path
+- ✅ Related information included if relevant
+- ✅ Clear next actions suggested
+
+## Failure Modes
+
+- ❌ Using ASCII table for options
+- ❌ Answering without citing source
+- ❌ Not acknowledging when info not found
+- ❌ No follow-up actions suggested
+
+---
+
 ## Role
 
 Knowledge retrieval skill to answer questions by querying memory bank artifacts.

package/flows/aidlc/skills/master/explain-flow.md

@@ -2,6 +2,30 @@
 
 ---
 
+## Mandatory Output Rules (READ FIRST)
+
+- 🚫 **NEVER** use ASCII tables for options - they break at different terminal widths
+- ✅ **ALWAYS** use numbered list format: `N - **Option**: Description`
+- ✅ **ALWAYS** show the three phases visually (Inception → Construction → Operations)
+- ✅ **ALWAYS** indicate user's current position if known
+- ✅ **ALWAYS** end with suggested next step
+
+## Success Metrics
+
+- ✅ Clear explanation of relevant AI-DLC concepts
+- ✅ Visual phase progression shown
+- ✅ Current position highlighted if known
+- ✅ Practical next step suggested
+
+## Failure Modes
+
+- ❌ Using ASCII table for phases or options
+- ❌ Abstract explanation without practical context
+- ❌ No indication of user's current position
+- ❌ Missing suggested next action
+
+---
+
 ## Role
 
 Educational skill to explain AI-DLC methodology and help users understand their position in the workflow.

package/flows/aidlc/skills/master/project-init.md

@@ -2,6 +2,31 @@
 
 ---
 
+## Mandatory Output Rules (READ FIRST)
+
+- 🚫 **NEVER** use ASCII tables for options - they break at different terminal widths
+- ✅ **ALWAYS** use numbered list format: `N - **Option**: Description`
+- ✅ **ALWAYS** ask one question at a time (never combine multiple questions)
+- ✅ **ALWAYS** show created files with ✅ markers
+- ✅ **ALWAYS** save project.yaml immediately after project type selection
+- 💾 **ALWAYS** confirm before saving each standard
+
+## Success Metrics
+
+- ✅ project.yaml created with project type
+- ✅ Standards created in correct order (dependencies respected)
+- ✅ Each question is single-focus (not combined)
+- ✅ Final summary shows all created/skipped standards
+
+## Failure Modes
+
+- ❌ Using ASCII table for options
+- ❌ Asking multiple questions at once
+- ❌ Creating standard before its dependencies
+- ❌ Not creating project.yaml
+
+---
+
 ## Role
 
 Setup skill to initialize a new project by facilitating creation of project standards through guided conversation.

package/flows/aidlc/skills/master/route-request.md

@@ -2,6 +2,30 @@
 
 ---
 
+## Mandatory Output Rules (READ FIRST)
+
+- 🚫 **NEVER** use ASCII tables for options - they break at different terminal widths
+- ✅ **ALWAYS** use numbered list format: `N - **Option**: Description`
+- ✅ **ALWAYS** show exact command with parameters
+- ✅ **ALWAYS** explain what the target agent will do
+- ✅ **ALWAYS** ask for confirmation before routing
+
+## Success Metrics
+
+- ✅ Recommended agent clearly identified
+- ✅ Exact command provided with all parameters
+- ✅ "What happens next" explanation included
+- ✅ Confirmation prompt before routing
+
+## Failure Modes
+
+- ❌ Using ASCII table for routing options
+- ❌ Vague routing without specific command
+- ❌ Missing parameters in command
+- ❌ Not explaining what target agent does
+
+---
+
 ## Role
 
 Routing skill to direct users to the appropriate specialist agent based on context and request.

package/flows/aidlc/skills/operations/build.md

@@ -2,6 +2,31 @@
 
 ---
 
+## Mandatory Output Rules (READ FIRST)
+
+- 🚫 **NEVER** use ASCII tables for options - they break at different terminal widths
+- ✅ **ALWAYS** use numbered list format: `N - **Option**: Description`
+- ✅ **ALWAYS** use status indicators: ✅ (done) ⏳ (current) [ ] (pending) 🚫 (blocked)
+- ✅ **ALWAYS** show progress tracker at start
+- ✅ **ALWAYS** display build artifact details (version, tag, size)
+- 🛑 **STOP** at Checkpoint 1 - require build approval before proceeding
+
+## Success Metrics
+
+- ✅ Prerequisites verified before building
+- ✅ Artifact details shown (version, tag, registry)
+- ✅ Build documentation created
+- ✅ Clear next step (deploy)
+
+## Failure Modes
+
+- ❌ Using ASCII table for checkpoints
+- ❌ Building without verifying prerequisites
+- ❌ Not documenting build metadata
+- ❌ Missing rollback information
+
+---
+
 ## Progress Display
 
 Show at start of this skill:

package/flows/aidlc/skills/operations/deploy.md

@@ -2,6 +2,32 @@
 
 ---
 
+## Mandatory Output Rules (READ FIRST)
+
+- 🚫 **NEVER** use ASCII tables for options - they break at different terminal widths
+- ✅ **ALWAYS** use numbered list format: `N - **Option**: Description`
+- ✅ **ALWAYS** use status indicators: ✅ (done) ⏳ (current) [ ] (pending) 🚫 (blocked)
+- ✅ **ALWAYS** show environment progression (Dev → Staging → Production)
+- ⚠️ **ALWAYS** display warnings prominently for production deployments
+- 🛑 **STOP** at Checkpoint 2 (staging) and Checkpoint 3 (production)
+- ✅ **ALWAYS** include rollback command in output
+
+## Success Metrics
+
+- ✅ Environment progression respected (no skipping)
+- ✅ Rollback command provided
+- ✅ Production warnings displayed prominently
+- ✅ Deployment history documented
+
+## Failure Modes
+
+- ❌ Using ASCII table for checkpoints
+- ❌ Deploying to prod without staging verification
+- ❌ Missing rollback command
+- ❌ Not documenting deployment history
+
+---
+
 ## Progress Display
 
 Show at start of this skill (varies by environment):

package/flows/aidlc/skills/operations/monitor.md

@@ -2,6 +2,31 @@
 
 ---
 
+## Mandatory Output Rules (READ FIRST)
+
+- 🚫 **NEVER** use ASCII tables for options - they break at different terminal widths
+- ✅ **ALWAYS** use numbered list format: `N - **Option**: Description`
+- ✅ **ALWAYS** use status indicators: ✅ (done) ⏳ (current) [ ] (pending)
+- ✅ **ALWAYS** show progress tracker at start
+- ✅ **ALWAYS** list dashboards, alerts, and SLOs created
+- 🛑 **STOP** at Checkpoint 4 - require monitoring setup approval
+
+## Success Metrics
+
+- ✅ Dashboards created and linked
+- ✅ Alerts configured with thresholds
+- ✅ SLOs defined
+- ✅ Runbooks documented
+
+## Failure Modes
+
+- ❌ Using ASCII table for checkpoints
+- ❌ Missing dashboard URLs
+- ❌ Alerts without thresholds
+- ❌ No runbooks for common issues
+
+---
+
 ## Progress Display
 
 Show at start of this skill:

package/flows/aidlc/skills/operations/navigator.md

@@ -2,6 +2,31 @@
 
 ---
 
+## Mandatory Output Rules (READ FIRST)
+
+- 🚫 **NEVER** use ASCII tables for options - they break at different terminal widths
+- ✅ **ALWAYS** use numbered list format: `N - **Option**: Description`
+- ✅ **ALWAYS** use status indicators: ✅ (done) ⏳ (current) [ ] (pending) 🚫 (blocked)
+- ✅ **ALWAYS** show deployment status for all environments
+- ✅ **ALWAYS** verify construction complete before proceeding
+- ✅ **ALWAYS** suggest next logical step in deployment pipeline
+
+## Success Metrics
+
+- ✅ Environment status shown for Dev/Staging/Prod
+- ✅ Suggested next step based on deployment state
+- ✅ Prerequisites verified (construction complete)
+- ✅ Clear call-to-action
+
+## Failure Modes
+
+- ❌ Using ASCII table for deployment status
+- ❌ Proceeding without verifying construction complete
+- ❌ Not showing all environment statuses
+- ❌ Missing suggested next step
+
+---
+
 ## Role
 
 Entry point for Operations Agent. Routes to appropriate skill based on state.

package/flows/aidlc/skills/operations/verify.md

@@ -2,6 +2,31 @@
 
 ---
 
+## Mandatory Output Rules (READ FIRST)
+
+- 🚫 **NEVER** use ASCII tables for options - they break at different terminal widths
+- ✅ **ALWAYS** use numbered list format: `N - **Option**: Description`
+- ✅ **ALWAYS** use status indicators: ✅ (pass) ❌ (fail) ⏳ (running)
+- ✅ **ALWAYS** show all check results (health, smoke tests, metrics)
+- ⚠️ **ALWAYS** recommend rollback prominently if verification fails
+- ✅ **ALWAYS** include rollback command in failure output
+
+## Success Metrics
+
+- ✅ All check types shown (health, smoke, metrics)
+- ✅ Clear pass/fail status per check
+- ✅ Rollback command provided on failure
+- ✅ Baseline comparison included if available
+
+## Failure Modes
+
+- ❌ Using ASCII table for check results
+- ❌ Not recommending rollback on failure
+- ❌ Missing rollback command
+- ❌ No baseline comparison
+
+---
+
 ## Role
 
 Post-deployment validation skill. Runs health checks and smoke tests.

package/lib/cli-utils.js

@@ -192,7 +192,7 @@ const CLIUtils = {
     for (const line of lines) {
       const stripped = line.replace(/\u001b\[[0-9;]*m/g, ''); // Strip ANSI codes for length calculation
       const paddedLine = line + ' '.repeat(Math.max(0, innerWidth - stripped.length));
-      console.log(colorFn(BOX.vertical) + paddedLine.slice(0, innerWidth) + colorFn(BOX.vertical));
+      console.log(colorFn(BOX.vertical) + paddedLine + colorFn(BOX.vertical));
     }
 
     // Padding bottom

package/lib/installers/AntigravityInstaller.js

@@ -1,5 +1,8 @@
 const ToolInstaller = require('./ToolInstaller');
 const path = require('path');
+const fs = require('fs-extra');
+const CLIUtils = require('../cli-utils');
+const { theme } = CLIUtils;
 
 class AntigravityInstaller extends ToolInstaller {
     get key() {
@@ -17,6 +20,93 @@ class AntigravityInstaller extends ToolInstaller {
     get detectPath() {
         return '.agent';
     }
+
+    /**
+     * Extract a description from markdown content.
+     * Uses the first H1 heading text as the description.
+     * @param {string} content - Markdown content
+     * @returns {string} Description text
+     */
+    extractDescription(content) {
+        // Look for first H1 heading
+        const h1Match = content.match(/^#\s+(.+)$/m);
+        if (h1Match) {
+            return h1Match[1].trim();
+        }
+        // Fallback: use first non-empty line
+        const lines = content.split('\n').filter(line => line.trim());
+        return lines[0] ? lines[0].replace(/^#+\s*/, '').trim() : 'IRIS workflow';
+    }
+
+    /**
+     * Check if content already has YAML frontmatter
+     * @param {string} content - Markdown content
+     * @returns {boolean}
+     */
+    hasFrontmatter(content) {
+        return content.trimStart().startsWith('---');
+    }
+
+    /**
+     * Add YAML frontmatter to content for Antigravity workflow format
+     * @param {string} content - Original markdown content
+     * @returns {string} Content with frontmatter
+     */
+    addFrontmatter(content) {
+        if (this.hasFrontmatter(content)) {
+            return content; // Already has frontmatter
+        }
+
+        const description = this.extractDescription(content);
+        const frontmatter = `---
+description: ${description}
+---
+`;
+        return frontmatter + content;
+    }
+
+    /**
+     * Override installCommands to add YAML frontmatter for Antigravity workflows.
+     * Antigravity requires workflows to have YAML frontmatter with a description field.
+     */
+    async installCommands(flowPath, config) {
+        const targetCommandsDir = this.commandsDir;
+        console.log(theme.dim(`  Installing workflows to ${targetCommandsDir}/...`));
+        await fs.ensureDir(targetCommandsDir);
+
+        const commandsSourceDir = path.join(flowPath, 'commands');
+
+        if (!await fs.pathExists(commandsSourceDir)) {
+            console.log(theme.warning(`  No commands folder found at ${commandsSourceDir}`));
+            return [];
+        }
+
+        const commandFiles = await fs.readdir(commandsSourceDir);
+        const installedFiles = [];
+
+        for (const cmdFile of commandFiles) {
+            if (cmdFile.endsWith('.md')) {
+                try {
+                    const sourcePath = path.join(commandsSourceDir, cmdFile);
+                    const prefix = (config && config.command && config.command.prefix) ? `${config.command.prefix}-` : '';
+                    const targetFileName = `iris-${prefix}${cmdFile}`;
+                    const targetPath = path.join(targetCommandsDir, targetFileName);
+
+                    // Read content and add YAML frontmatter for Antigravity
+                    let content = await fs.readFile(sourcePath, 'utf8');
+                    content = this.addFrontmatter(content);
+
+                    await fs.outputFile(targetPath, content, 'utf8');
+                    installedFiles.push(targetFileName);
+                } catch (err) {
+                    console.log(theme.warning(`  Failed to install ${cmdFile}: ${err.message}`));
+                }
+            }
+        }
+
+        CLIUtils.displayStatus('', `Installed ${installedFiles.length} workflows for ${this.name}`, 'success');
+        return installedFiles;
+    }
 }
 
 module.exports = AntigravityInstaller;

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "project-iris",
-  "version": "0.0.14",
+  "version": "0.0.16",
   "description": "Multi-agent orchestration system for AI-native software development. Delivers AI-DLC, Agile, and custom SDLC flows as markdown-based agent systems.",
   "main": "lib/installer.js",
   "bin": {
@@ -115,4 +115,4 @@
       ]
     ]
   }
-}
+}