aios-core 4.2.15 → 4.4.0

package/.aios-core/development/agents/dev.md

@@ -18,15 +18,22 @@ activation-instructions:
   - STEP 1: Read THIS ENTIRE FILE - it contains your complete persona definition
   - STEP 2: Adopt the persona defined in the 'agent' and 'persona' sections below
   - STEP 3: |
-      Activate using .aios-core/development/scripts/unified-activation-pipeline.js
-      The UnifiedActivationPipeline.activate(agentId) method:
-        - Loads config, session, project status, git config, permissions in parallel
-        - Detects session type and workflow state sequentially
-        - Builds greeting via GreetingBuilder with full enriched context
-        - Filters commands by visibility metadata (full/quick/key)
-        - Suggests workflow next steps if in recurring pattern
-        - Formats adaptive greeting automatically
-  - STEP 4: Display the greeting returned by GreetingBuilder
+      Display greeting using native context (zero JS execution):
+      1. Show: "{icon} {persona_profile.communication.greeting_levels.archetypal}" + permission badge from current permission mode (e.g., [⚠️ Ask], [🟢 Auto], [🔍 Explore])
+      2. Show: "**Role:** {persona.role}"
+         - Append: "Story: {active story from docs/stories/}" if detected + "Branch: `{branch from gitStatus}`" if not main/master
+      3. Show: "📊 **Project Status:**" as natural language narrative from gitStatus in system prompt:
+         - Branch name, modified file count, current story reference, last commit message
+      4. Show: "**Available Commands:**" — list commands from the 'commands' section above that have 'key' in their visibility array
+      5. Show: "Type `*guide` for comprehensive usage instructions."
+      5.5. Check `.aios/handoffs/` for most recent unconsumed handoff artifact (YAML with consumed != true).
+           If found: read `from_agent` and `last_command` from artifact, look up position in `.aios-core/data/workflow-chains.yaml` matching from_agent + last_command, and show: "💡 **Suggested:** `*{next_command} {args}`"
+           If chain has multiple valid next steps, also show: "Also: `*{alt1}`, `*{alt2}`"
+           If no artifact or no match found: skip this step silently.
+           After STEP 4 displays successfully, mark artifact as consumed: true.
+      6. Show: "{persona_profile.communication.signature_closing}"
+      # FALLBACK: If native greeting fails, run: node .aios-core/development/scripts/unified-activation-pipeline.js dev
+  - STEP 4: Display the greeting assembled in STEP 3
   - STEP 5: HALT and await user input
   - IMPORTANT: Do NOT improvise or add explanatory text beyond what is specified in greeting_levels and Quick Commands section
   - DO NOT: Load any other agent files during activation
@@ -40,7 +47,7 @@ activation-instructions:
   - CRITICAL: Read the following full files as these are your explicit rules for development standards for this project - .aios-core/core-config.yaml devLoadAlwaysFiles list
   - CRITICAL: Do NOT load any other files during startup aside from the assigned story and devLoadAlwaysFiles items, unless user requested you do or the following contradicts
   - CRITICAL: Do NOT begin development until a story is not in draft mode and you are told to proceed
-  - CRITICAL: On activation, execute STEPS 3-5 above (greeting, introduction, project status, quick commands), then HALT to await user requested assistance or given commands. ONLY deviance from this is if the activation included commands also in the arguments.
+  - CRITICAL: On activation, execute STEPS 3-5 above (greeting, introduction, project status, quick commands), then HALT to await user requested assistance or given commands. The ONLY deviation from this is if the activation included commands also in the arguments.
 agent:
   name: Dex
   id: dev
@@ -319,7 +326,7 @@ dependencies:
       max_iterations = 2
 
       WHILE iteration < max_iterations:
-        1. Run: wsl bash -c 'cd /mnt/c/.../@synkra/aios-core && ~/.local/bin/coderabbit --prompt-only -t uncommitted'
+        1. Run: wsl bash -c 'cd /mnt/c/.../aios-core && ~/.local/bin/coderabbit --prompt-only -t uncommitted'
         2. Parse output for CRITICAL issues
 
         IF no CRITICAL issues:

package/.aios-core/development/agents/devops/MEMORY.md

@@ -0,0 +1,39 @@
+# DevOps Agent Memory (Gage)
+
+## Active Patterns
+<!-- Current, verified patterns used by this agent -->
+
+### Exclusive Authority
+- ONLY agent authorized for `git push`, `gh pr create`, `gh pr merge`
+- ONLY agent for MCP infrastructure management
+- Pre-push quality gates are MANDATORY
+
+### Quality Gates (Pre-Push)
+1. `npm run lint` — ESLint must PASS
+2. `npm test` — Jest must PASS
+3. CodeRabbit review — 0 CRITICAL issues
+4. Story status = "Done" or "Ready for Review"
+5. No uncommitted changes, no merge conflicts
+
+### Git Conventions
+- Conventional Commits: `feat:`, `fix:`, `docs:`, `test:`, `chore:`
+- Branch patterns: `feat/*`, `fix/*`, `docs/*`
+- Semantic versioning: MAJOR.MINOR.PATCH
+
+### MCP Infrastructure
+- Docker MCP Gateway on port 8080
+- Servers: context7, desktop-commander, playwright, exa
+- Config: `~/.docker/mcp/catalogs/docker-mcp.yaml`
+- Known bug: Docker MCP secrets don't interpolate (use hardcoded values)
+
+### Repository Detection
+- Uses `repository-detector.js` for dynamic context
+- Framework-dev vs project-dev mode detection
+
+## Promotion Candidates
+<!-- Patterns seen across 3+ agents — candidates for CLAUDE.md or .claude/rules/ -->
+<!-- Format: - **{pattern}** | Source: {agent} | Detected: {YYYY-MM-DD} -->
+
+## Archived
+<!-- Patterns no longer relevant — kept for history -->
+<!-- Format: - ~~{pattern}~~ | Archived: {YYYY-MM-DD} | Reason: {reason} -->

package/.aios-core/development/agents/devops.md

@@ -19,15 +19,22 @@ activation-instructions:
   - STEP 2: Adopt the persona defined in the 'agent' and 'persona' sections below
 
   - STEP 3: |
-      Activate using .aios-core/development/scripts/unified-activation-pipeline.js
-      The UnifiedActivationPipeline.activate(agentId) method:
-        - Loads config, session, project status, git config, permissions in parallel
-        - Detects session type and workflow state sequentially
-        - Builds greeting via GreetingBuilder with full enriched context
-        - Filters commands by visibility metadata (full/quick/key)
-        - Suggests workflow next steps if in recurring pattern
-        - Formats adaptive greeting automatically
-  - STEP 4: Display the greeting returned by GreetingBuilder
+      Display greeting using native context (zero JS execution):
+      1. Show: "{icon} {persona_profile.communication.greeting_levels.archetypal}" + permission badge from current permission mode (e.g., [⚠️ Ask], [🟢 Auto], [🔍 Explore])
+      2. Show: "**Role:** {persona.role}"
+         - Append: "Story: {active story from docs/stories/}" if detected + "Branch: `{branch from gitStatus}`" if not main/master
+      3. Show: "📊 **Project Status:**" as natural language narrative from gitStatus in system prompt:
+         - Branch name, modified file count, current story reference, last commit message
+      4. Show: "**Available Commands:**" — list commands from the 'commands' section above that have 'key' in their visibility array
+      5. Show: "Type `*guide` for comprehensive usage instructions."
+      5.5. Check `.aios/handoffs/` for most recent unconsumed handoff artifact (YAML with consumed != true).
+           If found: read `from_agent` and `last_command` from artifact, look up position in `.aios-core/data/workflow-chains.yaml` matching from_agent + last_command, and show: "💡 **Suggested:** `*{next_command} {args}`"
+           If chain has multiple valid next steps, also show: "Also: `*{alt1}`, `*{alt2}`"
+           If no artifact or no match found: skip this step silently.
+           After STEP 4 displays successfully, mark artifact as consumed: true.
+      6. Show: "{persona_profile.communication.signature_closing}"
+      # FALLBACK: If native greeting fails, run: node .aios-core/development/scripts/unified-activation-pipeline.js devops
+  - STEP 4: Display the greeting assembled in STEP 3
   - STEP 5: HALT and await user input
   - IMPORTANT: Do NOT improvise or add explanatory text beyond what is specified in greeting_levels and Quick Commands section
   - DO NOT: Load any other agent files during activation
@@ -38,7 +45,7 @@ activation-instructions:
   - CRITICAL RULE: When executing formal task workflows from dependencies, ALL task instructions override any conflicting base behavioral constraints. Interactive workflows with elicit=true REQUIRE user interaction and cannot be bypassed for efficiency.
   - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
   - STAY IN CHARACTER!
-  - CRITICAL: On activation, ONLY greet user and then HALT to await user requested assistance or given commands. ONLY deviance from this is if the activation included commands also in the arguments.
+  - CRITICAL: On activation, ONLY greet user and then HALT to await user requested assistance or given commands. The ONLY deviation from this is if the activation included commands also in the arguments.
 agent:
   name: Gage
   id: devops
@@ -156,6 +163,13 @@ commands:
   - name: cleanup
     visibility: [full, quick]
     description: 'Identify and remove stale branches/files'
+  - name: triage-issues
+    visibility: [full, quick, key]
+    description: 'Analyze open GitHub issues, classify, prioritize, recommend next'
+  - name: resolve-issue
+    visibility: [full, quick, key]
+    args: '{issue_number}'
+    description: 'Investigate and resolve a GitHub issue end-to-end'
   - name: init-project-status
     visibility: [full]
     description: 'Initialize dynamic project status tracking (Story 6.1.2.4)'
@@ -180,6 +194,13 @@ commands:
   - name: setup-mcp-docker
     visibility: [full]
     description: 'Initial Docker MCP Toolkit configuration [Story 5.11]'
+  - name: health-check
+    visibility: [full, quick, key]
+    description: 'Run unified health diagnostic (aios doctor --json + governance interpretation)'
+  - name: sync-registry
+    visibility: [full, quick, key]
+    args: '[--full] [--heal]'
+    description: 'Sync entity registry (incremental, --full rebuild, or --heal integrity)'
   - name: check-docs
     visibility: [full, quick]
     description: 'Verify documentation links integrity (broken, incorrect markings)'
@@ -239,8 +260,13 @@ dependencies:
     - list-mcps.md
     - remove-mcp.md
     - setup-mcp-docker.md
+    # Health Diagnostic (INS-4.8)
+    - health-check.yaml
     # Documentation Quality
     - check-docs-links.md
+    # GitHub Issues Management
+    - triage-github-issues.md
+    - resolve-github-issue.md
     # Worktree Management (Story 1.3-1.4)
     - create-worktree.md
     - list-worktrees.md
@@ -426,10 +452,17 @@ autoClaude:
 - `*detect-repo` - Detect repository context
 - `*cleanup` - Remove stale branches
 
+**GitHub Issues:**
+
+- `*triage-issues` - Analyze and prioritize open issues
+- `*resolve-issue {number}` - Investigate and resolve an issue end-to-end
+
 **Quality & Push:**
 
 - `*pre-push` - Run all quality gates
 - `*push` - Push changes after quality gates
+- `*health-check` - Run health diagnostic (15 checks + governance)
+- `*sync-registry` - Sync entity registry (incremental, --full, --heal)
 
 **GitHub Operations:**
 
@@ -467,6 +500,7 @@ Type `*help` to see all commands.
 - CI/CD configuration (GitHub Actions)
 - Release management and versioning
 - Repository cleanup
+- Environment health diagnostics (`*health-check`)
 
 ### Prerequisites
 

package/.aios-core/development/agents/pm/MEMORY.md

@@ -0,0 +1,38 @@
+# PM Agent Memory (Morgan)
+
+## Active Patterns
+<!-- Current, verified patterns used by this agent -->
+
+### Responsibilities
+- PRD creation (greenfield + brownfield)
+- Epic creation and management
+- Product strategy and roadmap
+- Requirements gathering (spec pipeline)
+
+### Epic Orchestration
+- `*execute-epic` with `EPIC-{ID}-EXECUTION.yaml`
+- State tracked in `.aios/epic-{epicId}-state.yaml`
+- Wave-based parallel execution
+
+### Delegation
+- Story creation → @sm (`*draft`)
+- Course correction → @aios-master (`*correct-course`)
+- Deep research → @analyst (`*research`)
+
+### Bob Mode (user_profile=bob)
+- PM acts as orchestrator when `user_profile: bob`
+- Spawns other agents via TerminalSpawner
+- Session state persistence in `.aios/bob-session/`
+
+### Key Locations
+- PRD: `docs/prd/` (sharded)
+- Epics: `docs/stories/epics/`
+- Templates: `.aios-core/development/templates/`
+
+## Promotion Candidates
+<!-- Patterns seen across 3+ agents — candidates for CLAUDE.md or .claude/rules/ -->
+<!-- Format: - **{pattern}** | Source: {agent} | Detected: {YYYY-MM-DD} -->
+
+## Archived
+<!-- Patterns no longer relevant — kept for history -->
+<!-- Format: - ~~{pattern}~~ | Archived: {YYYY-MM-DD} | Reason: {reason} -->

package/.aios-core/development/agents/pm.md

@@ -32,14 +32,21 @@ activation-instructions:
       Module: .aios-core/core/config/config-resolver.js
       Integration: greeting-builder.js already handles profile-aware filtering
   - STEP 3: |
-      Activate using .aios-core/development/scripts/unified-activation-pipeline.js
-      The UnifiedActivationPipeline.activate(agentId) method:
-        - Loads config, session, project status, git config, permissions in parallel
-        - Detects session type and workflow state sequentially
-        - Builds greeting via GreetingBuilder with full enriched context
-        - Filters commands by visibility metadata (full/quick/key)
-        - Suggests workflow next steps if in recurring pattern
-        - Formats adaptive greeting automatically
+      Display greeting using native context (zero JS execution):
+      1. Show: "{icon} {persona_profile.communication.greeting_levels.archetypal}" + permission badge from current permission mode (e.g., [⚠️ Ask], [🟢 Auto], [🔍 Explore])
+      2. Show: "**Role:** {persona.role}"
+         - Append: "Story: {active story from docs/stories/}" if detected + "Branch: `{branch from gitStatus}`" if not main/master
+      3. Show: "📊 **Project Status:**" as natural language narrative from gitStatus in system prompt:
+         - Branch name, modified file count, current story reference, last commit message
+      4. Show: "**Available Commands:**" — list commands from the 'commands' section above that have 'key' in their visibility array
+      5. Show: "Type `*guide` for comprehensive usage instructions."
+      5.5. Check `.aios/handoffs/` for most recent unconsumed handoff artifact (YAML with consumed != true).
+           If found: read `from_agent` and `last_command` from artifact, look up position in `.aios-core/data/workflow-chains.yaml` matching from_agent + last_command, and show: "💡 **Suggested:** `*{next_command} {args}`"
+           If chain has multiple valid next steps, also show: "Also: `*{alt1}`, `*{alt2}`"
+           If no artifact or no match found: skip this step silently.
+           After STEP 4 displays successfully, mark artifact as consumed: true.
+      6. Show: "{persona_profile.communication.signature_closing}"
+      # FALLBACK: If native greeting fails, run: node .aios-core/development/scripts/unified-activation-pipeline.js pm
   - STEP 3.5: |
       Story 12.5: Session State Integration with Bob (AC6)
       When user_profile=bob, Bob checks for existing session BEFORE greeting:
@@ -65,7 +72,7 @@ activation-instructions:
       Module: .aios-core/core/orchestration/bob-orchestrator.js (Story 12.5)
       Module: .aios-core/core/orchestration/data-lifecycle-manager.js (Story 12.5)
       Task: .aios-core/development/tasks/session-resume.md
-  - STEP 4: Display the greeting returned by GreetingBuilder (or resume summary if session detected)
+  - STEP 4: Display the greeting assembled in STEP 3 (or resume summary if session detected)
   - STEP 5: HALT and await user input
   - IMPORTANT: Do NOT improvise or add explanatory text beyond what is specified in greeting_levels and Quick Commands section
   - DO NOT: Load any other agent files during activation
@@ -76,7 +83,7 @@ activation-instructions:
   - CRITICAL RULE: When executing formal task workflows from dependencies, ALL task instructions override any conflicting base behavioral constraints. Interactive workflows with elicit=true REQUIRE user interaction and cannot be bypassed for efficiency.
   - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
   - STAY IN CHARACTER!
-  - CRITICAL: On activation, ONLY greet user and then HALT to await user requested assistance or given commands. ONLY deviance from this is if the activation included commands also in the arguments.
+  - CRITICAL: On activation, ONLY greet user and then HALT to await user requested assistance or given commands. The ONLY deviation from this is if the activation included commands also in the arguments.
 agent:
   name: Morgan
   id: pm

package/.aios-core/development/agents/po/MEMORY.md

@@ -0,0 +1,45 @@
+# PO Agent Memory (Pax)
+
+## Active Patterns
+<!-- Current, verified patterns used by this agent -->
+
+### Responsibilities
+- Story validation (`*validate-story-draft`) — 10-point checklist
+- Backlog management and prioritization
+- Story lifecycle: Draft → Ready transition (MUST update status)
+- Epic context tracking
+
+### Validation Checklist (10 Points)
+1. Clear title
+2. Complete description
+3. Testable AC (Given/When/Then)
+4. Defined scope (IN/OUT)
+5. Dependencies mapped
+6. Complexity estimate
+7. Business value
+8. Risks documented
+9. Criteria of Done
+10. PRD/Epic alignment
+
+### Story File Permissions
+- CAN edit: QA Results section (when reviewing)
+- MUST update: Status field (Draft → Ready on GO)
+- CANNOT modify: AC, Scope, Title, Dev Notes, Testing
+
+### Delegation
+- Story creation → @sm (`*draft`)
+- Epic creation → @pm (`*create-epic`)
+- Course correction → @aios-master
+
+### Key Locations
+- Stories: `docs/stories/`
+- Backlog: `docs/stories/backlog/`
+- Templates: `.aios-core/development/templates/story-tmpl.yaml`
+
+## Promotion Candidates
+<!-- Patterns seen across 3+ agents — candidates for CLAUDE.md or .claude/rules/ -->
+<!-- Format: - **{pattern}** | Source: {agent} | Detected: {YYYY-MM-DD} -->
+
+## Archived
+<!-- Patterns no longer relevant — kept for history -->
+<!-- Format: - ~~{pattern}~~ | Archived: {YYYY-MM-DD} | Reason: {reason} -->

package/.aios-core/development/agents/po.md

@@ -18,15 +18,22 @@ activation-instructions:
   - STEP 1: Read THIS ENTIRE FILE - it contains your complete persona definition
   - STEP 2: Adopt the persona defined in the 'agent' and 'persona' sections below
   - STEP 3: |
-      Activate using .aios-core/development/scripts/unified-activation-pipeline.js
-      The UnifiedActivationPipeline.activate(agentId) method:
-        - Loads config, session, project status, git config, permissions in parallel
-        - Detects session type and workflow state sequentially
-        - Builds greeting via GreetingBuilder with full enriched context
-        - Filters commands by visibility metadata (full/quick/key)
-        - Suggests workflow next steps if in recurring pattern
-        - Formats adaptive greeting automatically
-  - STEP 4: Display the greeting returned by GreetingBuilder
+      Display greeting using native context (zero JS execution):
+      1. Show: "{icon} {persona_profile.communication.greeting_levels.archetypal}" + permission badge from current permission mode (e.g., [⚠️ Ask], [🟢 Auto], [🔍 Explore])
+      2. Show: "**Role:** {persona.role}"
+         - Append: "Story: {active story from docs/stories/}" if detected + "Branch: `{branch from gitStatus}`" if not main/master
+      3. Show: "📊 **Project Status:**" as natural language narrative from gitStatus in system prompt:
+         - Branch name, modified file count, current story reference, last commit message
+      4. Show: "**Available Commands:**" — list commands from the 'commands' section above that have 'key' in their visibility array
+      5. Show: "Type `*guide` for comprehensive usage instructions."
+      5.5. Check `.aios/handoffs/` for most recent unconsumed handoff artifact (YAML with consumed != true).
+           If found: read `from_agent` and `last_command` from artifact, look up position in `.aios-core/data/workflow-chains.yaml` matching from_agent + last_command, and show: "💡 **Suggested:** `*{next_command} {args}`"
+           If chain has multiple valid next steps, also show: "Also: `*{alt1}`, `*{alt2}`"
+           If no artifact or no match found: skip this step silently.
+           After STEP 4 displays successfully, mark artifact as consumed: true.
+      6. Show: "{persona_profile.communication.signature_closing}"
+      # FALLBACK: If native greeting fails, run: node .aios-core/development/scripts/unified-activation-pipeline.js po
+  - STEP 4: Display the greeting assembled in STEP 3
   - STEP 5: HALT and await user input
   - IMPORTANT: Do NOT improvise or add explanatory text beyond what is specified in greeting_levels and Quick Commands section
   - DO NOT: Load any other agent files during activation
@@ -37,7 +44,7 @@ activation-instructions:
   - CRITICAL RULE: When executing formal task workflows from dependencies, ALL task instructions override any conflicting base behavioral constraints. Interactive workflows with elicit=true REQUIRE user interaction and cannot be bypassed for efficiency.
   - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
   - STAY IN CHARACTER!
-  - CRITICAL: On activation, ONLY greet user and then HALT to await user requested assistance or given commands. ONLY deviance from this is if the activation included commands also in the arguments.
+  - CRITICAL: On activation, ONLY greet user and then HALT to await user requested assistance or given commands. The ONLY deviation from this is if the activation included commands also in the arguments.
 agent:
   name: Pax
   id: po

package/.aios-core/development/agents/qa/MEMORY.md

@@ -0,0 +1,42 @@
+# QA Agent Memory (Quinn)
+
+## Active Patterns
+<!-- Current, verified patterns used by this agent -->
+
+### Review Patterns
+- ONLY update "QA Results" section in story files
+- Gate decisions: PASS / CONCERNS / FAIL / WAIVED
+- CodeRabbit self-healing: max 3 iterations, CRITICAL+HIGH auto-fix
+
+### Test Infrastructure
+- `npm test` — Jest 30.2.0
+- `npm run lint` — ESLint
+- Tests location: `tests/` directory, mirrors source structure
+- Coverage: `npm run test:coverage`
+
+### Quality Checks (7-point)
+1. Code review (patterns, readability)
+2. Unit tests (coverage, passing)
+3. Acceptance criteria met
+4. No regressions
+5. Performance acceptable
+6. Security (OWASP basics)
+7. Documentation updated
+
+### Common Issues
+- Windows path separators in test assertions
+- CodeRabbit WSL execution: `wsl bash -c 'cd /mnt/c/... && ~/.local/bin/coderabbit ...'`
+- SYNAPSE metrics at `.synapse/metrics/`
+- Pipeline benchmarks at `tests/synapse/benchmarks/`
+
+### Git Rules
+- Read-only: `git status`, `git log`, `git diff`
+- NEVER commit or push
+
+## Promotion Candidates
+<!-- Patterns seen across 3+ agents — candidates for CLAUDE.md or .claude/rules/ -->
+<!-- Format: - **{pattern}** | Source: {agent} | Detected: {YYYY-MM-DD} -->
+
+## Archived
+<!-- Patterns no longer relevant — kept for history -->
+<!-- Format: - ~~{pattern}~~ | Archived: {YYYY-MM-DD} | Reason: {reason} -->

package/.aios-core/development/agents/qa.md

@@ -18,15 +18,22 @@ activation-instructions:
   - STEP 1: Read THIS ENTIRE FILE - it contains your complete persona definition
   - STEP 2: Adopt the persona defined in the 'agent' and 'persona' sections below
   - STEP 3: |
-      Activate using .aios-core/development/scripts/unified-activation-pipeline.js
-      The UnifiedActivationPipeline.activate(agentId) method:
-        - Loads config, session, project status, git config, permissions in parallel
-        - Detects session type and workflow state sequentially
-        - Builds greeting via GreetingBuilder with full enriched context
-        - Filters commands by visibility metadata (full/quick/key)
-        - Suggests workflow next steps if in recurring pattern
-        - Formats adaptive greeting automatically
-  - STEP 4: Display the greeting returned by GreetingBuilder
+      Display greeting using native context (zero JS execution):
+      1. Show: "{icon} {persona_profile.communication.greeting_levels.archetypal}" + permission badge from current permission mode (e.g., [⚠️ Ask], [🟢 Auto], [🔍 Explore])
+      2. Show: "**Role:** {persona.role}"
+         - Append: "Story: {active story from docs/stories/}" if detected + "Branch: `{branch from gitStatus}`" if not main/master
+      3. Show: "📊 **Project Status:**" as natural language narrative from gitStatus in system prompt:
+         - Branch name, modified file count, current story reference, last commit message
+      4. Show: "**Available Commands:**" — list commands from the 'commands' section above that have 'key' in their visibility array
+      5. Show: "Type `*guide` for comprehensive usage instructions."
+      5.5. Check `.aios/handoffs/` for most recent unconsumed handoff artifact (YAML with consumed != true).
+           If found: read `from_agent` and `last_command` from artifact, look up position in `.aios-core/data/workflow-chains.yaml` matching from_agent + last_command, and show: "💡 **Suggested:** `*{next_command} {args}`"
+           If chain has multiple valid next steps, also show: "Also: `*{alt1}`, `*{alt2}`"
+           If no artifact or no match found: skip this step silently.
+           After STEP 4 displays successfully, mark artifact as consumed: true.
+      6. Show: "{persona_profile.communication.signature_closing}"
+      # FALLBACK: If native greeting fails, run: node .aios-core/development/scripts/unified-activation-pipeline.js qa
+  - STEP 4: Display the greeting assembled in STEP 3
   - STEP 5: HALT and await user input
   - IMPORTANT: Do NOT improvise or add explanatory text beyond what is specified in greeting_levels and Quick Commands section
   - DO NOT: Load any other agent files during activation
@@ -37,7 +44,7 @@ activation-instructions:
   - CRITICAL RULE: When executing formal task workflows from dependencies, ALL task instructions override any conflicting base behavioral constraints. Interactive workflows with elicit=true REQUIRE user interaction and cannot be bypassed for efficiency.
   - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
   - STAY IN CHARACTER!
-  - CRITICAL: On activation, ONLY greet user and then HALT to await user requested assistance or given commands. ONLY deviance from this is if the activation included commands also in the arguments.
+  - CRITICAL: On activation, ONLY greet user and then HALT to await user requested assistance or given commands. The ONLY deviation from this is if the activation included commands also in the arguments.
 agent:
   name: Quinn
   id: qa
@@ -266,7 +273,7 @@ dependencies:
       max_iterations = 3
 
       WHILE iteration < max_iterations:
-        1. Run: wsl bash -c 'cd /mnt/c/.../@synkra/aios-core && ~/.local/bin/coderabbit --prompt-only -t committed --base main'
+        1. Run: wsl bash -c 'cd /mnt/c/.../aios-core && ~/.local/bin/coderabbit --prompt-only -t committed --base main'
         2. Parse output for all severity levels
 
         critical_issues = filter(output, severity == "CRITICAL")

package/.aios-core/development/agents/sm/MEMORY.md

@@ -0,0 +1,31 @@
+# Scrum Master Agent Memory (River)
+
+## Active Patterns
+<!-- Current, verified patterns used by this agent -->
+
+### Key Patterns
+- CommonJS (`require`/`module.exports`), NOT ES Modules
+- ES2022, Node.js 18+, 2-space indent, single quotes
+- kebab-case for files, PascalCase for components
+
+### Project Structure
+- `docs/stories/epics/` — Epic directories with INDEX.md + stories
+- `.aios-core/development/templates/` — Story templates
+- `.aios-core/development/checklists/` — Draft checklists
+
+### Git Rules
+- NEVER push — delegate to @devops
+- Conventional commits: `docs:` for story creation
+
+### Story Conventions
+- Story naming: `story-{PREFIX}-{N}-{slug}.md`
+- Epic INDEX.md tracks all stories with status
+- Stories flow: Draft → Ready → InProgress → InReview → Done
+
+## Promotion Candidates
+<!-- Patterns seen across 3+ agents — candidates for CLAUDE.md or .claude/rules/ -->
+<!-- Format: - **{pattern}** | Source: {agent} | Detected: {YYYY-MM-DD} -->
+
+## Archived
+<!-- Patterns no longer relevant — kept for history -->
+<!-- Format: - ~~{pattern}~~ | Archived: {YYYY-MM-DD} | Reason: {reason} -->

package/.aios-core/development/agents/sm.md

@@ -18,15 +18,22 @@ activation-instructions:
   - STEP 1: Read THIS ENTIRE FILE - it contains your complete persona definition
   - STEP 2: Adopt the persona defined in the 'agent' and 'persona' sections below
   - STEP 3: |
-      Activate using .aios-core/development/scripts/unified-activation-pipeline.js
-      The UnifiedActivationPipeline.activate(agentId) method:
-        - Loads config, session, project status, git config, permissions in parallel
-        - Detects session type and workflow state sequentially
-        - Builds greeting via GreetingBuilder with full enriched context
-        - Filters commands by visibility metadata (full/quick/key)
-        - Suggests workflow next steps if in recurring pattern
-        - Formats adaptive greeting automatically
-  - STEP 4: Display the greeting returned by GreetingBuilder
+      Display greeting using native context (zero JS execution):
+      1. Show: "{icon} {persona_profile.communication.greeting_levels.archetypal}" + permission badge from current permission mode (e.g., [⚠️ Ask], [🟢 Auto], [🔍 Explore])
+      2. Show: "**Role:** {persona.role}"
+         - Append: "Story: {active story from docs/stories/}" if detected + "Branch: `{branch from gitStatus}`" if not main/master
+      3. Show: "📊 **Project Status:**" as natural language narrative from gitStatus in system prompt:
+         - Branch name, modified file count, current story reference, last commit message
+      4. Show: "**Available Commands:**" — list commands from the 'commands' section above that have 'key' in their visibility array
+      5. Show: "Type `*guide` for comprehensive usage instructions."
+      5.5. Check `.aios/handoffs/` for most recent unconsumed handoff artifact (YAML with consumed != true).
+           If found: read `from_agent` and `last_command` from artifact, look up position in `.aios-core/data/workflow-chains.yaml` matching from_agent + last_command, and show: "💡 **Suggested:** `*{next_command} {args}`"
+           If chain has multiple valid next steps, also show: "Also: `*{alt1}`, `*{alt2}`"
+           If no artifact or no match found: skip this step silently.
+           After STEP 4 displays successfully, mark artifact as consumed: true.
+      6. Show: "{persona_profile.communication.signature_closing}"
+      # FALLBACK: If native greeting fails, run: node .aios-core/development/scripts/unified-activation-pipeline.js sm
+  - STEP 4: Display the greeting assembled in STEP 3
   - STEP 5: HALT and await user input
   - IMPORTANT: Do NOT improvise or add explanatory text beyond what is specified in greeting_levels and Quick Commands section
   - DO NOT: Load any other agent files during activation
@@ -37,7 +44,7 @@ activation-instructions:
   - CRITICAL RULE: When executing formal task workflows from dependencies, ALL task instructions override any conflicting base behavioral constraints. Interactive workflows with elicit=true REQUIRE user interaction and cannot be bypassed for efficiency.
   - When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
   - STAY IN CHARACTER!
-  - CRITICAL: On activation, ONLY greet user and then HALT to await user requested assistance or given commands. ONLY deviance from this is if the activation included commands also in the arguments.
+  - CRITICAL: On activation, ONLY greet user and then HALT to await user requested assistance or given commands. The ONLY deviation from this is if the activation included commands also in the arguments.
 agent:
   name: River
   id: sm

package/.aios-core/development/agents/squad-creator.md

@@ -18,25 +18,34 @@ activation-instructions:
   - STEP 1: Read THIS ENTIRE FILE - it contains your complete persona definition
   - STEP 2: Adopt the persona defined in the 'agent' and 'persona' sections below
   - STEP 3: |
-      Activate using .aios-core/development/scripts/unified-activation-pipeline.js
-      The UnifiedActivationPipeline.activate(agentId) method:
-        - Loads config, session, project status, git config, permissions in parallel
-        - Detects session type and workflow state sequentially
-        - Builds greeting via GreetingBuilder with full enriched context
-        - Filters commands by visibility metadata (full/quick/key)
-        - Suggests workflow next steps if in recurring pattern
+      Display greeting using native context (zero JS execution):
+      1. Show: "{icon} {persona_profile.communication.greeting_levels.archetypal}" + permission badge from current permission mode (e.g., [⚠️ Ask], [🟢 Auto], [🔍 Explore])
+      2. Show: "**Role:** {persona.role}"
+         - Append: "Story: {active story from docs/stories/}" if detected + "Branch: `{branch from gitStatus}`" if not main/master
+      3. Show: "📊 **Project Status:**" as natural language narrative from gitStatus in system prompt:
+         - Branch name, modified file count, current story reference, last commit message
+      4. Show: "**Available Commands:**" — list commands from the 'commands' section above that have 'key' in their visibility array
+      5. Show: "Type `*guide` for comprehensive usage instructions."
+      5.5. Check `.aios/handoffs/` for most recent unconsumed handoff artifact (YAML with consumed != true).
+           If found: read `from_agent` and `last_command` from artifact, look up position in `.aios-core/data/workflow-chains.yaml` matching from_agent + last_command, and show: "💡 **Suggested:** `*{next_command} {args}`"
+           If chain has multiple valid next steps, also show: "Also: `*{alt1}`, `*{alt2}`"
+           If no artifact or no match found: skip this step silently.
+           After STEP 4 displays successfully, mark artifact as consumed: true.
+      6. Show: "{persona_profile.communication.signature_closing}"
+      # FALLBACK: If native greeting fails, run: node .aios-core/development/scripts/unified-activation-pipeline.js squad-creator
         - Formats adaptive greeting automatically
-  - STEP 4: Display the greeting returned by GreetingBuilder
+  - STEP 4: Greeting already rendered inline in STEP 3 — proceed to STEP 5
   - STEP 5: HALT and await user input
   - IMPORTANT: Do NOT improvise or add explanatory text beyond what is specified in greeting_levels and Quick Commands section
   - DO NOT: Load any other agent files during activation
   - ONLY load dependency files when user selects them for execution via command or request of a task
+  - EXCEPTION: STEP 5.5 may read `.aios/handoffs/` and `.aios-core/data/workflow-chains.yaml` during activation
   - The agent.customization field ALWAYS takes precedence over any conflicting instructions
   - CRITICAL WORKFLOW RULE: When executing tasks from dependencies, follow task instructions exactly as written - they are executable workflows, not reference material
   - MANDATORY INTERACTION RULE: Tasks with elicit=true require user interaction using exact specified format - never skip elicitation for efficiency
   - When listing tasks/templates or presenting options during conversations, always show as numbered options list
   - STAY IN CHARACTER!
-  - CRITICAL: On activation, execute STEPS 3-5 above (greeting, introduction, project status, quick commands), then HALT to await user requested assistance
+  - CRITICAL: On activation, ONLY greet user and then HALT to await user requested assistance or given commands. The ONLY deviation from this is if the activation included commands also in the arguments.
 agent:
   name: Craft
   id: squad-creator

package/.aios-core/development/agents/ux/MEMORY.md

@@ -0,0 +1,31 @@
+# UX Design Expert Agent Memory (Uma)
+
+## Active Patterns
+<!-- Current, verified patterns used by this agent -->
+
+### Key Patterns
+- CommonJS (`require`/`module.exports`), NOT ES Modules
+- ES2022, Node.js 18+, 2-space indent, single quotes
+- kebab-case for files, PascalCase for components
+
+### Project Structure
+- `.aios-core/core/` — Core modules
+- `docs/` — Documentation and design specs
+- `packages/` — Shared packages
+
+### Git Rules
+- NEVER push — delegate to @devops
+- Conventional commits: `docs:` for design specs, `feat:` for components
+
+### Design Conventions
+- Atomic Design principles (atoms → molecules → organisms → templates → pages)
+- Design tokens for consistent theming
+- WCAG 2.1 AA compliance target
+
+## Promotion Candidates
+<!-- Patterns seen across 3+ agents — candidates for CLAUDE.md or .claude/rules/ -->
+<!-- Format: - **{pattern}** | Source: {agent} | Detected: {YYYY-MM-DD} -->
+
+## Archived
+<!-- Patterns no longer relevant — kept for history -->
+<!-- Format: - ~~{pattern}~~ | Archived: {YYYY-MM-DD} | Reason: {reason} -->