agileflow 2.93.0 → 2.94.1

package/src/core/commands/help.md

@@ -8,7 +8,69 @@ compact_context:
     - "ACTIVE COMMAND: /agileflow:help - System guide (display-only, no file writes)"
     - "MUST output markdown (never writes files)"
     - "MUST show folder map, concepts, daily workflow, all commands"
-    - "Include dynamic injection: <!-- {{COMMAND_LIST}} -->"
+    - "Include dynamic injection: Available commands (61 total):
+- `/agileflow:adr NUMBER=<number> TITLE=<text> CONTEXT=<text> DECISION=<text> CONSEQUENCES=<text> \[LINKS=<text>\]` - Create an Architecture Decision Record
+- `/agileflow:adr-list` - List all Architecture Decision Records
+- `/agileflow:adr-update NUMBER=<number> \[STATUS=<status>\] \[REASON=<text>\]` - Update ADR status or content
+- `/agileflow:adr-view NUMBER=<number>` - View ADR details with contextual actions
+- `/agileflow:agent AGENT\_ID=<id> ROLE=<text> \[TOOLS=<list>\] \[SCOPE=<list>\]` - Onboard a new agent with profile and contract
+- `/agileflow:assign STORY=<US\-ID> NEW\_OWNER=<id> \[NEW\_STATUS=<status>\] \[NOTE=<text>\]` - Assign or reassign a story to an owner
+- `/agileflow:audit STORY=<US\-ID>` - Audit story completion \- tests \+ acceptance criteria verification \(GSD pattern\)
+- `/agileflow:auto SOURCE=<path\|url> \[EPIC=<EP\-ID>\] \[OWNER=<id>\] \[AUTO\_CREATE=true\|false\]` - Auto\-generate stories from PRDs, mockups, or specs
+- `/agileflow:baseline` - Mark current state as verified baseline
+- `/agileflow:batch <operation> <pattern> \[<action>\]` - Process multiple items with functional patterns \(map/pmap/filter/reduce\)
+- `/agileflow:changelog \(no arguments\)` - Auto\-generate changelog from commit history
+- `/agileflow:choose <decision> \[<context>\]` - AI\-directed decision making with structured options
+- `/agileflow:ci \(no arguments\)` - Bootstrap CI/CD workflow with testing and quality checks
+- `/agileflow:council <question> \[--mode parallel\|debate\] \[--rounds N\]` - Convene AI Council for strategic decisions with three perspectives \(Optimist, Advocate, Analyst\)
+- `/agileflow:compress \(no arguments\)` - Compress status\.json by removing verbose fields and keeping only tracking metadata
+- `/agileflow:context-export \(no arguments\)` - Export concise context excerpt for web AI tools
+- `/agileflow:context-full \(no arguments\)` - Generate/refresh full context brief for web AI tools
+- `/agileflow:context-note NOTE=<text>` - Add timestamped note to context file
+- `/agileflow:debt \(no arguments\)` - Track and prioritize technical debt items
+- `/agileflow:deploy \(no arguments\)` - Set up automated deployment pipeline
+- `/agileflow:diagnose \(no arguments\)` - System health diagnostics
+- `/agileflow:epic EPIC=<EP\-ID> TITLE=<text> OWNER=<id> GOAL=<text> \[STORIES=<list>\] \[RESEARCH=<file>\]` - Create a new epic with stories
+- `/agileflow:epic-list` - List all epics with status and progress
+- `/agileflow:epic-view EPIC=<EP\-ID>` - View epic details with stories and contextual actions
+- `/agileflow:feedback \(no arguments\)` - Collect and process agent feedback
+- `/agileflow:handoff STORY=<US\-ID> FROM=<id> TO=<id> \[SUMMARY=<text>\] \[BLOCKERS=<list>\]` - Document work handoff between agents
+- `/agileflow:help \(no arguments\)` - Display AgileFlow system overview and commands
+- `/agileflow:multi-expert <question>` - Deploy multiple domain experts on the same problem for higher confidence
+- `/agileflow:packages \(no arguments\)` - Manage dependencies with updates and security audits
+- `/agileflow:pr STORY=<US\-ID> \[TITLE=<text>\] \[TEST\_EVIDENCE=<text>\]` - Generate pull request description from story
+- `/agileflow:readme-sync FOLDER=<path>\|all` - Synchronize a folder's README\.md with its current contents
+- `/agileflow:research-analyze` - Analyze existing research for implementation in your project
+- `/agileflow:research-ask TOPIC=<text> \[DETAILS=<text>\] \[ERROR=<text>\]` - Generate detailed research prompt for web AI tools \(ChatGPT, Perplexity, etc\.\)
+- `/agileflow:research-import TOPIC=<text> \[CONTENT=<text>\] \[SOURCE=<url>\]` - Import research results and save to research folder
+- `/agileflow:research-list \(no arguments\)` - Show research notes index
+- `/agileflow:research-view FILE=<filename>` - Read a specific research note
+- `/agileflow:rlm DOCUMENT=<path> QUERY=<text> \[MAX\_ITERATIONS=<number>\] \[DEPTH=<number>\]` - Analyze complex documents using RLM \(Recursive Language Models\) pattern
+- `/agileflow:session-cleanup \(no arguments\)` - Interactive session cleanup with AI assessment
+- `/agileflow:session-end \(no arguments\)` - Cleanly end session with optional merge to main
+- `/agileflow:session-history` - View past session history and metrics
+- `/agileflow:session-init \(no arguments\)` - Initialize session harness with test verification
+- `/agileflow:session-new \(no arguments\)` - Create a new parallel session with git worktree
+- `/agileflow:session-resume \(no arguments\)` - Pick a session to switch to or resume
+- `/agileflow:session-spawn` - Spawn multiple parallel Claude Code sessions in git worktrees
+- `/agileflow:session-status` - View current session state and activity
+- `/agileflow:skill-create` - Generate a custom skill with web research, cookbook pattern, and MCP integration
+- `/agileflow:skill-delete` - Remove an installed skill from \.claude/skills/
+- `/agileflow:skill-edit` - Edit an existing skill's SKILL\.md, cookbook entries, or references
+- `/agileflow:skill-list \(no arguments\)` - List all installed skills with their descriptions and status
+- `/agileflow:skill-test` - Verify a skill works correctly by testing its activation and functionality
+- `/agileflow:skill-upgrade` - Upgrade existing skills with self\-improving learning capability
+- `/agileflow:status STORY=<US\-ID> STATUS=<status> \[SUMMARY=<text>\] \[PR=<url>\] \[TO=<agent\-id>\]` - Update story status and progress
+- `/agileflow:story EPIC=<EP\-ID> STORY=<US\-ID> TITLE=<text> OWNER=<id> \[ESTIMATE=<pts>\] \[AC=<list>\] \[TDD=true\]` - Create a user story with acceptance criteria
+- `/agileflow:story-validate STORY=<US\-ID>` - Validate story completeness before development
+- `/agileflow:story-view STORY=<US\-ID>` - View story details with contextual actions
+- `/agileflow:template ACTION=create\|edit\|list\|use \[TYPE=story\|epic\|adr\|custom\] \[NAME=<name>\]` - Create and manage custom document templates
+- `/agileflow:tests \(no arguments\)` - Set up automated testing infrastructure
+- `/agileflow:validate-expertise` - Validate expertise files for drift and staleness
+- `/agileflow:verify` - Run project tests and update story test status
+- `/agileflow:whats-new \(no arguments\)` - Show what's new in AgileFlow
+- `/agileflow:workflow <template> \[<arguments>\]` - Define and run parameterized workflow templates
+"
   state_fields:
     - display_mode
 ---
@@ -61,7 +123,69 @@ Output includes:
 - Daily flow: Pick story → Implement to AC → Tests → PR → Update status
 - WIP limit: max 2 stories/agent
 - All available commands with examples
-- Dynamic injection: <!-- {{COMMAND_LIST}} -->
+- Dynamic injection: Available commands (61 total):
+- `/agileflow:adr NUMBER=<number> TITLE=<text> CONTEXT=<text> DECISION=<text> CONSEQUENCES=<text> \[LINKS=<text>\]` - Create an Architecture Decision Record
+- `/agileflow:adr-list` - List all Architecture Decision Records
+- `/agileflow:adr-update NUMBER=<number> \[STATUS=<status>\] \[REASON=<text>\]` - Update ADR status or content
+- `/agileflow:adr-view NUMBER=<number>` - View ADR details with contextual actions
+- `/agileflow:agent AGENT\_ID=<id> ROLE=<text> \[TOOLS=<list>\] \[SCOPE=<list>\]` - Onboard a new agent with profile and contract
+- `/agileflow:assign STORY=<US\-ID> NEW\_OWNER=<id> \[NEW\_STATUS=<status>\] \[NOTE=<text>\]` - Assign or reassign a story to an owner
+- `/agileflow:audit STORY=<US\-ID>` - Audit story completion \- tests \+ acceptance criteria verification \(GSD pattern\)
+- `/agileflow:auto SOURCE=<path\|url> \[EPIC=<EP\-ID>\] \[OWNER=<id>\] \[AUTO\_CREATE=true\|false\]` - Auto\-generate stories from PRDs, mockups, or specs
+- `/agileflow:baseline` - Mark current state as verified baseline
+- `/agileflow:batch <operation> <pattern> \[<action>\]` - Process multiple items with functional patterns \(map/pmap/filter/reduce\)
+- `/agileflow:changelog \(no arguments\)` - Auto\-generate changelog from commit history
+- `/agileflow:choose <decision> \[<context>\]` - AI\-directed decision making with structured options
+- `/agileflow:ci \(no arguments\)` - Bootstrap CI/CD workflow with testing and quality checks
+- `/agileflow:council <question> \[--mode parallel\|debate\] \[--rounds N\]` - Convene AI Council for strategic decisions with three perspectives \(Optimist, Advocate, Analyst\)
+- `/agileflow:compress \(no arguments\)` - Compress status\.json by removing verbose fields and keeping only tracking metadata
+- `/agileflow:context-export \(no arguments\)` - Export concise context excerpt for web AI tools
+- `/agileflow:context-full \(no arguments\)` - Generate/refresh full context brief for web AI tools
+- `/agileflow:context-note NOTE=<text>` - Add timestamped note to context file
+- `/agileflow:debt \(no arguments\)` - Track and prioritize technical debt items
+- `/agileflow:deploy \(no arguments\)` - Set up automated deployment pipeline
+- `/agileflow:diagnose \(no arguments\)` - System health diagnostics
+- `/agileflow:epic EPIC=<EP\-ID> TITLE=<text> OWNER=<id> GOAL=<text> \[STORIES=<list>\] \[RESEARCH=<file>\]` - Create a new epic with stories
+- `/agileflow:epic-list` - List all epics with status and progress
+- `/agileflow:epic-view EPIC=<EP\-ID>` - View epic details with stories and contextual actions
+- `/agileflow:feedback \(no arguments\)` - Collect and process agent feedback
+- `/agileflow:handoff STORY=<US\-ID> FROM=<id> TO=<id> \[SUMMARY=<text>\] \[BLOCKERS=<list>\]` - Document work handoff between agents
+- `/agileflow:help \(no arguments\)` - Display AgileFlow system overview and commands
+- `/agileflow:multi-expert <question>` - Deploy multiple domain experts on the same problem for higher confidence
+- `/agileflow:packages \(no arguments\)` - Manage dependencies with updates and security audits
+- `/agileflow:pr STORY=<US\-ID> \[TITLE=<text>\] \[TEST\_EVIDENCE=<text>\]` - Generate pull request description from story
+- `/agileflow:readme-sync FOLDER=<path>\|all` - Synchronize a folder's README\.md with its current contents
+- `/agileflow:research-analyze` - Analyze existing research for implementation in your project
+- `/agileflow:research-ask TOPIC=<text> \[DETAILS=<text>\] \[ERROR=<text>\]` - Generate detailed research prompt for web AI tools \(ChatGPT, Perplexity, etc\.\)
+- `/agileflow:research-import TOPIC=<text> \[CONTENT=<text>\] \[SOURCE=<url>\]` - Import research results and save to research folder
+- `/agileflow:research-list \(no arguments\)` - Show research notes index
+- `/agileflow:research-view FILE=<filename>` - Read a specific research note
+- `/agileflow:rlm DOCUMENT=<path> QUERY=<text> \[MAX\_ITERATIONS=<number>\] \[DEPTH=<number>\]` - Analyze complex documents using RLM \(Recursive Language Models\) pattern
+- `/agileflow:session-cleanup \(no arguments\)` - Interactive session cleanup with AI assessment
+- `/agileflow:session-end \(no arguments\)` - Cleanly end session with optional merge to main
+- `/agileflow:session-history` - View past session history and metrics
+- `/agileflow:session-init \(no arguments\)` - Initialize session harness with test verification
+- `/agileflow:session-new \(no arguments\)` - Create a new parallel session with git worktree
+- `/agileflow:session-resume \(no arguments\)` - Pick a session to switch to or resume
+- `/agileflow:session-spawn` - Spawn multiple parallel Claude Code sessions in git worktrees
+- `/agileflow:session-status` - View current session state and activity
+- `/agileflow:skill-create` - Generate a custom skill with web research, cookbook pattern, and MCP integration
+- `/agileflow:skill-delete` - Remove an installed skill from \.claude/skills/
+- `/agileflow:skill-edit` - Edit an existing skill's SKILL\.md, cookbook entries, or references
+- `/agileflow:skill-list \(no arguments\)` - List all installed skills with their descriptions and status
+- `/agileflow:skill-test` - Verify a skill works correctly by testing its activation and functionality
+- `/agileflow:skill-upgrade` - Upgrade existing skills with self\-improving learning capability
+- `/agileflow:status STORY=<US\-ID> STATUS=<status> \[SUMMARY=<text>\] \[PR=<url>\] \[TO=<agent\-id>\]` - Update story status and progress
+- `/agileflow:story EPIC=<EP\-ID> STORY=<US\-ID> TITLE=<text> OWNER=<id> \[ESTIMATE=<pts>\] \[AC=<list>\] \[TDD=true\]` - Create a user story with acceptance criteria
+- `/agileflow:story-validate STORY=<US\-ID>` - Validate story completeness before development
+- `/agileflow:story-view STORY=<US\-ID>` - View story details with contextual actions
+- `/agileflow:template ACTION=create\|edit\|list\|use \[TYPE=story\|epic\|adr\|custom\] \[NAME=<name>\]` - Create and manage custom document templates
+- `/agileflow:tests \(no arguments\)` - Set up automated testing infrastructure
+- `/agileflow:validate-expertise` - Validate expertise files for drift and staleness
+- `/agileflow:verify` - Run project tests and update story test status
+- `/agileflow:whats-new \(no arguments\)` - Show what's new in AgileFlow
+- `/agileflow:workflow <template> \[<arguments>\]` - Define and run parameterized workflow templates
+
 
 - **Related**: All AgileFlow commands, system documentation
 <!-- COMPACT_SUMMARY_END -->
@@ -89,7 +213,69 @@ Print a concise, one-screen overview:
 - WIP limit: max 2 stories/agent
 - List ALL available commands with one-line examples
 
-<!-- {{COMMAND_LIST}} -->
+Available commands (61 total):
+- `/agileflow:adr NUMBER=<number> TITLE=<text> CONTEXT=<text> DECISION=<text> CONSEQUENCES=<text> \[LINKS=<text>\]` - Create an Architecture Decision Record
+- `/agileflow:adr-list` - List all Architecture Decision Records
+- `/agileflow:adr-update NUMBER=<number> \[STATUS=<status>\] \[REASON=<text>\]` - Update ADR status or content
+- `/agileflow:adr-view NUMBER=<number>` - View ADR details with contextual actions
+- `/agileflow:agent AGENT\_ID=<id> ROLE=<text> \[TOOLS=<list>\] \[SCOPE=<list>\]` - Onboard a new agent with profile and contract
+- `/agileflow:assign STORY=<US\-ID> NEW\_OWNER=<id> \[NEW\_STATUS=<status>\] \[NOTE=<text>\]` - Assign or reassign a story to an owner
+- `/agileflow:audit STORY=<US\-ID>` - Audit story completion \- tests \+ acceptance criteria verification \(GSD pattern\)
+- `/agileflow:auto SOURCE=<path\|url> \[EPIC=<EP\-ID>\] \[OWNER=<id>\] \[AUTO\_CREATE=true\|false\]` - Auto\-generate stories from PRDs, mockups, or specs
+- `/agileflow:baseline` - Mark current state as verified baseline
+- `/agileflow:batch <operation> <pattern> \[<action>\]` - Process multiple items with functional patterns \(map/pmap/filter/reduce\)
+- `/agileflow:changelog \(no arguments\)` - Auto\-generate changelog from commit history
+- `/agileflow:choose <decision> \[<context>\]` - AI\-directed decision making with structured options
+- `/agileflow:ci \(no arguments\)` - Bootstrap CI/CD workflow with testing and quality checks
+- `/agileflow:council <question> \[--mode parallel\|debate\] \[--rounds N\]` - Convene AI Council for strategic decisions with three perspectives \(Optimist, Advocate, Analyst\)
+- `/agileflow:compress \(no arguments\)` - Compress status\.json by removing verbose fields and keeping only tracking metadata
+- `/agileflow:context-export \(no arguments\)` - Export concise context excerpt for web AI tools
+- `/agileflow:context-full \(no arguments\)` - Generate/refresh full context brief for web AI tools
+- `/agileflow:context-note NOTE=<text>` - Add timestamped note to context file
+- `/agileflow:debt \(no arguments\)` - Track and prioritize technical debt items
+- `/agileflow:deploy \(no arguments\)` - Set up automated deployment pipeline
+- `/agileflow:diagnose \(no arguments\)` - System health diagnostics
+- `/agileflow:epic EPIC=<EP\-ID> TITLE=<text> OWNER=<id> GOAL=<text> \[STORIES=<list>\] \[RESEARCH=<file>\]` - Create a new epic with stories
+- `/agileflow:epic-list` - List all epics with status and progress
+- `/agileflow:epic-view EPIC=<EP\-ID>` - View epic details with stories and contextual actions
+- `/agileflow:feedback \(no arguments\)` - Collect and process agent feedback
+- `/agileflow:handoff STORY=<US\-ID> FROM=<id> TO=<id> \[SUMMARY=<text>\] \[BLOCKERS=<list>\]` - Document work handoff between agents
+- `/agileflow:help \(no arguments\)` - Display AgileFlow system overview and commands
+- `/agileflow:multi-expert <question>` - Deploy multiple domain experts on the same problem for higher confidence
+- `/agileflow:packages \(no arguments\)` - Manage dependencies with updates and security audits
+- `/agileflow:pr STORY=<US\-ID> \[TITLE=<text>\] \[TEST\_EVIDENCE=<text>\]` - Generate pull request description from story
+- `/agileflow:readme-sync FOLDER=<path>\|all` - Synchronize a folder's README\.md with its current contents
+- `/agileflow:research-analyze` - Analyze existing research for implementation in your project
+- `/agileflow:research-ask TOPIC=<text> \[DETAILS=<text>\] \[ERROR=<text>\]` - Generate detailed research prompt for web AI tools \(ChatGPT, Perplexity, etc\.\)
+- `/agileflow:research-import TOPIC=<text> \[CONTENT=<text>\] \[SOURCE=<url>\]` - Import research results and save to research folder
+- `/agileflow:research-list \(no arguments\)` - Show research notes index
+- `/agileflow:research-view FILE=<filename>` - Read a specific research note
+- `/agileflow:rlm DOCUMENT=<path> QUERY=<text> \[MAX\_ITERATIONS=<number>\] \[DEPTH=<number>\]` - Analyze complex documents using RLM \(Recursive Language Models\) pattern
+- `/agileflow:session-cleanup \(no arguments\)` - Interactive session cleanup with AI assessment
+- `/agileflow:session-end \(no arguments\)` - Cleanly end session with optional merge to main
+- `/agileflow:session-history` - View past session history and metrics
+- `/agileflow:session-init \(no arguments\)` - Initialize session harness with test verification
+- `/agileflow:session-new \(no arguments\)` - Create a new parallel session with git worktree
+- `/agileflow:session-resume \(no arguments\)` - Pick a session to switch to or resume
+- `/agileflow:session-spawn` - Spawn multiple parallel Claude Code sessions in git worktrees
+- `/agileflow:session-status` - View current session state and activity
+- `/agileflow:skill-create` - Generate a custom skill with web research, cookbook pattern, and MCP integration
+- `/agileflow:skill-delete` - Remove an installed skill from \.claude/skills/
+- `/agileflow:skill-edit` - Edit an existing skill's SKILL\.md, cookbook entries, or references
+- `/agileflow:skill-list \(no arguments\)` - List all installed skills with their descriptions and status
+- `/agileflow:skill-test` - Verify a skill works correctly by testing its activation and functionality
+- `/agileflow:skill-upgrade` - Upgrade existing skills with self\-improving learning capability
+- `/agileflow:status STORY=<US\-ID> STATUS=<status> \[SUMMARY=<text>\] \[PR=<url>\] \[TO=<agent\-id>\]` - Update story status and progress
+- `/agileflow:story EPIC=<EP\-ID> STORY=<US\-ID> TITLE=<text> OWNER=<id> \[ESTIMATE=<pts>\] \[AC=<list>\] \[TDD=true\]` - Create a user story with acceptance criteria
+- `/agileflow:story-validate STORY=<US\-ID>` - Validate story completeness before development
+- `/agileflow:story-view STORY=<US\-ID>` - View story details with contextual actions
+- `/agileflow:template ACTION=create\|edit\|list\|use \[TYPE=story\|epic\|adr\|custom\] \[NAME=<name>\]` - Create and manage custom document templates
+- `/agileflow:tests \(no arguments\)` - Set up automated testing infrastructure
+- `/agileflow:validate-expertise` - Validate expertise files for drift and staleness
+- `/agileflow:verify` - Run project tests and update story test status
+- `/agileflow:whats-new \(no arguments\)` - Show what's new in AgileFlow
+- `/agileflow:workflow <template> \[<arguments>\]` - Define and run parameterized workflow templates
+
 
 OUTPUT: plain markdown only (no file writes)
 

package/src/core/commands/ideate.md

@@ -1,14 +1,14 @@
 ---
 description: Generate categorized improvement ideas using multi-expert analysis
-argument-hint: [SCOPE=all|security|perf|code|ux] [DEPTH=quick|deep] [OUTPUT=report|stories|both]
+argument-hint: [SCOPE=all|security|perf|code|ux] [DEPTH=quick|deep|ultradeep] [OUTPUT=report|stories|both]
 compact_context:
   priority: high
   preserve_rules:
     - "ACTIVE COMMAND: /agileflow:ideate - Ideation orchestrator with multi-expert analysis"
     - "CRITICAL: Deploy experts IN PARALLEL in ONE message with multiple Task calls"
     - "CRITICAL: Wait for all results before synthesis (use TaskOutput with block=true)"
-    - "CRITICAL: Confidence scoring: HIGH (2+ experts agree) | MEDIUM (1 expert with evidence) | LOW (vague, exclude)"
-    - "MUST parse arguments: SCOPE (all/security/perf/code/ux) | DEPTH (quick/deep) | OUTPUT (report/stories/both)"
+    - "CRITICAL: Confidence scoring varies by depth: quick/deep (HIGH=2+ agree) | ultradeep (HIGH=3+ agree)"
+    - "MUST parse arguments: SCOPE (all/security/perf/code/ux) | DEPTH (quick/deep/ultradeep) | OUTPUT (report/stories/both)"
     - "MUST categorize by domain: Security, Performance, Code Quality, UX, Testing, API/Architecture"
     - "MUST estimate effort for each idea: High/Medium/Low impact"
     - "Optional: Generate stories for HIGH-confidence items (if OUTPUT=stories or both)"
@@ -44,11 +44,11 @@ node .agileflow/scripts/obtain-context.js ideate
 /agileflow:ideate SCOPE=all DEPTH=quick OUTPUT=report
 ```
 
-**What It Does**: Deploy 4-6 domain experts → Each generates 3-5 ideas → Synthesize with confidence scoring → Categorized report
+**What It Does**: Deploy 4-15 domain experts → Each generates 3-5 ideas → Synthesize with confidence scoring → Categorized report
 
 **Arguments**:
 - `SCOPE=all|security|perf|code|ux` (default: all)
-- `DEPTH=quick|deep` (default: quick)
+- `DEPTH=quick|deep|ultradeep` (default: quick) — ultradeep uses 13 experts for ~65 ideas
 - `OUTPUT=report|stories|both` (default: report)
 
 ### Tool Usage Examples
@@ -87,7 +87,7 @@ node .agileflow/scripts/obtain-context.js ideate
 ```
 
 **Categories**: Security, Performance, Code Quality, UX/Design, Testing, API/Architecture
-**Confidence**: High (2+ experts agree), Medium (1 expert with evidence)
+**Confidence**: High (2+ experts agree; 3+ for ultradeep), Medium (1 expert with evidence)
 **Output**: `docs/08-project/ideation-<YYYYMMDD>.md` | Optional stories
 <!-- COMPACT_SUMMARY_END -->
 
@@ -104,7 +104,7 @@ node .agileflow/scripts/obtain-context.js ideate
 ┌─────────────────────────────────────────────────────────────┐
 │              IDEATION ORCHESTRATOR                          │
 │  1. Parse SCOPE to determine which experts                  │
-│  2. Deploy 4-6 experts IN PARALLEL                          │
+│  2. Deploy 4-13 experts IN PARALLEL (13 for ultradeep)      │
 │  3. Each expert generates 3-5 improvement ideas             │
 │  4. Collect and synthesize with confidence scoring          │
 │  5. Generate categorized report                             │
@@ -153,17 +153,20 @@ You coordinate multiple domain experts to generate improvement suggestions for t
 Parse the input arguments:
 
 **SCOPE** (which experts to deploy):
-| SCOPE | Experts |
-|-------|---------|
-| `all` (default) | security, performance, refactor, ui, testing, api (6 experts) |
-| `security` | security, api, testing (3 experts) |
-| `perf` | performance, database, api (3 experts) |
-| `code` | refactor, testing, api (3 experts) |
-| `ux` | ui, accessibility, api (3 experts) |
+| SCOPE | Experts (quick/deep) | Experts (ultradeep adds) |
+|-------|----------------------|--------------------------|
+| `all` (default) | security, performance, refactor, ui, testing, api (6) | + accessibility, compliance, database, monitoring, qa, analytics, documentation (13 total) |
+| `security` | security, api, testing (3) | + compliance, monitoring (5 total) |
+| `perf` | performance, database, api (3) | + monitoring, analytics (5 total) |
+| `code` | refactor, testing, api (3) | + documentation, qa (5 total) |
+| `ux` | ui, accessibility, api (3) | + design, analytics (5 total) |
 
 **DEPTH**:
 - `quick` (default): Each expert generates 3 ideas, focuses on high-impact only
 - `deep`: Each expert generates 5 ideas, includes lower-priority items
+- `ultradeep`: Deploy 13 experts (SCOPE=all) with 5 ideas each (~65 ideas), comprehensive coverage
+
+> **Note**: `DEPTH=ultradeep` is recommended for comprehensive audits, pre-release reviews, or quarterly codebase assessments. It deploys significantly more experts and takes longer to complete.
 
 **OUTPUT**:
 - `report` (default): Generate ideation report only
@@ -255,6 +258,103 @@ FORMAT each idea as:
 </invoke>
 ```
 
+**Example deployment for SCOPE=all DEPTH=ultradeep** (13 experts):
+
+```xml
+<!-- Deploy ALL 13 experts in a SINGLE message -->
+<invoke name="Task">
+<parameter name="description">Security ideation</parameter>
+<parameter name="prompt">[prompt with domain=security]</parameter>
+<parameter name="subagent_type">agileflow-security</parameter>
+<parameter name="run_in_background">true</parameter>
+</invoke>
+
+<invoke name="Task">
+<parameter name="description">Performance ideation</parameter>
+<parameter name="prompt">[prompt with domain=performance]</parameter>
+<parameter name="subagent_type">agileflow-performance</parameter>
+<parameter name="run_in_background">true</parameter>
+</invoke>
+
+<invoke name="Task">
+<parameter name="description">Code quality ideation</parameter>
+<parameter name="prompt">[prompt with domain=refactor]</parameter>
+<parameter name="subagent_type">agileflow-refactor</parameter>
+<parameter name="run_in_background">true</parameter>
+</invoke>
+
+<invoke name="Task">
+<parameter name="description">UX ideation</parameter>
+<parameter name="prompt">[prompt with domain=ui]</parameter>
+<parameter name="subagent_type">agileflow-ui</parameter>
+<parameter name="run_in_background">true</parameter>
+</invoke>
+
+<invoke name="Task">
+<parameter name="description">Testing ideation</parameter>
+<parameter name="prompt">[prompt with domain=testing]</parameter>
+<parameter name="subagent_type">agileflow-testing</parameter>
+<parameter name="run_in_background">true</parameter>
+</invoke>
+
+<invoke name="Task">
+<parameter name="description">API/Architecture ideation</parameter>
+<parameter name="prompt">[prompt with domain=api]</parameter>
+<parameter name="subagent_type">agileflow-api</parameter>
+<parameter name="run_in_background">true</parameter>
+</invoke>
+
+<!-- Additional ultradeep experts (7 more) -->
+<invoke name="Task">
+<parameter name="description">Accessibility ideation</parameter>
+<parameter name="prompt">[prompt with domain=accessibility]</parameter>
+<parameter name="subagent_type">agileflow-accessibility</parameter>
+<parameter name="run_in_background">true</parameter>
+</invoke>
+
+<invoke name="Task">
+<parameter name="description">Compliance ideation</parameter>
+<parameter name="prompt">[prompt with domain=compliance]</parameter>
+<parameter name="subagent_type">agileflow-compliance</parameter>
+<parameter name="run_in_background">true</parameter>
+</invoke>
+
+<invoke name="Task">
+<parameter name="description">Database ideation</parameter>
+<parameter name="prompt">[prompt with domain=database]</parameter>
+<parameter name="subagent_type">agileflow-database</parameter>
+<parameter name="run_in_background">true</parameter>
+</invoke>
+
+<invoke name="Task">
+<parameter name="description">Monitoring ideation</parameter>
+<parameter name="prompt">[prompt with domain=monitoring]</parameter>
+<parameter name="subagent_type">agileflow-monitoring</parameter>
+<parameter name="run_in_background">true</parameter>
+</invoke>
+
+<invoke name="Task">
+<parameter name="description">QA ideation</parameter>
+<parameter name="prompt">[prompt with domain=qa]</parameter>
+<parameter name="subagent_type">agileflow-qa</parameter>
+<parameter name="run_in_background">true</parameter>
+</invoke>
+
+<invoke name="Task">
+<parameter name="description">Analytics ideation</parameter>
+<parameter name="prompt">[prompt with domain=analytics]</parameter>
+<parameter name="subagent_type">agileflow-analytics</parameter>
+<parameter name="run_in_background">true</parameter>
+</invoke>
+
+<invoke name="Task">
+<parameter name="description">Documentation ideation</parameter>
+<parameter name="prompt">[prompt with domain=documentation]</parameter>
+<parameter name="subagent_type">agileflow-documentation</parameter>
+<parameter name="run_in_background">true</parameter>
+</invoke>
+```
+
 ### STEP 3: COLLECT RESULTS
 
 Wait for all experts to complete:
@@ -278,11 +378,13 @@ Analyze all expert ideas and synthesize:
 
 **Confidence Scoring**:
 
-| Confidence | Criteria | Action |
-|------------|----------|--------|
-| **HIGH** | 2+ experts suggest similar idea | Include prominently, recommend immediate action |
-| **MEDIUM** | 1 expert with specific evidence (file paths, metrics) | Include as opportunity |
-| **LOW** | 1 expert, vague/no evidence | Exclude from report |
+| Confidence | Criteria (quick/deep) | Criteria (ultradeep) | Action |
+|------------|----------------------|----------------------|--------|
+| **HIGH** | 2+ experts suggest similar idea | 3+ experts suggest similar idea | Include prominently, recommend immediate action |
+| **MEDIUM** | 1 expert with specific evidence | 1-2 experts with specific evidence | Include as opportunity |
+| **LOW** | 1 expert, vague/no evidence | 1-2 experts, vague/no evidence | Exclude from report |
+
+> For ultradeep mode, the higher threshold (3+) for HIGH confidence prevents noise from having many perspectives and ensures only truly cross-cutting concerns bubble up as top priorities.
 
 **Overlap Detection**:
 - Ideas about the same file/component from different experts = HIGH confidence
@@ -435,12 +537,35 @@ After generating output, present options:
 
 ---
 
+### Example: Ultradeep Execution
+
+**User**: `/agileflow:ideate SCOPE=all DEPTH=ultradeep OUTPUT=both`
+
+**Step 1**: Parse → SCOPE=all (13 experts), DEPTH=ultradeep (5 ideas each), OUTPUT=both
+
+**Step 2**: Deploy 13 experts in parallel (security, performance, refactor, ui, testing, api, accessibility, compliance, database, monitoring, qa, analytics, documentation)
+
+**Step 3**: Collect results (~65 raw ideas)
+
+**Step 4**: Synthesize with ultradeep thresholds:
+- 8 ideas mentioned by 3+ experts → HIGH confidence
+- 25 ideas with 1-2 experts + evidence → MEDIUM confidence
+- 32 ideas too vague or single expert without evidence → excluded
+
+**Step 5**: Generate report with 33 ideas, saved to `docs/08-project/ideation-20260106.md`
+
+**Step 6**: Generate 8 stories for HIGH-confidence items
+
+**Step 7**: Present next steps via AskUserQuestion
+
+---
+
 ## Arguments
 
 | Argument | Values | Default | Description |
 |----------|--------|---------|-------------|
 | SCOPE | all, security, perf, code, ux | all | Which domains to analyze |
-| DEPTH | quick, deep | quick | Number of ideas per expert (3 vs 5) |
+| DEPTH | quick, deep, ultradeep | quick | quick (3 ideas, 6 experts), deep (5 ideas, 6 experts), ultradeep (5 ideas, 13 experts) |
 | OUTPUT | report, stories, both | report | What to generate |
 
 {{argument}}

package/src/core/commands/session/end.md

@@ -106,6 +106,8 @@ Display:
 To resume later: cd {path} && claude
 ```
 
+Then proceed to **Step 4: Offer to Close Tab**.
+
 ### Step 3c: If "End and delete worktree" Selected
 
 ```bash
@@ -123,6 +125,8 @@ Display:
    git branch -d {branch}
 ```
 
+Then proceed to **Step 4: Offer to Close Tab**.
+
 ### Step 3d: If "Cancel" Selected
 
 ```
@@ -131,6 +135,39 @@ Session remains active.
 
 ---
 
+## Step 4: Offer to Close Tab (if in tmux)
+
+After ending a session (via end, delete, or merge), check if we're in tmux and offer to close the tab.
+
+**Check if in tmux:**
+```bash
+echo $TMUX
+```
+
+If `$TMUX` is set (non-empty), we're in tmux. Ask:
+
+```
+AskUserQuestion:
+  question: "Close this tmux tab?"
+  header: "Close tab"
+  multiSelect: false
+  options:
+    - label: "Yes, close tab"
+      description: "Close this terminal tab (Alt+x also works)"
+    - label: "No, keep open"
+      description: "Stay in this tab"
+```
+
+**If "Yes, close tab" selected:**
+```bash
+tmux kill-window
+```
+
+**If "No, keep open" selected:**
+Display any final messages and end.
+
+---
+
 ## MERGE FLOW (for "Complete & merge to main")
 
 ### Merge Step 1: Check for Uncommitted Changes
@@ -345,6 +382,8 @@ Summary:
 💡 To push your changes: git push
 ```
 
+Then proceed to **Step 4: Offer to Close Tab**.
+
 If failed:
 
 ```
@@ -532,6 +571,39 @@ Session remains active.
 
 ---
 
+### 🚨 RULE #5: OFFER TO CLOSE TMUX TAB
+
+After session ends (via end, delete, or merge), check if in tmux and offer to close:
+
+```bash
+# Check if in tmux
+echo $TMUX
+```
+
+If in tmux, ask:
+```xml
+<invoke name="AskUserQuestion">
+<parameter name="questions">[{
+  "question": "Close this tmux tab?",
+  "header": "Close tab",
+  "multiSelect": false,
+  "options": [
+    {"label": "Yes, close tab",
+     "description": "Close this terminal tab (Alt+x also works)"},
+    {"label": "No, keep open",
+     "description": "Stay in this tab"}
+  ]
+}]</parameter>
+</invoke>
+```
+
+If "Yes":
+```bash
+tmux kill-window
+```
+
+---
+
 ### KEY FILES
 
 | File | Purpose |
@@ -557,6 +629,7 @@ Session remains active.
    f. Execute integrate
    g. Show success with cd command
 5. If end/delete → Execute and show result
+6. If in tmux → Offer to close tab
 ```
 
 ---
@@ -588,5 +661,6 @@ Session remains active.
 - Merge flow: uncommitted → preview → conflicts → strategy → confirm → execute
 - Default strategy: squash
 - Always show cd command to return to main
+- **After session ends: Offer to close tmux tab (if in tmux)**
 
 <!-- COMPACT_SUMMARY_END -->