agileflow 3.3.0 → 3.4.0

package/src/core/commands/{audit → code}/test.md

@@ -1,14 +1,14 @@
 ---
 description: Multi-agent test quality analysis with consensus voting for finding test suite weaknesses
-argument-hint: "[file|directory] [DEPTH=quick|deep] [FOCUS=coverage|fragility|mocking|assertions|structure|integration|maintenance|patterns|all]"
+argument-hint: "[file|directory] [DEPTH=quick|deep|ultradeep] [FOCUS=coverage|fragility|mocking|assertions|structure|integration|maintenance|patterns|all] [MODEL=haiku|sonnet|opus]"
 compact_context:
   priority: high
   preserve_rules:
-    - "ACTIVE COMMAND: /agileflow:audit:test - Multi-agent test quality analysis"
+    - "ACTIVE COMMAND: /agileflow:code:test - Multi-agent test quality analysis"
     - "CRITICAL: Deploy analyzers IN PARALLEL in ONE message with multiple Task calls"
     - "CRITICAL: Wait for all results before running consensus (use TaskOutput with block=true)"
     - "CRITICAL: Confidence scoring: CONFIRMED (2+ agree), LIKELY (1 with evidence), INVESTIGATE (1 weak)"
-    - "MUST parse arguments: TARGET (file/dir), DEPTH (quick/deep), FOCUS (coverage|fragility|mocking|assertions|structure|integration|maintenance|patterns|all)"
+    - "MUST parse arguments: TARGET (file/dir), DEPTH (quick/deep/ultradeep), FOCUS (coverage|fragility|mocking|assertions|structure|integration|maintenance|patterns|all)"
     - "Pass consensus all analyzer outputs, let it synthesize the final report"
   state_fields:
     - target_path
@@ -18,7 +18,7 @@ compact_context:
     - findings_collected
 ---
 
-# /agileflow:audit:test
+# /agileflow:code:test
 
 Deploy multiple specialized test quality analyzers in parallel to find weaknesses in the test suite, then synthesize results through consensus voting into a prioritized Test Quality Audit Report.
 
@@ -27,11 +27,11 @@ Deploy multiple specialized test quality analyzers in parallel to find weaknesse
 ## Quick Reference
 
 ```
-/agileflow:audit:test app/                                # Analyze app tests (quick, core 5 analyzers)
-/agileflow:audit:test . DEPTH=deep                        # Deep analysis - all 8 analyzers
-/agileflow:audit:test src/ FOCUS=coverage,mocking          # Focus on specific areas
-/agileflow:audit:test . DEPTH=deep FOCUS=all               # Comprehensive full audit
-/agileflow:audit:test __tests__/ FOCUS=fragility            # Check test fragility specifically
+/agileflow:code:test app/                                # Analyze app tests (quick, core 5 analyzers)
+/agileflow:code:test . DEPTH=deep                        # Deep analysis - all 8 analyzers
+/agileflow:code:test src/ FOCUS=coverage,mocking          # Focus on specific areas
+/agileflow:code:test . DEPTH=deep FOCUS=all               # Comprehensive full audit
+/agileflow:code:test __tests__/ FOCUS=fragility            # Check test fragility specifically
 ```
 
 ---
@@ -40,7 +40,7 @@ Deploy multiple specialized test quality analyzers in parallel to find weaknesse
 
 ```
 +-------------------------------------------------------------+
-|                    /agileflow:audit:test                      |
+|                    /agileflow:code:test                      |
 |                                                               |
 |  1. Parse arguments (target, depth, focus)                    |
 |  2. Deploy analyzers IN PARALLEL                              |
@@ -73,8 +73,9 @@ Deploy multiple specialized test quality analyzers in parallel to find weaknesse
 | Argument | Values | Default | Description |
 |----------|--------|---------|-------------|
 | TARGET | file/directory | `.` | What to analyze |
-| DEPTH | quick, deep | quick | quick = core 5 analyzers, deep = all 8 |
+| DEPTH | quick, deep, ultradeep | quick | quick = core 5, deep = all 8, ultradeep = separate tmux sessions |
 | FOCUS | coverage,fragility,mocking,assertions,structure,integration,maintenance,patterns,all | all | Which analyzers to deploy |
+| MODEL | haiku, sonnet, opus | haiku | Model for analyzer subagents. Default preserves existing behavior. |
 
 ---
 
@@ -107,6 +108,15 @@ FOCUS = all (default) or comma-separated list
 **DEPTH behavior**:
 - `quick` (default): Deploy core 5 analyzers. Focus on CRITICAL/HIGH issues only.
 - `deep`: Deploy all 8 analyzers. Include MEDIUM/LOW findings.
+- `ultradeep`: Spawn each analyzer as a separate Claude Code session in tmux. Requires tmux. Uses model profiles from metadata. Falls back to `deep` if tmux unavailable.
+
+**ULTRADEEP mode** (DEPTH=ultradeep):
+1. Show cost estimate: `node .agileflow/scripts/spawn-audit-sessions.js --audit=test --target=TARGET --focus=FOCUS --model=MODEL --dry-run`
+2. Confirm with user before launching
+3. Spawn sessions: `node .agileflow/scripts/spawn-audit-sessions.js --audit=test --target=TARGET --focus=FOCUS --model=MODEL`
+4. Monitor sentinel files in `docs/09-agents/ultradeep/{trace_id}/` for completion
+5. Collect all findings and run consensus coordinator (same as deep mode)
+6. If tmux unavailable, fall back to `DEPTH=deep` with warning
 
 ### STEP 2: Deploy Analyzers in Parallel
 
@@ -368,13 +378,13 @@ FIX THIS SPRINT
 <!-- COMPACT_SUMMARY_START -->
 ## Compact Summary
 
-**Command**: `/agileflow:audit:test` - Multi-agent test quality analysis with consensus
+**Command**: `/agileflow:code:test` - Multi-agent test quality analysis with consensus
 
 **Quick Usage**:
 ```
-/agileflow:audit:test app/                        # Quick scan (core 5 analyzers)
-/agileflow:audit:test . DEPTH=deep                # All 8 analyzers
-/agileflow:audit:test src/ FOCUS=coverage,mocking  # Specific areas
+/agileflow:code:test app/                        # Quick scan (core 5 analyzers)
+/agileflow:code:test . DEPTH=deep                # All 8 analyzers
+/agileflow:code:test src/ FOCUS=coverage,mocking  # Specific areas
 ```
 
 **What It Does**: Deploy test quality analyzers in parallel -> Each finds different test weakness classes -> Consensus coordinator validates, filters by project type, assesses false confidence risk -> Actionable Test Quality Audit Report
@@ -409,7 +419,7 @@ FIX THIS SPRINT
 
 ## Boundary Rules (No Overlap)
 
-- **vs audit:logic**: No logic bugs in application code — only test quality
+- **vs code:logic**: No logic bugs in application code — only test quality
 - **vs qa agent**: The `qa.md` agent is a team member for story work. This is an on-demand test analysis tool
 
 ---
@@ -435,8 +445,8 @@ Add error handling tests before merging? [Y/n]
 
 ## Related Commands
 
-- `/agileflow:audit:logic` - Logic bug analysis (similar architecture)
-- `/agileflow:audit:security` - Security vulnerability analysis (similar architecture)
-- `/agileflow:audit:performance` - Performance bottleneck analysis (similar architecture)
-- `/agileflow:audit:legal` - Legal compliance analysis (similar architecture)
+- `/agileflow:code:logic` - Logic bug analysis (similar architecture)
+- `/agileflow:code:security` - Security vulnerability analysis (similar architecture)
+- `/agileflow:code:performance` - Performance bottleneck analysis (similar architecture)
+- `/agileflow:code:legal` - Legal compliance analysis (similar architecture)
 - `/agileflow:verify` - Run tests

package/src/core/commands/{discovery → ideate}/brief.md

@@ -4,7 +4,7 @@ argument-hint: "TOPIC=<text> [IDEATION=<path>] [RESEARCH=<path,...>]"
 compact_context:
   priority: critical
   preserve_rules:
-    - "ACTIVE COMMAND: /agileflow:discovery:brief - Product Brief synthesis"
+    - "ACTIVE COMMAND: /agileflow:ideate:brief - Product Brief synthesis"
     - "MUST read ideation report and/or research files as input"
     - "MUST generate a Product Brief using the product-brief template structure"
     - "MoSCoW mapping: HIGH-confidence ideas = MUST HAVE, single-expert ideas = SHOULD HAVE"
@@ -20,7 +20,7 @@ compact_context:
     - brief_generated
 ---
 
-# /agileflow:discovery:brief
+# /agileflow:ideate:brief
 
 Synthesize brainstorming results and research findings into a professional Product Brief artifact.
 
@@ -33,14 +33,14 @@ Generate a structured Product Brief that combines:
 - Research data (competitive analysis, market sizing, best practices)
 - Your own knowledge synthesis
 
-This can be used standalone (with existing ideation/research files) or as Phase 3 of the `/agileflow:discovery:new` workflow.
+This can be used standalone (with existing ideation/research files) or as Phase 3 of the `/agileflow:ideate:discover` workflow.
 
 ---
 
 ## STEP 0: Gather Context
 
 ```bash
-node .agileflow/scripts/obtain-context.js discovery:brief
+node .agileflow/scripts/obtain-context.js ideate:brief
 ```
 
 ---
@@ -49,13 +49,13 @@ node .agileflow/scripts/obtain-context.js discovery:brief
 
 ## Compact Summary
 
-**Command**: `/agileflow:discovery:brief` - Generate Product Brief from ideation + research
+**Command**: `/agileflow:ideate:brief` - Generate Product Brief from ideation + research
 
 **Quick Usage**:
 ```
-/agileflow:discovery:brief TOPIC="Mobile time tracking app"
-/agileflow:discovery:brief TOPIC="AI code review" IDEATION=docs/08-project/ideation/ideation-20260213.md
-/agileflow:discovery:brief TOPIC="Dashboard" RESEARCH=docs/10-research/20260213-dashboard-research.md
+/agileflow:ideate:brief TOPIC="Mobile time tracking app"
+/agileflow:ideate:brief TOPIC="AI code review" IDEATION=docs/08-project/ideation/ideation-20260213.md
+/agileflow:ideate:brief TOPIC="Dashboard" RESEARCH=docs/10-research/20260213-dashboard-research.md
 ```
 
 **What It Does**: Read ideation + research inputs -> Synthesize into Product Brief -> Save to docs/08-project/briefs/
@@ -307,19 +307,19 @@ Summary:
 
 ### Standalone (no prior ideation)
 ```
-/agileflow:discovery:brief TOPIC="Real-time collaboration for docs"
+/agileflow:ideate:brief TOPIC="Real-time collaboration for docs"
 ```
 Generates a brief from internal knowledge + topic analysis.
 
 ### With existing ideation
 ```
-/agileflow:discovery:brief TOPIC="API rate limiter" IDEATION=docs/08-project/ideation/ideation-20260213-api-rate-limiter.md
+/agileflow:ideate:brief TOPIC="API rate limiter" IDEATION=docs/08-project/ideation/ideation-20260213-api-rate-limiter.md
 ```
 Reads the ideation report and synthesizes into a brief.
 
 ### With ideation + research
 ```
-/agileflow:discovery:brief TOPIC="Mobile app" IDEATION=docs/08-project/ideation/ideation-20260213-mobile-app.md RESEARCH=docs/10-research/20260213-mobile-market-research.md,docs/10-research/20260213-mobile-competitors.md
+/agileflow:ideate:brief TOPIC="Mobile app" IDEATION=docs/08-project/ideation/ideation-20260213-mobile-app.md RESEARCH=docs/10-research/20260213-mobile-market-research.md,docs/10-research/20260213-mobile-competitors.md
 ```
 Full synthesis from both sources.
 
@@ -355,7 +355,7 @@ What would you like to do next?
 
 ## Related Commands
 
-- `/agileflow:discovery:new` - Full discovery workflow (brainstorm + research + brief)
+- `/agileflow:ideate:discover` - Full discovery workflow (brainstorm + research + brief)
 - `/agileflow:ideate:new` - Generate ideation report
 - `/agileflow:research:ask` - Generate research prompts
 - `/agileflow:research:synthesize` - Synthesize multiple research files

package/src/core/commands/{discovery/new.md → ideate/discover.md}

@@ -4,11 +4,11 @@ argument-hint: "TOPIC=<text> [DEPTH=quick|guided|deep]"
 compact_context:
   priority: critical
   preserve_rules:
-    - "ACTIVE COMMAND: /agileflow:discovery:new - Discovery workflow orchestrator"
+    - "ACTIVE COMMAND: /agileflow:ideate:discover - Discovery workflow orchestrator"
     - "DEPTH modes: quick (skip research, auto-generate), guided (interactive, optional research), deep (comprehensive research + curation)"
     - "Phase 1: Brainstorm via /agileflow:ideate:new SCOPE=all"
     - "Phase 2: Research via /agileflow:research:ask (optional in quick mode)"
-    - "Phase 3: Generate Product Brief via /agileflow:discovery:brief"
+    - "Phase 3: Generate Product Brief via /agileflow:ideate:brief"
     - "Output: docs/08-project/briefs/{date}-{topic-slug}-brief.md"
     - "MUST parse TOPIC (required) and DEPTH (default: guided)"
     - "After brief generation, offer: create epic, refine brief, or done"
@@ -22,7 +22,7 @@ compact_context:
     - research_files
 ---
 
-# /agileflow:discovery:new
+# /agileflow:ideate:discover
 
 Run a structured discovery workflow that produces a professional Product Brief. Chains brainstorming, optional research, and synthesis into a single orchestrated flow.
 
@@ -33,7 +33,7 @@ Run a structured discovery workflow that produces a professional Product Brief.
 Bridge the gap between "vague idea" and "epic planning". This command validates product viability BEFORE decomposing into stories/epics.
 
 ```
-Vague Idea --> /discovery:new --> Product Brief --> /epic --> Stories --> Implementation
+Vague Idea --> /ideate:discover --> Product Brief --> /epic --> Stories --> Implementation
 ```
 
 ---
@@ -41,7 +41,7 @@ Vague Idea --> /discovery:new --> Product Brief --> /epic --> Stories --> Implem
 ## STEP 0: Gather Context
 
 ```bash
-node .agileflow/scripts/obtain-context.js discovery
+node .agileflow/scripts/obtain-context.js ideate:discover
 ```
 
 ---
@@ -50,19 +50,19 @@ node .agileflow/scripts/obtain-context.js discovery
 
 ## Compact Summary
 
-**Command**: `/agileflow:discovery:new` - Orchestrate brainstorm + research + Product Brief generation
+**Command**: `/agileflow:ideate:discover` - Orchestrate brainstorm + research + Product Brief generation
 
 **Quick Usage**:
 ```
-/agileflow:discovery:new TOPIC="Mobile time tracking app"
-/agileflow:discovery:new TOPIC="AI code review tool" DEPTH=deep
-/agileflow:discovery:new TOPIC="Internal dashboard" DEPTH=quick
+/agileflow:ideate:discover TOPIC="Mobile time tracking app"
+/agileflow:ideate:discover TOPIC="AI code review tool" DEPTH=deep
+/agileflow:ideate:discover TOPIC="Internal dashboard" DEPTH=quick
 ```
 
 **Phases**:
 1. Brainstorm (delegates to `/agileflow:ideate:new`)
 2. Research (delegates to `/agileflow:research:ask` - optional in quick mode)
-3. Brief Generation (delegates to `/agileflow:discovery:brief`)
+3. Brief Generation (delegates to `/agileflow:ideate:brief`)
 
 **Depth Modes**:
 - `quick`: Auto-run brainstorm, skip research, generate brief immediately (~5-10 min)
@@ -87,7 +87,7 @@ node .agileflow/scripts/obtain-context.js discovery
 ## How It Works
 
 ```
-USER: /agileflow:discovery:new TOPIC="..." DEPTH=guided
+USER: /agileflow:ideate:discover TOPIC="..." DEPTH=guided
                     |
                     v
     +-------------------------------+
@@ -114,7 +114,7 @@ USER: /agileflow:discovery:new TOPIC="..." DEPTH=guided
                     v
     +-------------------------------+
     |   STEP 4: GENERATE BRIEF      |
-    |   Delegate to discovery:brief |
+    |   Delegate to ideate:brief    |
     |   Synthesize all inputs       |
     |   Output: Product Brief       |
     +-------------------------------+
@@ -386,7 +386,7 @@ What would you like to do next?
 
 ## Related Commands
 
-- `/agileflow:discovery:brief` - Generate a Product Brief from existing ideation + research
+- `/agileflow:ideate:brief` - Generate a Product Brief from existing ideation + research
 - `/agileflow:ideate:new` - Run multi-expert brainstorming
 - `/agileflow:research:ask` - Generate external research prompts
 - `/agileflow:research:import` - Import research results