maestro-flow 0.5.31 → 0.5.33

package/.claude/skills/team-uidesign/specs/scoring-guide.md

@@ -0,0 +1,114 @@
+# 8-Dimension Quality Scoring Rubric
+
+Score each dimension 0-4. Total: 0-32.
+
+## Dimensions
+
+### 1. Anti-AI-Slop (Weight: 10%)
+
+| Score | Criteria |
+|-------|----------|
+| 0 | 4+ P1 anti-patterns present |
+| 1 | 2-3 P1 anti-patterns present |
+| 2 | 1 P1 or 3+ P2 anti-patterns present |
+| 3 | 1-2 P2 or 2+ P3 anti-patterns only |
+| 4 | Zero P1/P2 anti-patterns, at most 1 P3 |
+
+### 2. Color Quality (Weight: 15%)
+
+| Score | Criteria |
+|-------|----------|
+| 0 | No color system; hex/rgb throughout; pure black/white used |
+| 1 | Some tokens but not OKLCH; no tinted neutrals; contrast failures |
+| 2 | OKLCH used partially; tinted neutrals attempted; most contrast passes |
+| 3 | Full OKLCH; tinted neutrals; 60-30-10 applied; all WCAG AA passes; semantic tokens present |
+| 4 | Score-3 plus: primitive->semantic->component hierarchy; color-mix usage; light/dark themes complete |
+
+### 3. Typography Quality (Weight: 15%)
+
+| Score | Criteria |
+|-------|----------|
+| 0 | System/generic font only; no scale; no fluid sizing |
+| 1 | Generic font (Inter/Roboto/etc); basic size scale; no clamp() |
+| 2 | Distinctive font chosen; modular scale present; no fluid sizing |
+| 3 | Distinctive font; modular scale with clamp(); proper line-height; reading width constrained |
+| 4 | Score-3 plus: font-display swap with fallback metrics; caption/body/heading line-heights differentiated |
+
+### 4. Spacing & Layout (Weight: 12.5%)
+
+| Score | Criteria |
+|-------|----------|
+| 0 | Arbitrary spacing; no system; nested cards |
+| 1 | Some consistent spacing but not 4pt scale; margin-heavy |
+| 2 | 4pt scale used; mostly gap over margin; some rhythm variation |
+| 3 | Full 4pt scale; gap throughout; rhythm variation (tight/comfortable/generous); touch targets met |
+| 4 | Score-3 plus: container queries used; no nested cards; 8px adjacent target gaps |
+
+### 5. Motion & Animation (Weight: 10%)
+
+| Score | Criteria |
+|-------|----------|
+| 0 | Layout property animations; no easing system; no reduced-motion |
+| 1 | Some transform/opacity; default ease/linear; no reduced-motion |
+| 2 | Transform/opacity only; custom easing present; reduced-motion exists but incomplete |
+| 3 | All animations on safe properties; ease-out-quart default; duration tokens; complete reduced-motion |
+| 4 | Score-3 plus: stagger system; will-change managed via JS; exit = 75% entrance |
+
+### 6. Interaction States (Weight: 15%)
+
+| Score | Criteria |
+|-------|----------|
+| 0 | Only default state; no hover/focus/disabled |
+| 1 | 2-3 states (e.g., default + hover + disabled) |
+| 2 | 5 states (default/hover/focus/active/disabled) but missing loading/error/success |
+| 3 | All 8 states defined; :focus-visible used; hover in @media(hover:hover) |
+| 4 | Score-3 plus: focus ring spec (2px solid + offset 2px); active scale(0.97); ARIA attributes on all states |
+
+### 7. Visual Hierarchy (Weight: 10%)
+
+| Score | Criteria |
+|-------|----------|
+| 0 | Everything same size/weight; no CTA hierarchy; all centered |
+| 1 | Some size variation; multiple primary CTAs per viewport |
+| 2 | Clear heading hierarchy; CTA levels present but inconsistent |
+| 3 | Passes squint test; single primary CTA per viewport; 3:1 size ratio; max 2 weights |
+| 4 | Score-3 plus: progressive disclosure; clear information density gradient |
+
+### 8. Responsive Design (Weight: 12.5%)
+
+| Score | Criteria |
+|-------|----------|
+| 0 | Fixed widths; breaks below 768px; content hidden on mobile |
+| 1 | Some media queries; horizontal scroll at 320px; small touch targets |
+| 2 | Mobile-first breakpoints; fluid widths; 14px min text; some issues at 320px |
+| 3 | Full breakpoint coverage; fluid design (clamp/vw/fr); 44px targets; no 320px scroll |
+| 4 | Score-3 plus: container queries; adapt-don't-hide approach; fluid typography |
+
+---
+
+## Rating Bands
+
+| Score | Band | Meaning |
+|-------|------|---------|
+| 28-32 | Excellent | Production-ready, Impeccable quality |
+| 22-27 | Good | Minor polish needed, shippable |
+| 16-21 | Acceptable | Needs revision, core structure sound |
+| 10-15 | Poor | Significant rework required |
+| 0-9 | Critical | Fundamental issues, restart design phase |
+
+## Severity Mapping
+
+| Severity | Dimension Score | Action |
+|----------|----------------|--------|
+| P0 Blocking | Dimension = 0 | Must fix before any progress |
+| P1 Major | Dimension = 1 | Fix in current iteration |
+| P2 Minor | Dimension = 2 | Fix in next iteration |
+| P3 Polish | Dimension = 3 | Track for future improvement |
+
+## Signal Determination
+
+| Condition | Signal | Action |
+|-----------|--------|--------|
+| Score >= 26 AND no P0 (no dim at 0) | `audit_passed` (GC CONVERGED) | Unblock downstream |
+| Score >= 20 AND no P0 | `audit_result` (REVISION NEEDED) | Create fix task |
+| Score < 20 OR any P0 | `fix_required` (CRITICAL) | Urgent fix task |

package/.claude/skills/team-uidesign/specs/team-config.json

@@ -0,0 +1,107 @@
+{
+  "team_name": "uidesign",
+  "team_display_name": "UI Design",
+  "description": "UI design team with CP-9 Dual-Track for parallel design and implementation",
+  "version": "1.0.0",
+
+  "roles": {
+    "coordinator": {
+      "task_prefix": null,
+      "responsibility": "Scope assessment, dual-track orchestration, sync point management, GC loop control",
+      "message_types": ["task_unblocked", "sync_checkpoint", "fix_required", "error", "shutdown"]
+    },
+    "researcher": {
+      "task_prefix": "RESEARCH",
+      "responsibility": "Design system analysis, component inventory, accessibility baseline audit",
+      "message_types": ["research_ready", "research_progress", "error"]
+    },
+    "designer": {
+      "task_prefix": "DESIGN",
+      "responsibility": "Design token definition, component specifications, layout design",
+      "message_types": ["design_ready", "design_revision", "design_progress", "error"]
+    },
+    "reviewer": {
+      "task_prefix": "AUDIT",
+      "additional_prefixes": [],
+      "responsibility": "8-dimension Impeccable-aligned audit (anti-slop, color, typography, spacing, motion, interaction, hierarchy, responsive)",
+      "message_types": ["audit_result", "audit_passed", "fix_required", "error"]
+    },
+    "implementer": {
+      "task_prefix": "BUILD",
+      "responsibility": "Component code implementation, CSS generation, design token consumption",
+      "message_types": ["build_complete", "build_progress", "error"]
+    }
+  },
+
+  "pipelines": {
+    "component": {
+      "description": "Single component: research → design → audit → build",
+      "task_chain": ["RESEARCH-001", "DESIGN-001", "AUDIT-001", "BUILD-001"],
+      "complexity": "low"
+    },
+    "system": {
+      "description": "Design system with dual-track: design tokens → audit → parallel build+components → audit → build components",
+      "task_chain": [
+        "RESEARCH-001",
+        "DESIGN-001:tokens", "AUDIT-001",
+        "DESIGN-002:components || BUILD-001:tokens",
+        "AUDIT-002", "BUILD-002:components"
+      ],
+      "sync_points": ["AUDIT-001", "AUDIT-002"],
+      "complexity": "medium"
+    },
+    "full-system": {
+      "description": "Complete design system with 3 audit checkpoints",
+      "task_chain": [
+        "RESEARCH-001",
+        "DESIGN-001:tokens", "AUDIT-001",
+        "DESIGN-002:components || BUILD-001:tokens",
+        "AUDIT-002",
+        "BUILD-002:components", "AUDIT-003"
+      ],
+      "sync_points": ["AUDIT-001", "AUDIT-002", "AUDIT-003"],
+      "complexity": "high"
+    }
+  },
+
+  "innovation_patterns": {
+    "generator_critic": {
+      "generator": "designer",
+      "critic": "reviewer",
+      "max_rounds": 2,
+      "convergence": "audit.score >= 8 && audit.critical_count === 0",
+      "escalation": "Coordinator intervenes after max rounds"
+    },
+    "shared_memory": {
+      "file": "shared-memory.json",
+      "fields": {
+        "researcher": ["component_inventory", "accessibility_patterns"],
+        "designer": ["design_token_registry", "style_decisions"],
+        "reviewer": ["audit_history"],
+        "implementer": ["component_inventory"]
+      }
+    },
+    "dynamic_pipeline": {
+      "criteria": {
+        "component": "scope.component_count <= 1",
+        "system": "scope.component_count <= 5 && scope.has_token_system",
+        "full-system": "scope.component_count > 5 || scope.is_full_redesign"
+      }
+    },
+    "dual_track": {
+      "pattern": "CP-9",
+      "description": "Design and implementation proceed in parallel after sync checkpoints",
+      "sync_mechanism": "AUDIT tasks serve as sync points between tracks",
+      "fallback": "If dual-track fails, coordinator falls back to sequential execution"
+    }
+  },
+
+  "session_dirs": {
+    "base": ".workflow/.team/UDS-{slug}-{YYYY-MM-DD}/",
+    "research": "research/",
+    "design": "design/",
+    "audit": "audit/",
+    "build": "build/",
+    "messages": ".workflow/.team-msg/{team-name}/"
+  }
+}

package/.claude/skills/team-uidesign/specs/ux-writing.md

@@ -0,0 +1,86 @@
+# UX Writing Standards
+
+Guidelines for all text content in UI components. From Impeccable's UX writing reference.
+
+---
+
+## Button Labels
+
+- **NEVER**: "OK", "Submit", "Yes", "No", "Cancel" (generic)
+- **ALWAYS**: verb + object — "Save changes", "Create account", "Delete message"
+- Destructive actions: name the destruction + show count — "Delete 5 items" not "Delete selected"
+- Primary CTA: specific benefit — "Start free trial" not "Get started"
+
+## Error Messages
+
+Formula: (1) What happened + (2) Why + (3) How to fix
+
+| Type | Template |
+|------|----------|
+| Format | "{Field} must be {format}. Example: {example}" |
+| Required | "{Field} is required to {reason}" |
+| Permission | "You don't have access to {resource}. Contact {who} for access" |
+| Network | "Couldn't reach the server. Check your connection and try again" |
+| Server | "Something went wrong on our end. Try again in a few minutes" |
+
+- Never blame user: "Please enter..." not "You entered..."
+- Never use codes alone: "Error 404" → "Page not found"
+- Be specific: "Password must be 8+ characters with a number" not "Invalid password"
+
+## Empty States
+
+Three components: (1) Acknowledge + (2) Explain value + (3) Provide action
+
+| Context | Example |
+|---------|---------|
+| First use | "No projects yet. Create your first project to get started. [Create project]" |
+| Search | "No results for '{query}'. Try a different search term or [browse all]" |
+| Filtered | "No items match these filters. [Clear filters]" |
+| Error | "Couldn't load items. [Try again]" |
+
+## Loading States
+
+- Be specific: "Saving your draft..." not "Loading..."
+- Multi-step: show progress — "Uploading (2 of 5 files)..."
+- Duration hint: "This usually takes about 30 seconds"
+
+## Confirmation Dialogs
+
+- Use sparingly — prefer undo over confirm
+- Title: what will happen — "Delete this project?"
+- Body: consequences — "This will permanently delete 12 files. This can't be undone."
+- Buttons: specific — "Delete project" / "Keep project" (not OK/Cancel)
+
+## Voice & Tone
+
+- **Voice**: consistent brand personality (professional/friendly/technical — choose one)
+- **Tone**: adapts to moment — cheerful for success, empathetic for errors, neutral for routine
+- Keep consistent: same word for same concept everywhere (delete/remove/trash → pick one)
+
+## Form Instructions
+
+- Show format with placeholder: `placeholder="john@example.com"`
+- Explain non-obvious fields with helper text below label
+- Mark optional fields (not required ones) — most fields should be required
+- Group related fields with clear section headers
+
+## Translation Planning
+
+| Language | Length vs English |
+|----------|------------------|
+| German | +30% |
+| French | +20% |
+| Finnish | +30-40% |
+| Chinese | -30% |
+| Japanese | -10-20% |
+
+- Design for longest language (German)
+- Never truncate translated text — allow wrapping
+- Avoid idioms and cultural references in source text
+
+## Redundant Copy Detection
+
+- Don't repeat visible information (heading ≠ first paragraph)
+- Labels describe the field, not restate the value
+- Tooltips add information, not repeat the label
+- If heading says it all, skip the intro paragraph

package/.claude/skills/team-ultra-analyze/SKILL.md

@@ -0,0 +1,173 @@
+---
+name: team-ultra-analyze
+description: Deep collaborative analysis team skill. Multi-role investigation with coordinator-driven synthesis. Triggers on "team ultra-analyze", "team analyze".
+allowed-tools: TeamCreate(*), TeamDelete(*), SendMessage(*), TaskCreate(*), TaskUpdate(*), TaskList(*), TaskGet(*), Agent(*), AskUserQuestion(*), Read(*), Write(*), Edit(*), Bash(*), Glob(*), Grep(*), mcp__maestro__team_msg(*)
+---
+
+# Team Ultra Analyze
+
+Deep collaborative analysis: explore -> analyze -> discuss -> synthesize. Supports Quick/Standard/Deep pipeline modes with configurable depth (N parallel agents). Discussion loops enable user-guided progressive understanding.
+
+## Architecture
+
+```
+Skill(skill="team-ultra-analyze", args="<topic>")
+                    |
+         SKILL.md (this file) = Router
+                    |
+     +--------------+--------------+
+     |                             |
+  no --role flag              --role <name>
+     |                             |
+  Coordinator                  Worker
+  roles/coordinator/role.md    roles/<name>/role.md
+     |
+     +-- analyze -> dispatch -> spawn workers -> STOP
+                                    |
+                    +-------+-------+-------+-------+
+                    v       v       v       v
+                 [team-worker agents, each loads roles/<role>/role.md]
+
+Pipeline (Standard mode):
+  [EXPLORE-1..N](parallel) -> [ANALYZE-1..N](parallel) -> DISCUSS-001 -> SYNTH-001
+
+Pipeline (Deep mode):
+  [EXPLORE-1..N] -> [ANALYZE-1..N] -> DISCUSS-001 -> ANALYZE-fix -> DISCUSS-002 -> ... -> SYNTH-001
+
+Pipeline (Quick mode):
+  EXPLORE-001 -> ANALYZE-001 -> SYNTH-001
+```
+
+## Role Registry
+
+| Role | Path | Prefix | Inner Loop |
+|------|------|--------|------------|
+| coordinator | [roles/coordinator/role.md](roles/coordinator/role.md) | — | — |
+| explorer | [roles/explorer/role.md](roles/explorer/role.md) | EXPLORE-* | false |
+| analyst | [roles/analyst/role.md](roles/analyst/role.md) | ANALYZE-* | false |
+| discussant | [roles/discussant/role.md](roles/discussant/role.md) | DISCUSS-* | false |
+| synthesizer | [roles/synthesizer/role.md](roles/synthesizer/role.md) | SYNTH-* | false |
+
+
+## Pre-load (coordinator, before dispatch)
+
+1. **Codebase docs**: If `.workflow/codebase/ARCHITECTURE.md` exists, read for module boundaries
+2. **Specs (arch)**: `maestro spec load --category arch` — load arch constraints as shared context
+3. **Wiki knowledge**: `maestro search "analysis investigation deep-dive" --json` — top 5 entries as prior context
+4. All optional — proceed without if unavailable
+## Role Router
+
+Parse `$ARGUMENTS`:
+- Has `--role <name>` → Read `roles/<name>/role.md`, execute Phase 2-4
+- No `--role` → `@roles/coordinator/role.md`, execute entry router
+
+## Shared Constants
+
+- **Session prefix**: `UAN`
+- **Session path**: `.workflow/.team/UAN-<slug>-<date>/`
+- **Team name**: `ultra-analyze`
+- **CLI tools**: `maestro delegate --mode analysis` (read-only), `maestro delegate --mode write` (modifications)
+- **Message bus**: `mcp__maestro__team_msg(session_id=<session-id>, ...)`
+
+## Worker Spawn Template
+
+Coordinator spawns workers using this template:
+
+```
+Agent({
+  subagent_type: "team-worker",
+  description: "Spawn <role> worker",
+  team_name: "ultra-analyze",
+  name: "<agent-name>",
+  run_in_background: true,
+  prompt: `## Role Assignment
+role: <role>
+role_spec: <skill_root>/roles/<role>/role.md
+session: <session-folder>
+session_id: <session-id>
+team_name: ultra-analyze
+requirement: <topic-description>
+agent_name: <agent-name>
+inner_loop: false
+
+## Progress Milestones
+session_id: <session-id>
+Report progress via team_msg at natural phase boundaries (context loaded -> core work done -> verification).
+Report blockers immediately via team_msg type="blocker".
+Report completion via team_msg type="task_complete" after final SendMessage.
+
+Read role_spec file (@<skill_root>/roles/<role>/role.md) to load Phase 2-4 domain instructions.
+Execute built-in Phase 1 (task discovery, owner=<agent-name>) -> role Phase 2-4 -> built-in Phase 5 (report).`
+})
+```
+
+## User Commands
+
+| Command | Action |
+|---------|--------|
+| `check` / `status` | Output execution status diagram, do not advance pipeline |
+| `resume` / `continue` | Check worker status, advance to next pipeline step |
+
+## Session Directory
+
+```
+.workflow/.team/UAN-{slug}-{YYYY-MM-DD}/
++-- .msg/messages.jsonl          # Message bus log
++-- .msg/meta.json               # Session metadata + cross-role state
++-- discussion.md                # Understanding evolution and discussion timeline
++-- explorations/                # Explorer output
+|   +-- exploration-001.json
+|   +-- exploration-002.json
++-- analyses/                    # Analyst output
+|   +-- analysis-001.json
+|   +-- analysis-002.json
++-- discussions/                 # Discussant output
+|   +-- discussion-round-001.json
++-- conclusions.json             # Synthesizer output
++-- wisdom/                      # Cross-task knowledge
+|   +-- learnings.md
+|   +-- decisions.md
+|   +-- conventions.md
+|   +-- issues.md
+```
+
+## Completion Action
+
+When pipeline completes, coordinator presents:
+
+```
+AskUserQuestion({
+  questions: [{
+    question: "Ultra-Analyze pipeline complete. What would you like to do?",
+    header: "Completion",
+    multiSelect: false,
+    options: [
+      { label: "Archive & Clean (Recommended)", description: "Archive session, clean up tasks and team resources" },
+      { label: "Keep Active", description: "Keep session active for follow-up work or inspection" },
+      { label: "Export Results", description: "Export deliverables to a specified location, then clean" }
+    ]
+  }]
+})
+```
+
+| Choice | Action |
+|--------|--------|
+| Archive & Clean | Update session status="completed" -> TeamDelete() -> output final summary |
+| Keep Active | Update session status="paused" -> output resume instructions |
+| Export Results | AskUserQuestion for target path -> copy deliverables -> Archive & Clean |
+
+## Specs Reference
+
+- [specs/team-config.json](specs/team-config.json) — Team configuration and pipeline settings
+
+## Error Handling
+
+| Scenario | Resolution |
+|----------|------------|
+| Unknown --role value | Error with role registry list |
+| Role file not found | Error with expected path (roles/{name}/role.md) |
+| Discussion loop stuck >5 rounds | Force synthesis, offer continuation |
+| CLI tool unavailable | Fallback chain: gemini -> codex -> manual analysis |
+| Explorer agent fails | Continue with available context, note limitation |
+| Fast-advance conflict | Coordinator reconciles on next callback |
+| Completion action fails | Default to Keep Active |

package/.claude/skills/team-ultra-analyze/roles/analyst/role.md

@@ -0,0 +1,98 @@
+---
+role: analyst
+prefix: ANALYZE
+inner_loop: false
+additional_prefixes: [ANALYZE-fix]
+message_types:
+  success: analysis_ready
+  error: error
+---
+
+# Deep Analyst
+
+Perform deep multi-perspective analysis on exploration results via CLI tools. Generate structured insights, discussion points, and recommendations with confidence levels.
+
+## Phase 2: Context Loading
+
+| Input | Source | Required |
+|-------|--------|----------|
+| Task description | From task subject/description | Yes |
+| Session path | Extracted from task description | Yes |
+| Exploration results | `<session>/explorations/*.json` | Yes |
+
+1. Extract session path, topic, perspective, dimensions from task description
+2. Detect direction-fix mode: `type:\s*direction-fix` with `adjusted_focus:\s*(.+)`
+3. Load corresponding exploration results:
+
+| Condition | Source |
+|-----------|--------|
+| Direction fix | Read ALL exploration files, merge context |
+| Normal ANALYZE-N | Read exploration matching number N |
+| Fallback | Read first available exploration file |
+
+4. Select CLI tool by perspective:
+
+| Perspective | CLI Tool | Rule Template |
+|-------------|----------|---------------|
+| technical | gemini | analysis-analyze-code-patterns |
+| architectural | claude | analysis-review-architecture |
+| business | codex | analysis-analyze-code-patterns |
+| domain_expert | gemini | analysis-analyze-code-patterns |
+| direction-fix (any) | gemini | analysis-diagnose-bug-root-cause |
+
+## Phase 3: Deep Analysis via CLI
+
+Build analysis prompt with exploration context:
+
+```
+PURPOSE: <Normal: "Deep analysis of '<topic>' from <perspective> perspective">
+         <Fix: "Supplementary analysis with adjusted focus on '<adjusted_focus>'">
+Success: Actionable insights with confidence levels and evidence references
+
+PRIOR EXPLORATION CONTEXT:
+- Key files: <top 5-8 files from exploration>
+- Patterns found: <top 3-5 patterns>
+- Key findings: <top 3-5 findings>
+
+TASK:
+- <perspective-specific analysis tasks>
+- Generate structured findings with confidence levels (high/medium/low)
+- Identify discussion points requiring user input
+- List open questions needing further exploration
+
+MODE: analysis
+CONTEXT: @**/* | Topic: <topic>
+EXPECTED: Structured analysis with: key_insights, key_findings, discussion_points, open_questions, recommendations
+CONSTRAINTS: Focus on <perspective> perspective | <dimensions>
+```
+
+Execute: `maestro delegate "<prompt>" --to <cli-tool> --mode analysis --rule <rule>`
+
+### Tech Profile Scan
+
+After analysis, emit context-aware trigger signals (based on detected codebase characteristics):
+
+1. Check analysis findings → signals (`sql_detected`, `auth_detected`, `ml_detected`, `api_surface`)
+2. Check risk areas → signals (`perf_sensitive`, `injection_risk`, `legacy_patterns`)
+3. Include `tech_profile` in Phase 5 state_update data
+
+## Phase 4: Result Aggregation
+
+Write analysis output to `<session>/analyses/analysis-<num>.json`:
+
+```json
+{
+  "perspective": "<perspective>",
+  "dimensions": ["<dim1>", "<dim2>"],
+  "is_direction_fix": false,
+  "key_insights": [{"insight": "...", "confidence": "high", "evidence": "file:line"}],
+  "key_findings": [{"finding": "...", "file_ref": "...", "impact": "..."}],
+  "discussion_points": ["..."],
+  "open_questions": ["..."],
+  "recommendations": [{"action": "...", "rationale": "...", "priority": "high"}],
+  "_metadata": {"cli_tool": "...", "cli_rule": "...", "perspective": "...", "timestamp": "..."}
+}
+```
+
+Update `<session>/wisdom/.msg/meta.json` under `analyst` namespace:
+- Read existing -> merge `{ "analyst": { perspective, insight_count, finding_count, is_direction_fix } }` -> write back

package/.claude/skills/team-ultra-analyze/roles/coordinator/commands/analyze.md

@@ -0,0 +1,73 @@
+# Analyze Task
+
+Parse topic -> detect pipeline mode and perspectives -> output analysis config.
+
+**CONSTRAINT**: Text-level analysis only. NO source code reading, NO codebase exploration.
+
+## Signal Detection
+
+### Pipeline Mode Detection
+
+Parse `--mode` from arguments first. If not specified, auto-detect from topic description:
+
+| Condition | Mode | Depth |
+|-----------|------|-------|
+| `--mode=quick` or topic contains "quick/overview/fast" | Quick | 1 |
+| `--mode=deep` or topic contains "deep/thorough/detailed/comprehensive" | Deep | N (from perspectives) |
+| Default (no match) | Standard | N (from perspectives) |
+
+### Dimension Detection
+
+Scan topic keywords to select analysis perspectives:
+
+| Dimension | Keywords |
+|-----------|----------|
+| architecture | architecture, design, structure |
+| implementation | implement, code, source |
+| performance | performance, optimize, speed |
+| security | security, auth, vulnerability |
+| concept | concept, theory, principle |
+| comparison | compare, vs, difference |
+| decision | decision, choice, tradeoff |
+
+**Depth** = number of selected perspectives. Quick mode always uses depth=1.
+
+## Pipeline Mode Rules
+
+| Mode | Task Structure |
+|------|----------------|
+| quick | EXPLORE-001 -> ANALYZE-001 -> SYNTH-001 (serial, depth=1) |
+| standard | EXPLORE-001..N (parallel) -> ANALYZE-001..N (parallel) -> DISCUSS-001 -> SYNTH-001 |
+| deep | Same as standard but SYNTH-001 omitted (created dynamically after discussion loop) |
+
+## Output
+
+Write analysis config to coordinator state (not a file), to be used by dispatch.md:
+
+```json
+{
+  "pipeline_mode": "<quick|standard|deep>",
+  "depth": <number>,
+  "perspectives": ["<perspective1>", "<perspective2>"],
+  "topic": "<original topic>",
+  "dimensions": ["<dim1>", "<dim2>"]
+}
+```
+
+## Complexity Scoring
+
+| Factor | Points |
+|--------|--------|
+| Per perspective | +1 |
+| Deep mode | +2 |
+| Cross-domain (3+ perspectives) | +1 |
+
+Results: 1-3 Quick, 4-6 Standard, 7+ Deep (if not explicitly set)
+
+## Discussion Loop Configuration
+
+| Mode | Max Discussion Rounds |
+|------|----------------------|
+| quick | 0 |
+| standard | 1 |
+| deep | 5 |