specweave 1.0.259 → 1.0.261

package/plugins/specweave/skills/do/SKILL.md

@@ -1,5 +1,5 @@
 ---
-description: Execute increment tasks following spec and plan with sync hooks. Use when saying "implement", "start working", "execute tasks", or "continue increment".
+description: Execute increment tasks following spec and plan with sync hooks. Use when saying "implement", "start working", "execute tasks", or "continue increment". IMPORTANT - Before starting, check task count and domain count. If 3+ domains or 15+ tasks, recommend /sw:team-lead instead (ask user for confirmation, or auto-invoke in auto mode).
 argument-hint: "<increment-id>"
 hooks:
   PostToolUse:
@@ -55,13 +55,43 @@ When no ID provided, auto-select (NEVER ask user for ID):
 2. **Load files**: Read `spec.md`, `plan.md`, `tasks.md`, `tests.md`
 3. **Load living docs**: Check ADRs and specs in `.specweave/docs/internal/` for related context
 4. **Verify readiness**: Status is planned/in-progress, no blocking deps, tasks exist
-5. **Task count validation**: If >25 tasks, warn and offer to split or phase execution
+5. **Task count validation**: If >25 tasks, warn and offer to split, phase, or use `/sw:auto`/`/sw:team-lead`
 6. **Validate AC presence** (MANDATORY):
    ```bash
    bash plugins/specweave/hooks/pre-increment-start.sh <increment-path>
    ```
    If fails: run `/sw:embed-acs`, then retry. Do NOT proceed without ACs in spec.md.
 
+### Step 2.5: Execution Strategy Check
+
+**Skip this step if already running inside `/sw:auto` or `/sw:team-lead`.** Check `.specweave/state/auto-mode.json` — if `active: true`, skip.
+
+Assess increment complexity to recommend the best execution mode:
+
+1. **Count pending tasks**: `grep -c '^\- \[ \]\|Status\*\*: \[ \]' tasks.md`
+2. **Count domains**: Scan spec.md and plan.md for distinct technology areas (frontend, backend, database, API, DevOps, security, mobile, ML/AI). Each distinct area = 1 domain.
+3. **Count ACs**: `grep -c 'AC-US' spec.md`
+
+**Recommendation matrix** (see CLAUDE.md Execution Strategy):
+
+| Tasks | Domains | Action |
+|-------|---------|--------|
+| ≤8 | 1 | Proceed with `/sw:do` silently |
+| 9-15 | 1-2 | Suggest `/sw:auto` for unattended execution |
+| >15 | 1-2 | Recommend `/sw:auto` (many tasks benefit from autonomous loop) |
+| any | 3+ | Recommend `/sw:team-lead` for parallel multi-agent execution |
+
+**When recommending (non-auto mode)**, use `AskUserQuestion` with these options:
+- `/sw:do` — Continue manual step-by-step (current mode)
+- `/sw:auto` — Autonomous sequential execution (unattended, stop-hook loop)
+- `/sw:team-lead` — Parallel multi-agent execution (higher quality for multi-domain, uses more tokens)
+
+Include trade-off note: "Team-lead and auto modes consume more tokens but deliver higher precision and quality for complex work."
+
+If user chooses auto or team-lead, invoke the chosen skill with the increment ID and **stop /sw:do execution**.
+
+**In auto mode (`.specweave/state/auto-mode.json` active)**: If 3+ domains detected, automatically invoke `/sw:team-lead` instead of proceeding sequentially.
+
 ### Step 3: TDD Setup
 
 Read `testMode` from metadata.json:

package/plugins/specweave/skills/increment/SKILL.md

@@ -126,7 +126,7 @@ After skill completes:
 
    Files: spec.md, plan.md, tasks.md, metadata.json
 
-   Next: /sw:do 0003 (start implementation)
+   Next: /sw:do 0003 | /sw:auto 0003 | /sw:team-lead (see Execution Strategy)
 ```
 
 ## Error Handling

package/plugins/specweave/skills/increment-planner/SKILL.md

@@ -200,6 +200,32 @@ Skill({ skill: "sw:architect", args: "Design architecture for increment XXXX" })
 Skill({ skill: "sw:test-aware-planner", args: "Generate tasks for increment XXXX" })
 ```
 
+## Step 5: Execution Strategy Recommendation
+
+After delegation completes (architect + test-aware-planner have created plan.md and tasks.md), analyze the increment:
+
+1. **Count tasks**: `grep -c '^\- \[ \]\|^### T-' tasks.md`
+2. **Count domains** from spec.md user stories and plan.md architecture (frontend, backend, database, API, DevOps, security, mobile, ML/AI)
+3. **Classify**: Low (≤8 tasks, 1 domain) | Medium (9-15, 1-2 domains) | High (>15 OR 3+ domains)
+
+**Show recommendation in output:**
+
+```
+EXECUTION STRATEGY
+================================================
+Tasks: [N] | Domains: [M] | Complexity: [Low/Medium/High]
+
+  /sw:do <id>         - Step-by-step, full control
+  /sw:auto <id>       - Autonomous sequential (unattended)
+  /sw:team-lead       - Parallel multi-agent (best quality for multi-domain, higher token cost)
+```
+
+- **Low**: Show `/sw:do <id>` as next step (default behavior)
+- **Medium**: Show `/sw:do <id>` and recommend `/sw:auto <id>` for unattended execution
+- **High**: Recommend `/sw:team-lead` as primary, with `/sw:auto` and `/sw:do` as alternatives
+
+See CLAUDE.md Execution Strategy section for the full decision matrix.
+
 ## Usage
 
 ```typescript

package/plugins/specweave/skills/increment-work-router/SKILL.md

@@ -107,6 +107,29 @@ Compare user's request against active increment:
 - **Medium match (40-70%)**: Related area → Ask confirmation
 - **Low match (<40%)**: Unrelated → Suggest new increment
 
+### Step 3.5: Assess Complexity (before routing)
+
+**Before routing to `/sw:do`, assess the target increment's complexity:**
+
+```bash
+# Count pending tasks
+PENDING=$(grep -c '^\- \[ \]\|Status\*\*: \[ \]' "$INCREMENT_PATH/tasks.md" 2>/dev/null || echo 0)
+
+# Count domains from spec.md + plan.md
+DOMAINS=$(grep -ciE 'frontend|backend|database|api|devops|security|mobile|ml|ai' "$INCREMENT_PATH/spec.md" "$INCREMENT_PATH/plan.md" 2>/dev/null | sort -u | wc -l)
+```
+
+**Modify routing based on complexity** (see CLAUDE.md Execution Strategy):
+
+| Tasks | Domains | Routing Modification |
+|-------|---------|---------------------|
+| ≤8 | 1 | Route to `/sw:do` as usual |
+| 9-15 | 1-2 | Route to `/sw:do` + add tip: "Tip: use `/sw:auto <id>` for unattended execution" |
+| >15 | 1-2 | Suggest `/sw:auto <id>` — "This increment has [N] tasks. Consider `/sw:auto` for autonomous execution." |
+| any | 3+ | Suggest `/sw:team-lead` — "This increment spans [M] domains. Consider `/sw:team-lead` for parallel multi-agent execution (higher quality, uses more tokens)." |
+
+In non-auto mode: always ask user before switching mode. In auto mode: use team-lead automatically for 3+ domains.
+
 ### Step 4: Route Intelligently
 
 **Scenario A: High relevance to active increment**
@@ -286,15 +309,20 @@ Would you like to:
 
 ## Decision Matrix
 
-| User Intent | Active Increments | Relevance | Action |
-|-------------|------------------|-----------|--------|
-| "Implement auth" | 1 (auth-related) | High (>70%) | Auto `/sw:do` |
-| "Implement auth" | 1 (unrelated) | Low (<40%) | Ask: New or add to current? |
-| "Implement auth" | 0 | N/A | Auto `/sw:increment` |
-| "Implement auth" | 2+ | N/A | Ask which increment |
-| "Let's continue" | 1 | N/A | Auto `/sw:do` |
-| "Let's continue" | 2+ | N/A | Ask which increment |
-| "Let's continue" | 0 | N/A | "No active increment. What should we build?" |
+| User Intent | Active Increments | Relevance | Complexity | Action |
+|-------------|------------------|-----------|------------|--------|
+| "Implement auth" | 1 (auth-related) | High (>70%) | Low | Auto `/sw:do` |
+| "Implement auth" | 1 (auth-related) | High (>70%) | Medium | Auto `/sw:do` + suggest `/sw:auto` |
+| "Implement auth" | 1 (auth-related) | High (>70%) | High | Suggest `/sw:auto` or `/sw:team-lead` |
+| "Implement auth" | 1 (unrelated) | Low (<40%) | Any | Ask: New or add to current? |
+| "Implement auth" | 0 | N/A | Any | Auto `/sw:increment` |
+| "Implement auth" | 2+ | N/A | Any | Ask which increment |
+| "Let's continue" | 1 | N/A | Low/Med | Auto `/sw:do` |
+| "Let's continue" | 1 | N/A | High | Auto `/sw:do` + suggest mode switch |
+| "Let's continue" | 2+ | N/A | Any | Ask which increment |
+| "Let's continue" | 0 | N/A | Any | "No active increment. What should we build?" |
+
+**Complexity**: Low (≤8 tasks, 1 domain) | Medium (9-15 tasks, 1-2 domains) | High (>15 tasks OR 3+ domains)
 
 ## Relevance Matching Logic
 

package/plugins/specweave/skills/plan/SKILL.md

@@ -77,6 +77,43 @@ Generate `plan.md` and `tasks.md` for an increment using Architect Agent and tes
    - PLANNING → ACTIVE transition (tasks.md now exists)
    - Update lastUpdated timestamp
 
+6. **Execution Strategy Recommendation** (MANDATORY):
+   After generating tasks.md, analyze complexity and output a recommendation:
+
+   **6a. Count pending tasks** in the generated tasks.md (count `[ ]` markers)
+
+   **6b. Detect domains** from file paths and task descriptions:
+   - Frontend: `src/components/`, `src/pages/`, `src/hooks/`, `src/styles/`, `.tsx`, `.css`, React/Vue/Angular keywords
+   - Backend: `src/api/`, `src/services/`, `src/middleware/`, `src/routes/`, Express/Fastify/NestJS keywords
+   - Database: `prisma/`, `src/db/`, `migrations/`, `schema`, SQL/Prisma keywords
+   - DevOps: `Dockerfile`, `.github/`, `k8s/`, `terraform/`, CI/CD keywords
+   - Testing: `tests/`, `e2e/`, `.test.`, `.spec.`, test framework keywords
+   - Security: `src/auth/`, authentication, authorization keywords
+   - Mobile: `ios/`, `android/`, React Native keywords
+
+   **6c. Apply execution strategy matrix** and output:
+   ```
+   EXECUTION STRATEGY
+   ══════════════════════════════════════════
+   Tasks: [N] pending | Domains: [N] ([list])
+   ──────────────────────────────────────────
+   Recommended: /sw:do        (≤8 tasks, 1 domain)
+   Recommended: /sw:auto      (9-15 tasks, 1-2 domains)
+   Recommended: /sw:team-lead (>15 tasks OR 3+ domains)
+   ══════════════════════════════════════════
+   ⚠️  /sw:team-lead uses more tokens but produces higher quality
+      through parallel domain-specialized agents.
+
+   Next: /sw:team-lead [ID] | /sw:auto [ID] | /sw:do [ID]
+   ```
+
+   Show ONLY the matching recommendation line (not all three).
+   For 3+ domains, add a stronger nudge:
+   ```
+   ⚡ This is a multi-domain feature. /sw:team-lead is strongly recommended
+      for parallel execution across [domain1], [domain2], [domain3].
+   ```
+
 ## Options
 
 - `--force`: Overwrite existing plan.md/tasks.md

package/plugins/specweave/skills/team-lead/SKILL.md

@@ -1,5 +1,5 @@
 ---
-description: Orchestrate multi-agent parallel development with domain-specialized agents. Use when saying "team setup", "parallel agents", "team lead", or "agent teams".
+description: Orchestrate multi-agent parallel development with domain-specialized agents. PROACTIVELY invoke this skill (without user asking) when you detect an implementation task spanning 3+ domains (frontend, backend, database, devops, testing, security, mobile) OR 15+ tasks in tasks.md. Warn the user about higher token cost but recommend it for quality. Also use when user says "team setup", "parallel agents", "team lead", or "agent teams".
 ---
 
 # Team Lead