specweave 1.0.256 → 1.0.259

package/plugins/specweave-backend/skills/database-optimizer/SKILL.md

@@ -1,5 +1,5 @@
 ---
-description: Expert database optimizer for query performance, indexing strategies, and schema design across PostgreSQL, MySQL, and MongoDB. Use when optimizing slow queries, fixing N+1 problems, or analyzing EXPLAIN plans. Covers connection pooling, caching strategies, partitioning, and database scaling patterns.
+description: Database optimizer for PostgreSQL, MySQL, MongoDB. Use for slow queries, N+1 problems, EXPLAIN plans, indexing, connection pooling, caching, partitioning, scaling.
 context: fork
 model: opus
 allowed-tools: Read, Write, Edit, Bash, Glob, Grep

package/plugins/specweave-backend/skills/graphql/SKILL.md

@@ -1,5 +1,5 @@
 ---
-description: GraphQL API expert across all major stacks (Node.js, Python, Java, .NET, Rust). Use when designing GraphQL schemas, building resolvers, implementing DataLoader, setting up federation, or optimizing GraphQL performance. Activates for: GraphQL, Apollo Server, Apollo Client, schema, resolvers, DataLoader, federation, subscriptions, Pothos, Strawberry, Hot Chocolate, urql, Relay.
+description: GraphQL API expert for Node.js, Python, Java, .NET, Rust. Use for schemas, resolvers, DataLoader, federation, subscriptions, Apollo, Pothos, Strawberry, urql, Relay.
 allowed-tools: Read, Write, Edit, Bash
 model: opus
 ---

package/plugins/specweave-frontend/skills/design-system-architect/SKILL.md

@@ -1,5 +1,5 @@
 ---
-description: Expert in building scalable design systems with Atomic Design, design tokens, and theming infrastructure. Use when creating component libraries, implementing dark mode, or establishing typography and color systems. Covers multi-brand support, Storybook-driven development, and accessibility-first component APIs.
+description: Scalable design systems with Atomic Design, design tokens, theming. Use for component libraries, dark mode, typography, color systems, Storybook, multi-brand, a11y.
 ---
 
 # Design System Architect

package/plugins/specweave-frontend/skills/frontend/SKILL.md

@@ -1,5 +1,5 @@
 ---
-description: Expert frontend developer for React, Vue, Angular, and modern JavaScript/TypeScript. Use when creating components, implementing hooks, handling state management, or building responsive web interfaces. Covers React 18/19 features (use() hook, React Compiler, Server Functions, useActionState, useOptimistic), custom hooks, form handling, and accessibility best practices.
+description: Frontend developer for React, Vue, Angular, TypeScript. Use for components, hooks, state management, responsive UIs. Covers React 18/19, custom hooks, forms, a11y.
 ---
 
 # Frontend Development Expert

package/plugins/specweave-frontend/skills/frontend-architect/SKILL.md

@@ -1,5 +1,5 @@
 ---
-description: Expert frontend architect for React, Next.js, Vue, and Angular with Atomic Design and state management patterns. Use when designing component architecture, building dashboards, or implementing complex frontend features. Covers TanStack Query, Zustand/Redux, routing strategies, and performance optimization.
+description: Frontend architect for React, Next.js, Vue, Angular. Use for component architecture, dashboards, Atomic Design, TanStack Query, Zustand/Redux, routing, performance.
 context: fork
 model: opus
 allowed-tools: Read, Write, Edit, Bash, Glob, Grep

package/plugins/specweave-frontend/skills/frontend-design/SKILL.md

@@ -1,5 +1,5 @@
 ---
-description: Frontend design expert for polished, production-ready UIs with distinctive visual characteristics and micro-interactions. Use when improving visual design, adding CSS animations, or polishing the UI with shadows, gradients, and transitions. Rejects generic AI aesthetics in favor of bold, distinctive design choices.
+description: Frontend design expert for polished UIs with micro-interactions. Use for visual design, CSS animations, shadows, gradients, transitions. Bold, distinctive design choices.
 allowed-tools: Read, Write, Edit, Glob, Grep
 model: opus
 context: fork

package/plugins/specweave-frontend/skills/i18n-expert/SKILL.md

@@ -1,5 +1,5 @@
 ---
-description: Expert in frontend internationalization (i18n) and localization (l10n) covering i18next/react-i18next setup, Next.js i18n routing, RTL support, date/number/currency formatting with Intl APIs, translation management workflows, and performance optimization. Use when implementing multilingual apps, adding locale support, handling RTL layouts, or managing translation pipelines.
+description: Frontend i18n and l10n expert. Use for multilingual apps, i18next/react-i18next, Next.js i18n routing, RTL layouts, Intl APIs, date/number/currency formatting, translation pipelines.
 allowed-tools: Read, Write, Edit, Bash
 model: opus
 context: fork

package/plugins/specweave-payments/skills/billing-automation/SKILL.md

@@ -1,5 +1,5 @@
 ---
-description: Automated billing systems for SaaS subscription management, invoicing, and payment recovery. Use when implementing recurring billing, automating invoice generation, or handling failed payment dunning. Covers proration calculations, billing cycle management, usage-based billing, and tax compliance (VAT/GST).
+description: SaaS billing automation for subscriptions, invoicing, payment recovery. Use for recurring billing, dunning, proration, usage-based billing, tax compliance (VAT/GST).
 ---
 
 # Billing Automation

package/plugins/specweave-testing/skills/accessibility-testing/SKILL.md

@@ -1,5 +1,5 @@
 ---
-description: Accessibility testing expert for WCAG compliance, axe-core, pa11y, Lighthouse, screen reader testing, keyboard navigation, and CI/CD a11y gates. Use for accessibility audits, a11y test automation, WCAG compliance, screen reader testing, keyboard navigation, color contrast, ARIA patterns, or form accessibility.
+description: Accessibility testing for WCAG compliance, axe-core, pa11y, Lighthouse, screen readers, keyboard nav, CI/CD a11y gates. Use for a11y audits, ARIA, color contrast.
 allowed-tools: Read, Write, Edit, Bash
 model: opus
 context: fork

package/src/templates/CLAUDE.md.template

@@ -1,133 +1,40 @@
 # {PROJECT_NAME} - SpecWeave Reference
 
+<!-- SECTION:hook-priority required -->
+## Hook Instructions Override Everything
+
+`<system-reminder>` hook output = **BLOCKING PRECONDITIONS**.
+
+| Hook Message | Action |
+|---|---|
+| **"RESTART REQUIRED"** | ALL tools blocked → STOP, wait for restart |
+| **"SKILL FIRST"** | Call shown skill FIRST → chain domain skills → implement |
+<!-- /SECTION -->
+
 <!-- SECTION:header required -->
 **Framework**: SpecWeave | **Truth**: `spec.md` + `tasks.md`
 <!-- /SECTION -->
 
 <!-- SECTION:claude-code-concepts -->
-## Claude Code Concepts (2.1.3+)
-
-**Skills and slash commands are now unified.** Both file formats create the same `/name` command:
-- `.claude/commands/review.md` → `/review`
-- `.claude/skills/review/SKILL.md` → `/review`
-
-### Core Concepts
-
-| Concept | What It Is | How to Use |
-|---------|------------|------------|
-| **Skills** | Reusable instructions in SKILL.md | `/skill-name` or auto-invoke via keywords |
-| **Plugins** | Packages with skills, agents, hooks | `claude plugin install sw@specweave` |
-| **Agents** | Isolated subagents with own context | Task tool or `context: fork` in skill |
+## Skills & Plugins
 
-### Skill Invocation Control (Frontmatter)
+**Invoke**: `/skill-name` | auto-trigger by keywords | `Skill({ skill: "name" })`
+**Parallel work**: Append "use subagents" to requests
 
-| Frontmatter | User Can Invoke | Claude Can Invoke | Use Case |
-|-------------|-----------------|-------------------|----------|
-| (default) | Yes | Yes | Most skills |
-| `disable-model-invocation: true` | Yes | **No** | Workflows with side effects (`/deploy`) |
-| `user-invocable: false` | **No** | Yes | Background knowledge |
+**Key skills**: `sw:pm`, `sw:architect`, `sw:grill`, `sw:tdd-orchestrator`, `sw-frontend:*`, `sw-backend:*`, `sw-testing:*`
 
-### SpecWeave Skill Organization
+**Skill chaining** — skills are NOT "one and done":
+1. **Planning**: `sw:pm` (specs) → `sw:architect` (design)
+2. **Implementation**: Invoke domain skill per tech (React → `sw-frontend:frontend-architect`, .NET → `sw-backend:dotnet-backend`, Stripe → `sw-payments:stripe-integration`, etc.)
+3. **Closure**: `sw:grill` runs automatically via `/sw:done`
 
-```
-plugins/specweave/
-├── commands/          # User-invocable workflows (have hooks)
-│   ├── do.md          # → /sw:do (execute tasks)
-│   ├── done.md        # → /sw:done (close increment)
-│   └── status.md      # → /sw:status
-└── skills/            # Auto-activating expertise (keyword-triggered)
-    ├── architect/     # → activates on "architecture", "system design"
-    ├── pm/            # → activates on "product", "requirements", "MVP"
-    └── code-simplifier/  # → activates on "simplify code", "clean up code"
-```
-
-### Quick Examples
-
-```bash
-# Explicit invocation (user types command)
-/sw:do                              # Execute tasks
-/sw:increment "auth feature"        # Plan increment
-
-# Auto-activation (Claude detects keywords, loads skill)
-"Design the auth architecture"      # → architect skill
-"Help me plan this product"         # → PM skill
-```
-
-### Key Insight
-
-**Old "commands" are just skills with `disable-model-invocation: true`** - they only respond to explicit `/name` invocation, not keyword detection.
+If auto-activation fails, invoke explicitly: `Skill({ skill: "name" })`
 <!-- /SECTION -->
 
-<!-- SECTION:skill-chaining required -->
-## ⚠️ MANDATORY: Skill Chaining During Implementation
-
-**Skills are NOT "one and done".** You MUST use multiple skills throughout implementation.
-
-### The Pattern (FOLLOW THIS)
-
-```
-PLANNING PHASE:
-  Hook says "SKILL FIRST" → Call sw:increment-planner
-  Then ALSO invoke: sw:pm (specs), sw:architect (design)
-
-IMPLEMENTATION PHASE:
-  For each domain, invoke the relevant skill:
-  - React/Vue/Angular → sw-frontend:frontend-architect
-  - .NET/C# → sw-backend:dotnet-backend
-  - Node.js → sw-backend:nodejs-backend
-  - Stripe → sw-payments:stripe-integration
-  - Database → sw-backend:database-optimizer
-
-CODE INTELLIGENCE (LSP - REQUIRES SETUP):
-  ⚠️ LSP does NOT work automatically - it requires explicit setup!
-
-  **Setup steps:**
-  1. Enable: `export ENABLE_LSP_TOOL=1` (add to ~/.zshrc or ~/.bashrc)
-  2. Add marketplace: `/plugin marketplace add boostvolt/claude-code-lsps`
-  3. Install plugin: `/plugin install vtsls@claude-code-lsps` (TypeScript)
-
-  **Note:** Official marketplace LSP plugins are broken (Issue #15148).
-  Use `boostvolt/claude-code-lsps` instead.
-
-  **Available LSP operations:** goToDefinition, findReferences, hover, documentSymbol, workspaceSymbol
-```
-
-### Why Auto-Activation May Not Trigger
-
-Per [official Claude Code docs](https://code.claude.com/docs/en/skills):
-1. Description keywords don't match user's exact phrasing
-2. Character budget exceeded (15K default, many skills loaded)
-3. Multi-domain requests dilute keyword matching
-
-**Solution**: When auto-activation fails, EXPLICITLY invoke with `Skill({ skill: "name" })`
-
-### Example: Multi-Domain Request
-
-User says: "Create React dashboard with Stripe checkout and .NET backend"
+<!-- SECTION:lsp -->
+## LSP (Code Intelligence)
 
-**WRONG** (what I did before):
-```
-Skill(sw:increment-planner) → Implement everything directly
-```
-
-**CORRECT** (what I should do):
-```
-Skill(sw:increment-planner)           → Plan the increment
-Skill(sw-frontend:frontend-architect) → React dashboard patterns
-Skill(sw-payments:stripe-integration) → Stripe checkout flow
-Skill(sw-backend:dotnet-backend)      → .NET API patterns
-[LSP available if configured - see LSP Setup section]
-```
-
-**Note on LSP**: LSP requires explicit setup (`ENABLE_LSP_TOOL=1` + `boostvolt/claude-code-lsps` marketplace). Official plugins are broken (Issue #15148).
-
-### Skill Usage Checklist
-
-Before marking implementation complete, verify:
-- [ ] Used planning skills (PM, Architect) if complex feature
-- [ ] Used domain skills for each tech in the stack
-- [ ] LSP configured if needed (requires `ENABLE_LSP_TOOL=1` + plugin setup)
-- [ ] Invoked skills explicitly if auto-activation didn't trigger
+**Native LSP broken in v2.1.0+.** Use: `specweave lsp refs|def|hover src/file.ts SymbolName`
 <!-- /SECTION -->
 
 <!-- SECTION:start -->
@@ -172,8 +79,8 @@ SpecWeave auto-detects product descriptions and routes to `/sw:increment`:
 ### 4. Think-Before-Act (Dependencies)
 **Satisfy dependencies BEFORE dependent operations.**
 ```
-❌ node script.js → Error → npm run build
-✅ npm run build → node script.js → Success
+Bad:  node script.js → Error → npm run build
+Good: npm run build → node script.js → Success
 ```
 <!-- /SECTION -->
 
@@ -187,15 +94,10 @@ SpecWeave auto-detects product descriptions and routes to `/sw:increment`:
    find .specweave/increments -maxdepth 2 -type d -name "[0-9]*" | grep -oE '[0-9]{4}E?' | sort -u | tail -5
    ```
 4. **Emergency**: "emergency mode" → 1 edit, 50 lines max, no agents
-5. **⛔ Initialization guard**: `.specweave/` folders MUST ONLY exist where `specweave init` was run
-6. **⛔ Marketplace refresh**: Use `specweave refresh-marketplace` CLI (not `scripts/refresh-marketplace.sh`)
-7. **⛔ Numbered folder collisions**: Before creating `docs/NN-*` folders, CHECK existing prefixes:
-   ```bash
-   ls docs/ | grep -E '^[0-9]{2}-' | cut -d'-' -f1 | sort -u
-   ```
-   Use next available number. **NEVER create duplicate prefixes.**
-8. **⛔ Multi-repo**: ALL repos MUST be at `repositories/{org}/{repo-name}/` — NEVER directly under `repositories/`
-   Discover org from config: `repository.organization` → `sync.profiles` → `umbrella.childRepos` → filesystem
+5. **Initialization guard**: `.specweave/` folders MUST ONLY exist where `specweave init` was run
+6. **Marketplace refresh**: Use `specweave refresh-marketplace` CLI (not `scripts/refresh-marketplace.sh`)
+7. **Numbered folder collisions**: Before creating `docs/NN-*` folders, CHECK existing prefixes
+8. **Multi-repo**: ALL repos MUST be at `repositories/{org}/{repo-name}/` — NEVER directly under `repositories/`
 <!-- /SECTION -->
 
 <!-- SECTION:workflow required -->
@@ -209,7 +111,7 @@ SpecWeave auto-detects product descriptions and routes to `/sw:increment`:
 | `/sw:do` | Execute tasks |
 | `/sw:auto` | Autonomous execution |
 | `/sw:auto-status` | Check auto session |
-| `/sw:cancel-auto` | ⚠️ EMERGENCY ONLY manual cancel |
+| `/sw:cancel-auto` | EMERGENCY ONLY manual cancel |
 | `/sw:validate` | Quality check |
 | `/sw:done` | Close |
 | `/sw:progress-sync` | Sync progress to all external tools |
@@ -219,49 +121,9 @@ SpecWeave auto-detects product descriptions and routes to `/sw:increment`:
 <!-- /SECTION -->
 
 <!-- SECTION:save-nested-repos required -->
-## /sw:save - Nested Repository Scanning (MANDATORY)
-
-**⚠️ ALWAYS scan for nested repositories BEFORE any git operations:**
-
-```bash
-# MANDATORY first step - check for nested repos
-for folder in repositories packages services apps libs workspace; do
-  [ -d "$folder" ] && find "$folder" -maxdepth 2 -name ".git" -type d
-done
-```
-
-**Common SpecWeave structure:**
-```
-project/
-├── .specweave/
-├── repositories/        # ← ALWAYS check this!
-│   ├── frontend/.git
-│   ├── backend/.git
-│   └── shared/.git
-└── .git                 # Parent repo
-```
-
-**NEVER assume single-repo mode without scanning first!**
-
-### Multi-Repo Increment Placement (CRITICAL)
+## Nested Repos
 
-**In umbrella projects with `repositories/` folder:**
-- Each repo manages its OWN `.specweave/increments/`
-- Team agents MUST create increments in their assigned repo's `.specweave/`
-- The umbrella root `.specweave/` is for config and docs ONLY
-- Run `specweave init` in each repo if `.specweave/` doesn't exist
-- Agent working directory = `repositories/{org}/{repo-name}/`
-
-```
-# CORRECT                           # WRONG
-repositories/                        .specweave/increments/
-  org/frontend/                        0001-all-agents-here/  ← NO!
-    .specweave/increments/
-      0001-ui-feature/  ← YES
-  org/backend/
-    .specweave/increments/
-      0001-api-feature/  ← YES
-```
+Before git operations, scan: `for d in repositories packages services apps libs workspace; do [ -d "$d" ] && find "$d" -maxdepth 2 -name ".git" -type d; done`
 <!-- /SECTION -->
 
 <!-- SECTION:reflect -->
@@ -270,7 +132,6 @@ repositories/                        .specweave/increments/
 SpecWeave learns from corrections. Learnings saved here automatically. Edit or delete as needed.
 
 **Disable**: Set `"reflect": { "enabled": false }` in `.specweave/config.json`
-
 <!-- /SECTION -->
 
 <!-- SECTION:context -->
@@ -291,7 +152,7 @@ SpecWeave learns from corrections. Learnings saved here automatically. Edit or d
 └── config.json
 ```
 
-**⛔ Increment root**: ONLY `metadata.json`, `spec.md`, `plan.md`, `tasks.md`
+**Increment root**: ONLY `metadata.json`, `spec.md`, `plan.md`, `tasks.md`
 
 **Everything else → subfolders**: `reports/` | `logs/` | `scripts/` | `backups/`
 <!-- /SECTION -->
@@ -307,126 +168,31 @@ SpecWeave learns from corrections. Learnings saved here automatically. Edit or d
 <!-- /SECTION -->
 
 <!-- SECTION:secrets required -->
-## Secrets Check
-
-**BEFORE CLI tools**: Check existing config first!
-```bash
-# Check if credentials EXIST (never display values!)
-grep -qE "(GITHUB_TOKEN|GH_TOKEN|JIRA_|AZURE_DEVOPS_|ADO_)" .env 2>/dev/null && echo "Credentials found in .env"
-cat .specweave/config.json | grep -A5 '"sync"'
-gh auth status
-```
+## Secrets
 
-**SECURITY**: NEVER use `grep TOKEN .env` without `-q` flag - it exposes credentials in terminal!
+Before CLI tools, check existing config (`grep -q` only — never display values).
 <!-- /SECTION -->
 
 <!-- SECTION:syncing -->
-## External Sync (GitHub/JIRA/ADO)
-
-**Primary command**: `/sw:progress-sync` — syncs tasks.md → spec.md → living docs → external tools (auto-creates missing issues)
+## External Sync
 
-**Individual commands**:
-| Command | Action |
-|---------|--------|
-| `/sw-github:create {id}` | Create GitHub issue for increment |
-| `/sw-github:push {id}` | Push task progress to GitHub issue |
-| `/sw-github:close {id}` | Close GitHub issue |
-| `/sw-github:status {id}` | Check sync status |
-| `/sw:sync-specs` | Sync living docs locally |
-
-**Mapping**: Feature → Milestone | Story → Issue | Task → Checkbox
-
-**Auto-configured**: Sync enabled by default during `specweave init` when a tracker is selected.
-
-**After task completion**: Run `/sw:progress-sync` or `/sw-github:push` to sync changes to external tools.
+Primary: `/sw:progress-sync`. Individual: `/sw-github:push`, `/sw-github:close`. Mapping: Feature→Milestone | Story→Issue | Task→Checkbox.
 <!-- /SECTION -->
 
 <!-- SECTION:testing -->
 ## Testing
 
-BDD in tasks.md | Unit >80% | `.test.ts` (Vitest)
-
-```typescript
-// ESM mocking: vi.hoisted() + vi.mock() (Vitest 4.x+)
-const { mockFn } = vi.hoisted(() => ({ mockFn: vi.fn() }));
-vi.mock('./module', () => ({ func: mockFn }));
-```
-
-### Browser Automation Mode
-
-**Default**: `@playwright/cli` if installed (98% token reduction vs MCP)
-**Fallback**: Playwright MCP plugin (rich DOM introspection)
-**Config**: `testing.playwright.preferCli: true|false` in `.specweave/config.json`
-**Install CLI**: `npm install -g @playwright/cli@latest`
+BDD in tasks.md | Unit >80% | `.test.ts` (Vitest) | ESM mocking: `vi.hoisted()` + `vi.mock()`
 <!-- /SECTION -->
 
 <!-- SECTION:tdd -->
-## TDD Mode (Test-Driven Development)
-
-**When `testing.defaultTestMode: "TDD"` is configured**, follow RED-GREEN-REFACTOR discipline:
-
-### TDD Workflow (MANDATORY when configured)
-
-```
-1. RED:     Write FAILING test first → verify it fails
-2. GREEN:   Write MINIMAL code to pass → no extra features
-3. REFACTOR: Improve code quality → keep tests green
-```
-
-### Check TDD Mode Before Implementation
-
-```bash
-# Check if TDD mode is enabled
-jq -r '.testing.defaultTestMode' .specweave/config.json
-# Returns: "TDD" | "test-first" | "test-after"
-```
-
-### TDD Commands
-
-| Command | Phase | Purpose |
-|---------|-------|---------|
-| `/sw:tdd-red` | RED | Write failing tests |
-| `/sw:tdd-green` | GREEN | Minimal implementation |
-| `/sw:tdd-refactor` | REFACTOR | Code quality improvement |
-| `/sw:tdd-cycle` | ALL | Full orchestrated workflow |
-
-### Enforcement Levels
-
-Set `testing.tddEnforcement` in config.json:
-
-| Level | Behavior |
-|-------|----------|
-| `strict` | **BLOCKS** task completion if RED not done before GREEN |
-| `warn` | Shows warning but allows continuation (default) |
-| `off` | No enforcement |
-
-### TDD Task Format
-
-When TDD is enabled, tasks include phase markers:
-
-```markdown
-### T-001: [RED] Write auth service tests
-**Depends On**: None
-**Status**: [ ] pending
-
-### T-002: [GREEN] Implement auth service
-**Depends On**: T-001
-**Status**: [ ] pending
+## TDD
 
-### T-003: [REFACTOR] Extract token utilities
-**Depends On**: T-002
-**Status**: [ ] pending
-```
-
-**Rule**: Complete dependencies BEFORE dependent tasks (RED before GREEN).
+When `testing.defaultTestMode: "TDD"` in config.json: RED→GREEN→REFACTOR. Use `/sw:tdd-cycle`. Enforcement via `testing.tddEnforcement` (strict|warn|off).
 <!-- /SECTION -->
 
 <!-- SECTION:api -->
-## API Development (OpenAPI-First)
-
-**For API projects only.** Commands: `/sw:api-docs --all` | `--openapi` | `--postman` | `--validate`
-
-Enable in config: `{"apiDocs":{"enabled":true,"openApiPath":"openapi.yaml"}}`
+<!-- API: Enable `apiDocs` in config.json. Commands: /sw:api-docs -->
 <!-- /SECTION -->
 
 <!-- SECTION:limits -->
@@ -440,42 +206,25 @@ Enable in config: `{"apiDocs":{"enabled":true,"openApiPath":"openapi.yaml"}}`
 
 | Issue | Fix |
 |-------|-----|
-| Skills/commands missing | Restart Claude Code |
+| Skills missing | Restart Claude Code |
 | Plugins outdated | `specweave refresh-marketplace` |
 | Out of sync | `/sw:sync-tasks` |
-| Duplicate IDs | `/sw:fix-duplicates` |
-| Edits blocked | Add `"additionalDirectories":["repositories"]` to `.claude/settings.json` |
-| Session stuck | Kill + `rm -f .specweave/state/*.lock` + restart |
+| Session stuck | `rm -f .specweave/state/*.lock` + restart |
 <!-- /SECTION -->
 
 <!-- SECTION:lazyloading -->
 ## Plugin Auto-Loading
 
-Plugins load automatically based on project type and keywords. Manual install if needed:
-
-```bash
-claude plugin install sw-frontend@specweave  # Install plugin
-claude plugin list                           # Check installed
-export SPECWEAVE_DISABLE_AUTO_LOAD=1         # Disable auto-load
-```
-
-**Token savings**: Core ~3-5K tokens vs all plugins ~60K+
+Plugins load automatically. Manual: `claude plugin install sw-frontend@specweave`. Disable: `export SPECWEAVE_DISABLE_AUTO_LOAD=1`
 <!-- /SECTION -->
 
 <!-- SECTION:principles -->
 ## Principles
 
-### SpecWeave Principles
 1. **Spec-first**: `/sw:increment` before coding
 2. **Docs = truth**: Specs guide implementation
-3. **Incremental**: Small, validated increments
-4. **Traceable**: All work → specs → ACs
-
-### Core Principles (Quality)
-- **Simplicity First**: Make every change as simple as possible. Impact minimal code.
-- **No Laziness**: Find root causes. No temporary fixes. Senior developer standards.
-- **Minimal Impact**: Changes should only touch what's necessary. Avoid introducing bugs.
-- **Demand Elegance**: For non-trivial changes, pause and ask "is there a more elegant way?" - but skip this for simple, obvious fixes (don't over-engineer).
+3. **Simplicity First**: Minimal code, minimal impact
+4. **No Laziness**: Root causes, senior standards
 <!-- /SECTION -->
 
 <!-- SECTION:linking -->
@@ -489,40 +238,15 @@ Task format: `**AC**: AC-US1-01, AC-US1-02` (CRITICAL for linking)
 <!-- SECTION:mcp -->
 ## External Services
 
-**Priority**: CLI tools first (simpler) → MCP for complex integrations
-
-**CLI tools** (check auth first):
-```bash
-gh auth status          # GitHub
-wrangler whoami         # Cloudflare
-supabase status         # Supabase
-```
-
-**MCP servers** (for richer integrations):
-```bash
-claude mcp add --transport http github https://api.github.com/mcp
-claude mcp add --transport stdio postgres -- npx -y @modelcontextprotocol/server-postgres
-/mcp                    # Check status in Claude Code
-```
-
-MCP supports lazy-loading (auto mode) - tools load on-demand when >10% context.
+CLI tools first (`gh`, `wrangler`, `supabase`) → MCP for complex integrations.
 <!-- /SECTION -->
 
 <!-- SECTION:auto -->
 ## Auto Mode
 
-**Commands**: `/sw:auto` (start) | `/sw:auto-status` (check) | `/sw:cancel-auto` (emergency only)
+`/sw:auto` (start) | `/sw:auto-status` (check) | `/sw:cancel-auto` (emergency)
 
-**Pattern**: IMPLEMENT → TEST → FAIL? → FIX → PASS → NEXT
-
-**TDD in Auto Mode**: If `testing.defaultTestMode: "TDD"` is configured:
-- Use `/sw:auto --tdd` for strict enforcement (ALL tests must pass)
-- Auto mode reads config and displays TDD banner
-- Follow RED → GREEN → REFACTOR order for task triplets
-
-**Pragmatic completion**: MUST (MVP, security, data integrity) | SHOULD (edge cases) | CAN SKIP (conflicts - ask user)
-
-**STOP & ASK** if: Spec conflicts | Task unnecessary | Requirement ambiguous
+Pattern: IMPLEMENT → TEST → FAIL? → FIX → PASS → NEXT. STOP & ASK if spec conflicts or ambiguity.
 <!-- /SECTION -->
 
 <!-- SECTION:docs -->
@@ -534,35 +258,5 @@ MCP supports lazy-loading (auto mode) - tools load on-demand when >10% context.
 <!-- SECTION:non-claude -->
 ## Using SpecWeave with Other AI Tools
 
-**Not using Claude Code?** See **AGENTS.md** for complete instructions on using SpecWeave with Cursor, Copilot, Windsurf, Aider, and other AI coding assistants.
-
-### Key Differences for Non-Claude Tools
-
-| Feature | Claude Code | Other Tools |
-|---------|-------------|-------------|
-| **Hooks** | Automatic | Manual sync required (see AGENTS.md) |
-| **Commands** | Slash syntax works | Read command .md files |
-| **Skills** | Auto-activate | Load .md files manually |
-| **Task tracking** | Auto-updates | Manual checkbox updates |
-
-### Quick Start (Non-Claude)
-
-```bash
-# 1. Install SpecWeave globally
-npm install -g specweave
-
-# 2. Initialize your project
-specweave init .
-
-# 3. Read AGENTS.md for your specific tool
-cat AGENTS.md  # or open in your editor
-```
-
-**Essential workflow for ANY AI tool:**
-1. After completing a task → Update `tasks.md`: `[ ]` → `[x]`
-2. If task satisfies ACs → Update `spec.md`: `[ ] AC-XX` → `[x] AC-XX`
-3. Run `/sw:sync-tasks` to update progress cache
-4. When all tasks done → Run `/sw:done {id}` to close increment
-
-**Full guide with hook simulation, tool-specific setup, and workflows**: See **AGENTS.md**
+See **AGENTS.md** for Cursor, Copilot, Windsurf, Aider instructions.
 <!-- /SECTION -->

package/src/templates/config.json.template

@@ -77,12 +77,16 @@
 
   "hooks": {
     "post_task_completion": {
-      "sync_living_docs": true,
       "sync_tasks_md": true,
       "external_tracker_sync": true
     },
     "post_increment_planning": {
       "auto_create_github_issue": true
+    },
+    "post_increment_done": {
+      "sync_living_docs": true,
+      "sync_to_github_project": true,
+      "close_github_issue": true
     }
   }
 }