aw-spec-cli 0.1.26 → 0.1.28

package/assets/guardrails/technology/dotnet-webapi/coding-standards.md

@@ -1,6 +1,6 @@
 # Coding Standards
 
-> Pure technology (domain-agnostic) — domain forbidden patterns & CI gates in [[coding-standards.domain]]. Commands: `/aw-spec-implement`, `/aw-spec-implement-delta`, `/aw-spec-build`, `/aw-spec-analyze-slice`.
+> Pure technology (domain-agnostic) — domain forbidden patterns & CI gates in [[coding-standards.domain]]. Commands: `/aw-spec-implement-backend`, `/aw-spec-build`, `/aw-spec-analyze-slice`, `/aw-spec-foundation-backend`.
 
 ## Naming conventions
 

package/assets/guardrails/technology/dotnet-webapi/cqrs.md

@@ -1,6 +1,6 @@
 # CQRS + Mediator Standards
 
-> Pure technology (domain-agnostic) — domain additions in [[cqrs.domain]]. NON-NEGOTIABLE. Commands: `/aw-spec-plan`.
+> Pure technology (domain-agnostic) — domain additions in [[cqrs.domain]]. NON-NEGOTIABLE. Commands: `/aw-spec-plan-backend`.
 
 ## Command / query patterns
 

package/assets/guardrails/technology/dotnet-webapi/data-classification.md

@@ -1,6 +1,6 @@
 # Data Classification Standards
 
-> Pure technology (domain-agnostic) — domain data categories in [[data-classification.domain]]. NON-NEGOTIABLE. Commands: `/aw-spec-plan`.
+> Pure technology (domain-agnostic) — domain data categories in [[data-classification.domain]]. NON-NEGOTIABLE. Commands: `/aw-spec-plan-backend`.
 
 ## Classification framework
 

package/assets/guardrails/technology/dotnet-webapi/dependency-policy.md

@@ -1,6 +1,6 @@
 # Dependency Policy
 
-> Pure technology (domain-agnostic) — domain package rules in [[dependency-policy.domain]]. Commands: `/aw-spec-implement`, `/aw-spec-implement-delta`.
+> Pure technology (domain-agnostic) — domain package rules in [[dependency-policy.domain]]. Commands: `/aw-spec-implement-backend`, `/aw-spec-foundation-backend`.
 
 ## Package governance
 

package/assets/guardrails/technology/dotnet-webapi/eventing.md

@@ -1,6 +1,6 @@
 # Eventing Standards
 
-> Pure technology (domain-agnostic) — domain additions in [[eventing.domain]]. Commands: `/aw-spec-plan`.
+> Pure technology (domain-agnostic) — domain additions in [[eventing.domain]]. Commands: `/aw-spec-plan-backend`.
 
 ## Domain events
 

package/assets/guardrails/technology/dotnet-webapi/folder-structure.md

@@ -1,6 +1,6 @@
 # Mandatory Folder Structure
 
-> Pure technology (domain-agnostic) — domain additions (Interop adapters, conformance tests, fixtures) in [[folder-structure.domain]]. NON-NEGOTIABLE. Commands: `/aw-spec-plan`, `/aw-spec-implement`, `/aw-spec-implement-delta`.
+> Pure technology (domain-agnostic) — domain additions (Interop adapters, conformance tests, fixtures) in [[folder-structure.domain]]. NON-NEGOTIABLE. Commands: `/aw-spec-plan-backend`, `/aw-spec-implement-backend`, `/aw-spec-foundation-backend`.
 >
 > Replace `<SampleProjectName>` with the project name (e.g. `Acme.Billing`).
 

package/assets/guardrails/technology/dotnet-webapi/framework-api-map.md

@@ -1,7 +1,7 @@
 # Framework API Map — which package and namespace each cited type comes from
 
 > Pure technology (domain-agnostic). NON-NEGOTIABLE where it names a package.
-> Commands: `/aw-spec-implement`, `/aw-spec-implement-delta`, `/aw-spec-analyze-slice`.
+> Commands: `/aw-spec-implement-backend`, `/aw-spec-analyze-slice`, `/aw-spec-foundation-backend`.
 >
 > The rules in this corpus name framework types — `AggregateRootBase<TId>`,
 > `IAggregateChild`, `IUnitOfWork`. This file says where each one LIVES. Without it a

package/assets/guardrails/technology/dotnet-webapi/modular-monolith.md

@@ -1,6 +1,6 @@
 # Modular Monolith Standards
 
-> Pure technology (domain-agnostic). NON-NEGOTIABLE where marked. Commands: `/aw-spec-plan`.
+> Pure technology (domain-agnostic). NON-NEGOTIABLE where marked. Commands: `/aw-spec-plan-backend`.
 
 ## Module boundaries
 

package/assets/guardrails/technology/dotnet-webapi/persistence.md

@@ -1,6 +1,6 @@
 # Persistence Standards
 
-> Pure technology (domain-agnostic) — domain additions in [[persistence.domain]]. NON-NEGOTIABLE where marked. Commands: `/aw-spec-plan`, `/aw-spec-run`.
+> Pure technology (domain-agnostic) — domain additions in [[persistence.domain]]. NON-NEGOTIABLE where marked. Commands: `/aw-spec-plan-backend`, `/aw-spec-run`.
 
 ## EF Core conventions
 

package/assets/guardrails/technology/dotnet-webapi/testing.md

@@ -1,6 +1,6 @@
 # Testing Standards
 
-> Pure technology (domain-agnostic) — domain additions in [[testing.domain]]. Commands: `/aw-spec-plan`, `/aw-spec-implement`, `/aw-spec-implement-delta`, `/aw-spec-analyze-slice`.
+> Pure technology (domain-agnostic) — domain additions in [[testing.domain]]. Commands: `/aw-spec-plan-backend`, `/aw-spec-implement-backend`, `/aw-spec-analyze-slice`, `/aw-spec-foundation-backend`.
 
 ## Test-first engineering
 

package/assets/guardrails/technology/dotnet-webapi/vertical-slices.md

@@ -1,6 +1,6 @@
 # Vertical Slice Standards
 
-> Pure technology (domain-agnostic) — domain additions in [[vertical-slices.domain]]. Commands: `/aw-spec-plan`.
+> Pure technology (domain-agnostic) — domain additions in [[vertical-slices.domain]]. Commands: `/aw-spec-plan-backend`.
 
 ## Feature organization
 

package/assets/guardrails/technology/dotnet-webapi/zero-trust.md

@@ -1,6 +1,6 @@
 # Zero-Trust Standards
 
-> Pure technology (domain-agnostic) — domain additions in [[zero-trust.domain]]. NON-NEGOTIABLE where marked. Commands: `/aw-spec-plan`.
+> Pure technology (domain-agnostic) — domain additions in [[zero-trust.domain]]. NON-NEGOTIABLE where marked. Commands: `/aw-spec-plan-backend`.
 
 ## Transport security (mTLS / TLS)
 

package/assets/guardrails/technology/nextjs/accessibility-implementation.md

@@ -1,7 +1,7 @@
 # Accessibility Standards — nextjs (frontend lane)
 
 > Pure technology (domain-agnostic). NON-NEGOTIABLE.
-> Commands: `/aw-spec-plan-ui`, `/aw-spec-implement-ui`.
+> Commands: `/aw-spec-plan-frontend`, `/aw-spec-implement-frontend`.
 > Detail layer under `constitution.ui.md` UX-I (accessibility floor).
 
 UX-I makes the floor non-negotiable; this file is what meeting it means in practice. The

package/assets/guardrails/technology/nextjs/api-client.md

@@ -1,7 +1,7 @@
 # API Client Standards — nextjs (frontend lane)
 
 > Pure technology (domain-agnostic). NON-NEGOTIABLE.
-> Commands: `/aw-spec-implement-ui`.
+> Commands: `/aw-spec-implement-frontend`, `/aw-spec-foundation-frontend`.
 > Detail layer under `constitution.ui.md` UX-IV (the contract is the only server input)
 > and UX-VII (mutations flow through one path).
 

package/assets/guardrails/technology/nextjs/api-integration.dotnet-webapi.md

@@ -2,7 +2,7 @@
 
 > The CROSS-LANE pairing rules: how the `nextjs` frontend lane consumes an
 > `dotnet-webapi` service lane. NON-NEGOTIABLE where marked.
-> Commands: `/aw-spec-plan-ui`, `/aw-spec-implement-ui`.
+> Commands: `/aw-spec-plan-frontend`, `/aw-spec-implement-frontend`.
 > Detail layer under `constitution.ui.md` UX-IV (the contract is the only server input).
 
 This file is named for the service lane it pairs with, and a project maps it through the

package/assets/guardrails/technology/nextjs/api-integration.java-spring.md

@@ -2,7 +2,7 @@
 
 > The CROSS-LANE pairing rules: how the `nextjs` frontend lane consumes a `java-spring`
 > (Spring Boot) service lane. NON-NEGOTIABLE where marked.
-> Commands: `/aw-spec-plan-ui`, `/aw-spec-implement-ui`.
+> Commands: `/aw-spec-plan-frontend`, `/aw-spec-implement-frontend`.
 > Detail layer under `constitution.ui.md` UX-IV (the contract is the only server input).
 
 This file is named for the service lane it pairs with, and a project maps it through the

package/assets/guardrails/technology/nextjs/auth-session.md

@@ -1,7 +1,7 @@
 # Authentication & Session Standards — nextjs (frontend lane)
 
 > Pure technology (domain-agnostic). NON-NEGOTIABLE.
-> Commands: `/aw-spec-plan-ui`, `/aw-spec-implement-ui`.
+> Commands: `/aw-spec-plan-frontend`, `/aw-spec-implement-frontend`.
 > Detail layer under `constitution.ui.md` UX-VIII (client state carries no secret) and
 > UX-IV (the contract is the only server input).
 

package/assets/guardrails/technology/nextjs/client-security.md

@@ -1,7 +1,7 @@
 # Client Security Standards — nextjs (frontend lane)
 
 > Pure technology (domain-agnostic). NON-NEGOTIABLE.
-> Commands: `/aw-spec-implement-ui`.
+> Commands: `/aw-spec-implement-frontend`.
 > Detail layer under `constitution.ui.md` UX-VIII (client state carries no secret).
 
 The client is a hostile environment: its code is readable, its storage is inspectable, and

package/assets/guardrails/technology/nextjs/component-architecture.md

@@ -1,6 +1,6 @@
 # Component Architecture Standards — nextjs (frontend lane)
 
-> Pure technology (domain-agnostic). Commands: `/aw-spec-plan-ui`.
+> Pure technology (domain-agnostic). Commands: `/aw-spec-plan-frontend`, `/aw-spec-foundation-frontend`.
 > Detail layer under `constitution.ui.md` UX-II (design system) and UX-III (server components).
 
 The rules the UI design author composes a feature's `§3 Component Structure` from. They

package/assets/guardrails/technology/nextjs/component-conventions.md

@@ -1,6 +1,6 @@
 # Component Conventions — nextjs (frontend lane)
 
-> Pure technology (domain-agnostic). Commands: `/aw-spec-implement-ui`.
+> Pure technology (domain-agnostic). Commands: `/aw-spec-implement-frontend`, `/aw-spec-foundation-frontend`.
 > Detail layer under `constitution.ui.md` UX-II (design system) and its Mandatory
 > Frontend Folder Structure.
 
@@ -18,7 +18,7 @@ writing within it.
   states. Business composition does not live in a route file.
 - A component reused by two or more features moves to `components/` — and moving it is a
   decision, recorded in the design, not a refactor made mid-generation.
-- Nothing this lane generates is written outside the lane's declared source path.
+- Nothing this lane generates is written outside the declared lane root folder.
 
 ## Naming
 

package/assets/guardrails/technology/nextjs/design-system.md

@@ -1,7 +1,7 @@
 # Design System Standards — nextjs (frontend lane)
 
 > Pure technology (domain-agnostic). NON-NEGOTIABLE.
-> Commands: `/aw-spec-plan-ui`, `/aw-spec-implement-ui`.
+> Commands: `/aw-spec-plan-frontend`, `/aw-spec-implement-frontend`, `/aw-spec-foundation-frontend`.
 > Detail layer under `constitution.ui.md` UX-II (the design system is the only source of
 > visual truth).
 

package/assets/guardrails/technology/nextjs/error-handling.md

@@ -1,6 +1,6 @@
 # Interaction & Error State Standards — nextjs (frontend lane)
 
-> Pure technology (domain-agnostic). Commands: `/aw-spec-plan-ui`, `/aw-spec-implement-ui`.
+> Pure technology (domain-agnostic). Commands: `/aw-spec-plan-frontend`, `/aw-spec-implement-frontend`.
 > Detail layer under `constitution.ui.md` UX-V (every interaction state is specified).
 
 The rules behind `design.ui.md §4 Interaction & Flow` — the section a backend-shaped

package/assets/guardrails/technology/nextjs/forms-and-validation.md

@@ -1,7 +1,7 @@
 # Forms & Validation Standards — nextjs (frontend lane)
 
 > Pure technology (domain-agnostic). NON-NEGOTIABLE where marked.
-> Commands: `/aw-spec-plan-ui`, `/aw-spec-implement-ui`.
+> Commands: `/aw-spec-plan-frontend`, `/aw-spec-implement-frontend`.
 > Detail layer under `constitution.ui.md` UX-V (every interaction state is specified) and
 > UX-VII (mutations flow through one path).
 

package/assets/guardrails/technology/nextjs/frontend-testing.md

@@ -1,7 +1,7 @@
 # Frontend Testing Standards — nextjs (frontend lane)
 
 > Pure technology (domain-agnostic). NON-NEGOTIABLE.
-> Commands: `/aw-spec-implement-ui`.
+> Commands: `/aw-spec-implement-frontend`, `/aw-spec-foundation-frontend`.
 > Detail layer under `constitution.ui.md` UX-XI (frontend test-first).
 
 Every file `implement-ui` generates ships with its test. The design says what to test: each

package/assets/guardrails/technology/nextjs/i18n.md

@@ -1,6 +1,6 @@
 # Internationalization Standards — nextjs (frontend lane)
 
-> Pure technology (domain-agnostic). Commands: `/aw-spec-plan-ui`, `/aw-spec-implement-ui`.
+> Pure technology (domain-agnostic). Commands: `/aw-spec-plan-frontend`, `/aw-spec-implement-frontend`.
 > Detail layer under `constitution.ui.md` UX-X (internationalization is structural).
 
 Internationalization is structural: it is cheap while the surface is being designed and

package/assets/guardrails/technology/nextjs/observability.md

@@ -1,7 +1,7 @@
 # Frontend Observability Standards — nextjs (frontend lane)
 
 > Pure technology (domain-agnostic). NON-NEGOTIABLE where marked.
-> Commands: `/aw-spec-implement-ui`.
+> Commands: `/aw-spec-implement-frontend`.
 > Detail layer under `constitution.ui.md` UX-VIII (client state carries no secret).
 
 The service is instrumented end to end — OpenTelemetry, structured logs, trace propagation

package/assets/guardrails/technology/nextjs/performance-budgets.md

@@ -1,7 +1,7 @@
 # Performance Budget Standards — nextjs (frontend lane)
 
 > Pure technology (domain-agnostic). NON-NEGOTIABLE.
-> Commands: `/aw-spec-plan-ui`, `/aw-spec-implement-ui`.
+> Commands: `/aw-spec-plan-frontend`, `/aw-spec-implement-frontend`.
 > Detail layer under `constitution.ui.md` UX-IX (the performance budget is a gate).
 
 A budget that is not enforced is an aspiration. Core Web Vitals thresholds and a per-route

package/assets/guardrails/technology/nextjs/routing-navigation.md

@@ -1,6 +1,6 @@
 # Routing & Navigation Standards — nextjs (frontend lane)
 
-> Pure technology (domain-agnostic). Commands: `/aw-spec-plan-ui`.
+> Pure technology (domain-agnostic). Commands: `/aw-spec-plan-frontend`, `/aw-spec-foundation-frontend`.
 > Detail layer under `constitution.ui.md` UX-III (server components) and UX-V (every
 > interaction state specified).
 

package/assets/guardrails/technology/nextjs/state-management.md

@@ -1,6 +1,6 @@
 # Client State Standards — nextjs (frontend lane)
 
-> Pure technology (domain-agnostic). Commands: `/aw-spec-plan-ui`.
+> Pure technology (domain-agnostic). Commands: `/aw-spec-plan-frontend`.
 > Detail layer under `constitution.ui.md` UX-VI (caching declared), UX-VII (one mutation
 > path) and UX-VIII (client state carries no secret).
 

package/assets/guardrails/technology/nextjs/ui-constitution.md

@@ -19,7 +19,7 @@ continue them — the two govern different lanes and version independently.
 
 ## Declared Lane
 
-Stack **nextjs** — Next.js (TypeScript, App Router), lane id `web`, owning `web/`.
+Stack **nextjs** — Next.js (TypeScript, App Router), lane id `web`, owning `frontend/` (the default lane root folder).
 
 Where `.appweaver/stacks.json` declares a frontend lane, that declaration is authoritative for the
 lane id and root; a scaffold that disagrees fails `STACK-MISMATCH:` rather than rewriting it.
@@ -121,11 +121,11 @@ another stack's assumptions. Elsewhere in this corpus the file is referenced as
 
 ## Mandatory Frontend Folder Structure
 
-The whole layout sits under the lane's root (`web/`) and never adds to the service lane's
+The whole layout sits under the lane root folder (`frontend/` by default) and never adds to the service lane's
 structure.
 
 ```
-web/
+frontend/
   app/                  # App Router — route segments, layouts, loading/error/not-found
   components/           # design-system compositions, presentational only
   features/<Feature>/   # one folder per spec feature: its components, hooks, actions

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "aw-spec-cli",
-  "version": "0.1.26",
+  "version": "0.1.28",
   "description": "AppWeaver Spec-Driven Development CLI - scaffolds projects with vertical slices, DDD, CQRS, and agent skills",
   "type": "module",
   "main": "dist/index.js",

package/assets/.agents/skills/appweaver-demo/SKILL.md

@@ -1,59 +0,0 @@
----
-name: "appweaver-demo"
-description: "Prototype launcher (Antigravity): run the aw-orchestrator using the specified strategy (spawn, agent, sdk, sdk-apply)."
-argument-hint: "Optional strategy ('agent', 'spawn', 'sdk', 'sdk-apply') and/or k=value vars (e.g. 'agent out_dir=...')"
-compatibility: "Requires .appweaver/orchestrator/ and the gemini CLI on PATH"
-user-invocable: true
-disable-model-invocation: false
----
-
-# Orchestrator Launcher
-
-All orchestration lives in the workflow YAML and is executed by `.appweaver/orchestrator/orchestrator.py` (the general, agent-agnostic engine). The interpreter assembles the COMPLETE payload (system + user) for every request; you never author generation context yourself.
-
-- **Engine + workflow (general):** `.appweaver/orchestrator/orchestrator.py`, `*.orch.yaml`
-- **This agent's transport profile:** `.agents/agent.json`
-
-  > Antigravity spawns via the `agy` CLI (Gemini-based; no `--system-prompt`, so
-  > `system` is folded into the prompt). Its `sdk` block declares the SDK the
-  > `sdk`/`sdk-apply` strategies import (`google-antigravity`) and the adapter
-  > (`.appweaver/orchestrator/adapters/google_antigravity.py`, shared per-SDK)
-  > that owns its calling convention.
-
-## Execution Steps
-
-1. **Parse Arguments**:
-   - Identify the requested strategy (one of: `agent`, `spawn`, `sdk`, `sdk-apply`). If the user specifies a strategy as the first argument, use it. Otherwise, default to `spawn`.
-   - Always pass the strategy explicitly: `--strategy <strategy>`.
-   - `--agent-profile .agents/agent.json` is required for `spawn`, `sdk`, and `sdk-apply`:
-     `spawn` reads the CLI to launch (`agy`) from it; `sdk`/`sdk-apply` read the SDK
-     package/module (and its `adapter` file) to import from its `sdk` block.
-     If the SDK package isn't installed, add `--sdk-install` so the engine
-     pip-installs the declared package first. (`agent` needs no profile.)
-   - `--checkpoint .appweaver/orchestrator/.demo-out/demo.state.json` is required for
-     `sdk-apply` and `agent` (suspend/resume — follow the loop in step 3).
-   - `spawn` accepts `--model <name>` (e.g. `gemini-2.5-pro`); isolation is
-     best-effort for Antigravity (no `--bare` equivalent). `sdk`/`sdk-apply`
-     accept `--model <name>`; isolation is intrinsic (fresh SDK session).
-
-2. **Run the Interpreter**:
-   Run the command (include only the bracketed flags that apply to the chosen strategy):
-   ```bash
-   python3 .appweaver/orchestrator/orchestrator.py \
-     .appweaver/orchestrator/workflows/aw-spec-demo.orch.yaml \
-     --strategy <strategy> \
-     [--agent-profile .agents/agent.json]   # spawn, sdk, sdk-apply \
-     [--checkpoint .appweaver/orchestrator/.demo-out/demo.state.json]  # sdk-apply, agent \
-     --json
-   ```
-
-3. **Handle Suspend/Resume Loop (for `agent` or `sdk-apply` strategies)**:
-   - If the command exits with code `2` (suspend):
-     - Read the prompt from the sidecar file `<checkpoint-path>.user.md` (and system instructions from `<checkpoint-path>.system.md`).
-     - Fulfill the request directly using your own tools (e.g., implementing the handler or reviewing files in the workspace).
-     - Write the final generation or review output to `<checkpoint-path>.response.md`.
-     - Re-run the exact same command.
-     - Repeat until the orchestrator exits with code `0`.
-
-4. **Report**:
-   Report the final JSON outputs (`status`, `outputs`, `review_pass`, generated file paths, etc.) to the user.

package/assets/.appweaver/orchestrator/.smoke-out/smoke.md

@@ -1,6 +0,0 @@
-<!-- authored by aw-orchestrator MOCK transport -->
-<!-- target: .appweaver/orchestrator/.smoke-out/smoke.md -->
-<!-- envelope: system=[] context=['.appweaver/orchestrator/.smoke-out/smoke.md'] -->
-<!-- task chars: 48 -->
-
-# (mock content)

package/assets/.appweaver/orchestrator/workflows/aw-spec-demo.orch.yaml

@@ -1,100 +0,0 @@
-# =============================================================================
-# aw-spec-demo.orch.yaml — a runnable demo workflow for the aw-orchestrator.
-# Launch via the parametric skill:  /appweaver demo [strategy]
-#
-# It walks the exact loop from the diagram:
-#   build_context → agent_generate (fresh) → agent_review (fresh) → repeat
-#
-# Run it (safe, no model calls — prints the assembled payloads):
-#   python3 .appweaver/orchestrator/orchestrator.py .appweaver/orchestrator/workflows/aw-spec-demo.orch.yaml
-#
-# Run it for real (spawns fresh `claude -p --bare` per generation):
-#   python3 .appweaver/orchestrator/orchestrator.py .appweaver/orchestrator/workflows/aw-spec-demo.orch.yaml \
-#       --transport claude --model opus --budget 0.50
-# =============================================================================
-
-dialect: aw-spec.orchestrator/v1
-name: demo-fresh-generation
-
-vars:
-  out_dir: .appweaver/orchestrator/.demo-out
-  review_pass: "false"          # loop guard, flipped by agent_review
-
-workflow:
-
-  # 1. Builds Complete Context — the interpreter reads standards (→ system) and
-  #    any prior artifacts (→ user context). Every standard it loads is kit-resident,
-  #    so the demo runs in a bare checkout with no guardrails/ tree at all.
-  - id: ctx_generate
-    action: build_context
-    system:
-      - { path: .appweaver/ai-rules.md }   # kit-resident, so the demo needs no project tree
-    context:
-      - { path: "{{out_dir}}/spec.md", optional: true }
-
-  # 2. Invoke Claude Code (FRESH generation) — it decides the file path(s) itself
-  #    (per the loaded folder-structure/architecture standards), writes them with
-  #    its tools, and REPORTS the paths back. The interpreter binds that list.
-  - id: gen_handler
-    action: agent_generate
-    tools: "Read,Write,Edit,Bash"
-    permission_mode: acceptEdits
-    task: |
-      Implement a CQRS command handler `CreateOrderHandler` for a "Create Order"
-      feature, following the loaded Clean Architecture + CQRS standards. Keep it
-      compilable C#; no TODOs.
-    outputs:
-      - { name: gen_status,  from: "$.status" }
-      - { name: gen_summary, from: "$.summary" }
-      - { name: gen_files,   from: "$.files" }    # the paths the agent chose
-
-  # 3. Review the current output — a SECOND fresh generation, read-only, that
-  #    judges the files the generation reported and returns pass/issues.
-  - id: review_handler
-    action: agent_review
-    review_of_var: gen_files
-    task: |
-      Review the handler for compliance with the loaded standards (naming, layer
-      boundaries, CQRS separation). Decide pass/fail.
-    outputs:
-      - { name: review_pass,   from: "$.pass" }
-      - { name: review_issues, from: "$.issues" }
-
-  # 4. If review failed, rebuild context (now including the issues) and
-  #    regenerate — up to 3 times. This is the "…continues" cycle.
-  - id: revise
-    action: loop
-    while: "{{review_pass}} != true"
-    max_iterations: 3
-    steps:
-      - id: ctx_revise
-        action: build_context
-        vars:
-          issues: "{{review_issues}}"
-        system:
-          - { path: .appweaver/ai-rules.md }
-        context_from: gen_files            # the files the agent chose last round
-      - id: regen
-        action: agent_generate
-        tools: "Read,Write,Edit"
-        task: |
-          Fix these review issues in the file(s) provided in context, preserving
-          everything already correct: {{issues}}
-        outputs:
-          - { name: gen_files, from: "$.files" }
-      - id: rereview
-        action: agent_review
-        review_of_var: gen_files
-        task: Re-review after the fix. Decide pass/fail.
-        outputs:
-          - { name: review_pass,   from: "$.pass" }
-          - { name: review_issues, from: "$.issues" }
-      - id: stop_when_pass
-        action: break
-        condition: "{{review_pass}} == true"
-
-outputs:
-  generated: "{{gen_summary}}"
-  review_pass: "{{review_pass}}"
-  files: "{{gen_files}}"          # decided by the fresh agent, not the interpreter
-  next: "interpreter continues to the next workflow step"

package/assets/.claude/skills/appweaver-demo/SKILL.md

@@ -1,59 +0,0 @@
----
-name: "appweaver-demo"
-description: "Prototype launcher (Claude Code): run the aw-orchestrator using the specified strategy (spawn, agent, sdk, sdk-apply)."
-argument-hint: "Optional strategy ('agent', 'spawn', 'sdk', 'sdk-apply') and/or k=value vars (e.g. 'agent out_dir=...')"
-compatibility: "Requires .appweaver/orchestrator/ and the claude CLI on PATH"
-user-invocable: true
-disable-model-invocation: false
----
-
-# Orchestrator Launcher
-
-All orchestration lives in the workflow YAML and is executed by `.appweaver/orchestrator/orchestrator.py` (the general, agent-agnostic engine). The interpreter assembles the COMPLETE payload (system + user) for every request; you never author generation context yourself.
-
-- **Engine + workflow (general):** `.appweaver/orchestrator/orchestrator.py`, `*.orch.yaml`
-- **This agent's transport profile:** `.claude/agent.json`
-
-  > Claude Code spawns via the `claude -p` CLI (native `--system-prompt`,
-  > `--tools`, and `--bare` isolation). Its `sdk` block declares the SDK the
-  > `sdk`/`sdk-apply` strategies import (`claude-agent-sdk`) and the adapter
-  > (`.appweaver/orchestrator/adapters/claude_agent_sdk.py`, shared per-SDK)
-  > that owns its calling convention.
-
-## Execution Steps
-
-1. **Parse Arguments**:
-   - Identify the requested strategy (one of: `agent`, `spawn`, `sdk`, `sdk-apply`). If the user specifies a strategy as the first argument, use it. Otherwise, default to `spawn`.
-   - Always pass the strategy explicitly: `--strategy <strategy>`.
-   - `--agent-profile .claude/agent.json` is required for `spawn`, `sdk`, and `sdk-apply`:
-     `spawn` reads the CLI to launch from it; `sdk`/`sdk-apply` read the SDK
-     package/module (and its `adapter` file) to import from its `sdk` block.
-     If the SDK package isn't installed, add `--sdk-install` so the engine
-     pip-installs the declared package first. (`agent` needs no profile.)
-   - `--checkpoint .appweaver/orchestrator/.demo-out/demo.state.json` is required for
-     `sdk-apply` and `agent` (suspend/resume — follow the loop in step 3).
-   - `spawn` may also add `--isolation bare|fresh` and `--model <name>` (bare is
-     strongest; use it when `ANTHROPIC_API_KEY` is set). `sdk`/`sdk-apply` accept
-     `--model <name>`; isolation is intrinsic (fresh SDK session, no settings).
-
-2. **Run the Interpreter**:
-   Run the command (include only the bracketed flags that apply to the chosen strategy):
-   ```bash
-   python3 .appweaver/orchestrator/orchestrator.py \
-     .appweaver/orchestrator/workflows/aw-spec-demo.orch.yaml \
-     --strategy <strategy> \
-     [--agent-profile .claude/agent.json]   # spawn, sdk, sdk-apply \
-     [--checkpoint .appweaver/orchestrator/.demo-out/demo.state.json]  # sdk-apply, agent \
-     --json
-   ```
-
-3. **Handle Suspend/Resume Loop (for `agent` or `sdk-apply` strategies)**:
-   - If the command exits with code `2` (suspend):
-     - Read the prompt from the sidecar file `<checkpoint-path>.user.md` (and system instructions from `<checkpoint-path>.system.md`).
-     - Fulfill the request directly using your own tools (e.g., implementing the handler or reviewing files in the workspace).
-     - Write the final generation or review output to `<checkpoint-path>.response.md`.
-     - Re-run the exact same command.
-     - Repeat until the orchestrator exits with code `0`.
-
-4. **Report**:
-   Report the final JSON outputs (`status`, `outputs`, `review_pass`, generated file paths, etc.) to the user.

package/assets/.kilocode/agent.json

@@ -1,28 +0,0 @@
-{
-  "name": "kilocode",
-  "sdk": {
-    "type": "claude-agent-sdk",
-    "package": "claude-agent-sdk",
-    "module": "claude_agent_sdk",
-    "adapter": "../.appweaver/orchestrator/adapters/claude_agent_sdk.py"
-  },
-  "runtime": "Kilo Code launches the interpreter; generation delegates to the Claude Code CLI",
-  "note": "Kilo Code is a VS Code extension with no standalone headless generation CLI, so this profile reuses `claude -p` for the fresh generation. To generate via Gemini instead, replace bin/args/system/user/tools_flag/approval with the .agents (antigravity) profile's values.",
-  "bin": "claude",
-  "args": ["-p", "--output-format", "json", "--no-session-persistence"],
-  "model_flag": "--model",
-  "system": { "flag": "--system-prompt" },
-  "user": { "mode": "stdin" },
-  "tools_flag": "--tools",
-  "approval": {
-    "acceptEdits": ["--permission-mode", "acceptEdits"],
-    "bypassPermissions": ["--permission-mode", "bypassPermissions"],
-    "default": ["--permission-mode", "default"]
-  },
-  "isolation": {
-    "bare": ["--bare"],
-    "fresh": ["--setting-sources", ""]
-  },
-  "budget_flag": "--max-budget-usd",
-  "result_keys": ["result"]
-}