@ludecker/aaac 1.1.3 → 1.1.5

package/templates/cursor/skills/shared/platform-release/orchestrator/SKILL.md

@@ -18,7 +18,7 @@ disable-model-invocation: true
 1. [../SKILL.md](../SKILL.md) — swarm DAG
 2. [ship-procedure.md](../ship-procedure.md) — step reference
 3. [graph.yaml](../../../../aaac/graph.yaml) — `release-app`
-4. [ludecker-infrastructure](../../../ludecker/infrastructure/SKILL.md)
+4. Project overlay infrastructure skill when present (`skills/<project>/infrastructure/`)
 
 ## Phases
 
@@ -32,11 +32,11 @@ Spawn subagent per [agents/release-git.md](../../../../agents/release-git.md).
 
 **Do not** start Wave 2 until `commit_sha` is returned.
 
-### 2. Wave 2 — Render
+### 2. Wave 2 — Deploy (optional)
 
-Spawn [release-render](../../../../agents/release-render.md) with `commit_sha`, `commit_message_first_line`, `commit_message_body`.
+When project overlay supplies a deploy agent, spawn it with `commit_sha`, `commit_message_first_line`, `commit_message_body`. Skip when not configured.
 
-If Render `build_failed`, overall status is failed.
+If deploy `build_failed`, overall status is failed.
 
 ### 3. Verify + report
 

package/templates/cursor/skills/shared/platform-release/ship-procedure.md

@@ -1,31 +1,30 @@
 # Release ship procedure (reference)
 
-Canonical steps migrated from legacy `/ship-ludecker`. Subagents in `agents/release-*.md` own each slice.
+Generic git-first release. Deploy steps are **optional** — enable via project overlay (`docs/project_context.md`, `.cursor/rules/deploy.mdc`). Subagents in `agents/release-*.md` own each slice.
 
 ## Git (Wave 1 — blocking)
 
-1. Confirm repo: `signalbynoise/ludecker` (or local ludecker monorepo)
+1. Confirm repo root (`git rev-parse --show-toplevel`)
 2. `git status` + `git diff` + `git diff --staged` + `git log -5 --oneline`
-3. Never stage `.env`, `.env.local`, credentials, or API keys
+3. Never stage `.env`, credentials, or API keys
 4. Draft 1–2 sentence commit message from diff and user intent
 5. `git add` intentional paths → `git commit` (HEREDOC message)
-6. Ensure on `main`: `git checkout main` if needed; `git pull --rebase origin main`
-7. `git push origin main` — on reject, rebase once more; never force-push main
+6. Ensure on default branch: checkout if needed; `git pull --rebase origin <branch>`
+7. `git push origin <branch>` — on reject, rebase once more; never force-push protected branches
 8. Output: `commit_sha`, `commit_message_first_line`, `commit_message_body`
 
-**Rules:** No force-push main. On pre-commit hook failure: fix and new commit — never amend unless user asked.
+**Rules:** No force-push to protected branches. On pre-commit hook failure: fix and new commit — never amend unless user asked.
 
-## Render (Wave 2 — after push)
+## Deploy (Wave 2 — optional, project overlay)
 
-MCP: `user-render` only (not `plugin-render-render`).
+Skip when no deploy agent or `project.config.json` deploy section is configured.
 
-**Service SSOT:** `ludecker-website` (see `render.yaml`, `docs/deployment.md`).
-
-1. `list_services` — find `name === "ludecker-website"`, note `id`
-2. After push: `list_deploys` (`limit: 5`) — match deploy `commit.id` to `commit_sha`
-3. Poll up to **15 minutes**, every **30s**, until `status === "live"` or terminal failure
-4. Smoke check: `curl -fsS -o /dev/null -w "%{http_code}" https://ludecker-website.onrender.com/` — expect **200**
+1. Read service name and smoke URL from `docs/project_context.md` or `.cursor/rules/deploy.mdc`
+2. Use your team's configured deploy MCP (see [mcp-and-deploy.md](../../../policies/mcp-and-deploy.md))
+3. After push: list deploys — match `commit.id` to `commit_sha`
+4. Poll until `live` or terminal failure
+5. Smoke check production URL — expect success status
 
 ## Preflight (optional, Wave 0)
 
-If intent includes "with tests": run `pnpm typecheck` from repo root before git work.
+If intent includes "with tests": run project typecheck/test command from repo root before git work.

package/templates/cursor/skills/shared/schema/SKILL.md

@@ -14,7 +14,7 @@ disable-model-invocation: true
 
 ## Execution focus
 
-- New migration file per change; apply via Supabase MCP (`hjadkzfemzuvhpwbixbt`)
+- New migration file per change; apply via configured database MCP (see [mcp-and-deploy.md](../../../policies/mcp-and-deploy.md))
 - Backward-compatible defaults; document breaking changes in report
 - RLS and security advisors after apply
 

package/templates/cursor/skills/shared/testing/SKILL.md

@@ -18,15 +18,15 @@ Phase `verify` (and `test_only` orchestrators). On **fix** paths, run fix verify
 2. Invoke [unit-test-run.md](../../../agents/unit-test-run.md) pattern for targeted vitest
 3. Fallow MCP → `check_changed` on touched files when configured
 4. `ReadLints` on edited paths
-5. **App build gate (when enabled):** before advancing `verify`, run:
+5. **Website build gate (mandatory on create / update / fix):** before advancing `verify`, run:
    ```bash
    node .cursor/aaac/scripts/run-engine/verify-website-build.mjs --run-id <run_id>
    ```
-   Reads `verify` from `.cursor/aaac/project.config.json`. Skips when `verify.enabled: false` (default on fresh install). When enabled, checks `index_html` static assets and runs the configured build command. `advance-phase.mjs verify` **blocks** until this passes and writes `artifacts/verify.yaml`.
+   This checks `index.html` static asset paths resolve under `apps/website/public/` (or project root for Vite dev) and runs `pnpm --filter @ludecker/website build`. `advance-phase.mjs verify` **blocks** until this passes and writes `artifacts/verify.yaml`.
 
 ## Fix verify swarm (mandatory on fix verb / fix_mode)
 
-After unit tests, launch **3 parallel** `Task` subagents in **one message**:
+After unit tests, launch **3 parallel** `Task` subagents in **one message**. Each prompt **must** include [_task-prompt-policy.md](../_task-prompt-policy.md) and investigation artifact paths.
 
 | # | Agent spec | `subagent_type` | Role |
 |---|------------|-----------------|------|

package/templates/cursor/skills/shared/verbs/_dispatch-utils.md

@@ -16,9 +16,11 @@ Orchestrators execute phases from the Run `pending` queue. Do not skip gates unl
 Read before any phase:
 
 1. [.cursor/policies/master-rules.md](../../../policies/master-rules.md)
-2. [.cursor/policies/implementation.md](../../../policies/implementation.md)
-3. [.cursor/policies/mcp-and-deploy.md](../../../policies/mcp-and-deploy.md)
-4. [.cursor/policies/minimal-complexity.md](../../../policies/minimal-complexity.md) — **required for create / update / fix**
+2. [.cursor/policies/project-context.md](../../../policies/project-context.md)
+3. [.cursor/policies/ui-design.md](../../../policies/ui-design.md)
+4. [.cursor/policies/implementation.md](../../../policies/implementation.md)
+5. [.cursor/policies/mcp-and-deploy.md](../../../policies/mcp-and-deploy.md)
+6. [.cursor/policies/minimal-complexity.md](../../../policies/minimal-complexity.md) — **required for create / update / fix**
 
 ## Minimal complexity (create / update / fix)
 

package/templates/cursor/skills/shared/verbs/check/orchestrator/SKILL.md

@@ -17,7 +17,7 @@ Read [_dispatch-utils.md](../_dispatch-utils.md) first.
 3. **load_inventory** — when domain slug maps to inventory
 4. **object_skills** — from graph `object_skills.<object>`
 5. [check](../../check/SKILL.md) — swarm per check skill
-6. **contract_checks** — run project test commands from domain inventory when present; for `@ludecker/aaac` package maintenance use `pnpm --filter @ludecker/aaac test` and `test:e2e`
+6. **contract_checks** — run test commands from domain inventory or `project.config.json` when present
 7. [reporting](../../reporting/SKILL.md) — **Answer** (yes/no/partial) then **How**
 
 No code changes. For test runs use `test-*`; for fixes use `fix-*`.

package/templates/cursor/skills/shared/verbs/update/orchestrator/contract.yaml

@@ -23,9 +23,11 @@ failure_conditions:
   - skip domain inventory when slug resolves to inventory file
 dependencies:
   skills: [discovery, planning, execution, testing, verification, reporting]
-  policies: [master-rules, implementation, mcp-and-deploy]
+  policies: [master-rules, project-context, ui-design, implementation, mcp-and-deploy]
   docs:
     - docs/master_rules.md
+    - docs/ui_design.md
+    - docs/project_context.md
     - docs/architecture.md
     - docs/design_system.md
 verification:

package/templates/docs/agentic_architecture.md

@@ -57,7 +57,7 @@ AAAC generates ~130 commands from **8 verbs × 12 objects**:
 Install copies everything you need. Open the project in Cursor and run commands.
 
 - ~130 slash commands and the full shared pipeline (discover → plan → execute → verify → report)
-- Generic `master_rules.md` and `architecture.md` in your docs folder — **already filled in**, not empty stubs
+- Generic `master_rules.md`, `ui_design.md`, `project_context.md`, and `architecture.md` in your docs folder — **already filled in**, not empty stubs
 - Hook scripts and Run lifecycle under `.cursor/`
 - Generic capability registry (shared skills only)
 - **No** project domains required; **no** app build gate until you opt in (`verify.enabled: false` in `project.config.json`)
@@ -66,7 +66,7 @@ You do **not** need to enable hooks manually, write rules, add domains, or confi
 
 ### Optional — when you want more (any stack)
 
-1. Replace or extend `docs/master_rules.md` and `docs/architecture.md` with team-specific detail
+1. Fill in `docs/project_context.md` with your repo layout and SSOT anchors; extend `docs/master_rules.md` and `docs/architecture.md` when needed
 2. Add `domains/<slug>/update/` (orchestrator + inventory) — see Part 2
 3. Extend `graph.project.yaml` with resolvers and project skills
 4. Enable verify in `project.config.json` when you have a web app to gate: