@lifeaitools/rdc-skills 0.9.15 → 0.9.17

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@lifeaitools/rdc-skills",
-  "version": "0.9.15",
+  "version": "0.9.17",
   "description": "RDC typed-agent dispatch skill suite for Claude Code — plan, build, review, overnight builds",
   "keywords": [
     "claude-code",

package/skills/build/SKILL.md

@@ -192,6 +192,15 @@ Read the task title and description, then:
      - **`"When done, set your work item to 'review' (NOT 'done') and return AGENT_COMPLETE with a verification field. The validator closes work items — you do not."`**
      - **`"COMPLETION PROOF REQUIRED in AGENT_COMPLETE: list every file written, the exact commit hash, and paste the vitest/tsc output. A report without this evidence will be rejected."`**
      - **`"If you find that a file or feature already exists: you MUST still verify it satisfies the full task spec before marking review. Finding a file is not completion. Run verification, check every requirement, and report what you found vs. what was required."`**
+     - **The test plan items from the work item's checklist** (all `test-*` prefixed items). Include them verbatim in the prompt and instruct the agent:
+       ```
+       TEST PLAN — you MUST implement/verify each of these and tick them off via update_checklist_item:
+       - test-assert-xxx: <description> → write a vitest test that proves this
+       - test-smoke-xxx: <description> → run the command and confirm the result
+       - test-visual-xxx: <description> → note: delegate to UI audit (you cannot verify this yourself)
+       - test-contract-xxx: <description> → verify the export/type/shape exists
+       Tick each item as you complete it. Do NOT batch — tick immediately after each verification.
+       ```
    - Use `run_in_background: true` for parallel execution
    - NEVER let agents overlap on the same files
 
@@ -255,11 +264,18 @@ Read the task title and description, then:
     - Runs `npx tsc --noEmit` for every touched app/package
     - Starts the dev server and probes every modified route (expects HTTP 200, not 500)
     - Runs vitest for every touched package
+    - **Verifies test plan completion per work item:**
+      - For each `test-assert-*` checklist item: confirm a corresponding vitest test exists and passes
+      - For each `test-smoke-*` checklist item: run the command and confirm exit code / HTTP status
+      - For each `test-visual-*` checklist item: note as "delegated to UI audit" (validator cannot verify visuals)
+      - For each `test-contract-*` checklist item: verify the export/type/shape exists in the built code
+      - Any unchecked `test-*` item with `required: true` = work item CANNOT be set to `done` (DB enforces this)
     - Sets passing items to `done`, failing items back to `todo` with failure detail
-    - Returns `VALIDATOR_COMPLETE` report
+    - Returns `VALIDATOR_COMPLETE` report with test plan status per item
 
     **If the validator finds failures:** fix them in a new wave, then re-run the validator. Do not skip.
     **File existence alone is NOT verification.** A route returning 500 is a failure regardless of tsc passing.
+    **Unchecked test plan items are a hard gate** — `update_work_item_status('done')` will raise an exception if any `required: true` checklist item is unchecked.
 
 11. **After verification passes:**
     - All wave commits are already on develop and pushed (Step 9 pushes after each wave merge).

package/skills/plan/SKILL.md

@@ -49,26 +49,74 @@ description: >-
 4. **Define work packages** — break into agent-dispatchable units:
    - Each work package = one agent assignment
    - No file overlap between packages
-   - Each package has: scope, files to create/modify, test requirements
+   - Each package has: scope, files to create/modify, test plan
    - Assign an agent type to each work package from the typed dispatch table in rdc:build. Include the guide file path (from `.rdc/guides/`, fallback `.rdc/guides/`) in each work package description.
    - Estimate: small (1 agent, <500 LOC), medium (1 agent, 500-1500 LOC), large (needs splitting)
 
-5. **Write plan doc** to `.rdc/plans/<topic-slug>.md` (fallback: `.rdc/plans/<topic-slug>.md` if `.rdc/` does not exist):
+5. **Write a test plan for each work package (MANDATORY):**
+
+   Every work package MUST have a `test_plan` section with specific, concrete test items. Each item has a type:
+
+   | Type | What it proves | How agent verifies | Example |
+   |------|---------------|-------------------|---------|
+   | `assert` | Logic is correct | Write a vitest test — input → expected output | `extractCode("```tsx\nfoo\n```") returns "foo"` |
+   | `smoke` | It runs without crashing | Run command, check exit code / HTTP status | `tsc --noEmit passes`, `GET /api/layout/scan returns 200` |
+   | `visual` | It looks right | Delegate to UI audit tool with specific checkpoints | `"/layout page renders container tree, not login screen"` |
+   | `contract` | Interface matches spec | Check exports, prop types, response shape | `ScanResult has { roots: ContainerNode[] }` |
+
+   **Rules for writing test plan items:**
+   - Every item must be a specific, falsifiable assertion — not "write tests" or "verify it works"
+   - New functions/modules MUST have at least one `assert` item
+   - API routes MUST have at least one `smoke` item
+   - UI pages MUST have at least one `visual` item
+   - New exports/types MUST have at least one `contract` item
+   - `assert` and `smoke` are mandatory for every work package. `visual` and `contract` when applicable.
+
+   **Example test plan in a plan doc:**
+   ```markdown
+   ### WP-2: AST Scanner
+   **Test plan:**
+   - assert: `scanFile` returns only Window/Frame/Pane/SubPane nodes, not Badge/Button
+   - assert: SubPane nested directly in root produces a warning
+   - assert: Valid Window > Frame > Pane > SubPane nesting produces no warnings
+   - smoke: `GET /api/layout/scan?dir=apps/studio/src` returns 200 with JSON body
+   - smoke: `npx tsc --noEmit` exits 0
+   - contract: `ScanResult` has shape `{ filePath: string, roots: ContainerNode[], warnings: ScanWarning[] }`
+   ```
+
+6. **Write plan doc** to `.rdc/plans/<topic-slug>.md` (fallback: `.rdc/plans/<topic-slug>.md` if `.rdc/` does not exist):
    ```markdown
    # Plan: <Topic>
    > Generated: <date> | Epic: <id if exists>
 
    ## Goal
    ## Design Decisions
-   ## Work Packages
+   ## Work Packages (each with test plan)
    ## Sequencing (what can parallelize, what depends on what)
    ## Risks & Mitigations
    ```
 
-6. **Create Supabase epic + child tasks:**
-   - Epic via `insert_work_item(p_item_type := 'epic', p_definition_of_done := '[{"id":"...", "text":"...", "required":true, "checked":false}]'::jsonb, ...)`
+7. **Create Supabase epic + child tasks:**
+   - Epic via `insert_work_item(p_item_type := 'epic', p_definition_of_done := '[...]'::jsonb, ...)`
+   - Epic DoD MUST include: `{"id":"test-plan-verified","text":"All test plan items implemented and passing","required":true,"checked":false}`
    - Set `p_definition_of_done` on the epic — child tasks inserted under it will auto-inherit it as their checklist
    - One task per work package via `insert_work_item(p_parent_id := <epic_id>, ...)` — checklist auto-hydrated from epic's DoD
+   - **Additionally, write test plan items as checklist items** on each task, using id format `test-<type>-<slug>`:
+     ```sql
+     SELECT insert_work_item(
+       p_parent_id := '<epic_id>',
+       p_title := 'WP-2: AST Scanner',
+       p_checklist := '[
+         {"id":"test-assert-scanner-filters","text":"assert: scanFile returns only container components","required":true,"checked":false},
+         {"id":"test-assert-nesting-warn","text":"assert: invalid nesting produces warnings","required":true,"checked":false},
+         {"id":"test-smoke-scan-api","text":"smoke: GET /api/layout/scan returns 200","required":true,"checked":false},
+         {"id":"test-contract-scanresult","text":"contract: ScanResult shape matches spec","required":true,"checked":false},
+         {"id":"tsc-clean","text":"npx tsc --noEmit passes","required":true,"checked":false}
+       ]'::jsonb
+     );
+     ```
+   - Agents MUST tick each `test-*` checklist item as they implement/verify it (via `update_checklist_item`)
+   - `update_work_item_status('done')` will REJECT if any `required: true` item is unchecked — this is the enforcement gate
    - Set priorities: urgent/high/normal based on sequencing
 
 7. **Report results:**

package/skills/status/SKILL.md

@@ -57,11 +57,20 @@ description: >-
    git branch -v
    ```
 
-6. **Infrastructure health** (if MCP available):
+6. **Dev server health (PM2):**
+   SSH into the Coolify server and check PM2 process state:
+   ```bash
+   SSH_KEY=$(curl -s http://127.0.0.1:52437/v/ssh-key-path)
+   ssh -i "$SSH_KEY" -o StrictHostKeyChecking=no root@64.237.54.189 "pm2 jlist 2>/dev/null"
+   ```
+   Parse the JSON array — for each process note `name`, `pm2_env.status` (online/stopped/errored), and `pm2_env.pm_uptime`.
+   If SSH fails or PM2 returns nothing, note "PM2 unreachable" and continue.
+
+7. **Infrastructure health** (if MCP available):
    - Get infrastructure overview or diagnose issues
    - Report any apps with failed builds or down containers
 
-7. **Present as a compact dashboard:**
+8. **Present as a compact dashboard:**
    ```
    ## Open Epics (N)
    <table>
@@ -71,6 +80,9 @@ description: >-
    ## Recent (48h)
    <list>
    
+   ## Dev Servers (PM2)
+   online: studio canvas lifeai ...   stopped: issho-invest
+   
    ## Deployments
    <green/red/yellow status>