@lifeaitools/rdc-skills 0.24.42 → 0.25.1

package/skills/design/reference/studio-model.md

@@ -1,153 +1,153 @@
-# Studio Model for RDC Design
-
-Studio is the token authority and live website editor for LIFEAI brands. It is not a page builder. The design skill must work with Studio's real routes, APIs, token tables, and editor/debug model.
-
-## Required Source Docs
-
-Read these before Studio design work:
-
-- `docs/systems/studio/ARCHITECTURE.md`
-- `apps/studio/CLAUDE.md`
-- `.claude/context/design-system-global.md`
-
-## Runtime Locations
-
-- local Studio: `http://localhost:3011`
-- staging Studio: `https://staged.studio.regendevcorp.com`
-- production Studio: `https://studio.regendevcorp.com`
-
-## Brand Pages
-
-- `/brands`
-- `/brands/new`
-- `/brands/[id]/colors`
-- `/brands/[id]/typography`
-- `/brands/[id]/spacing`
-- `/brands/[id]/diff`
-- `/brands/[id]/book`
-- `/brands/[id]/voice`
-- `/brands/[id]/assets`
-- `/brands/[id]/export`
-- `/brands/[id]/table-styles`
-
-## Editor Routes
-
-- `/editor`
-- `/editor/local/[brandSlug]`
-- `/editor/local-test-target`
-- legacy `/editor/[brandSlug]` may redirect to local editor unless `?legacy=1`
-
-Read local debug docs:
-
-- `docs/systems/studio/local-debug-agent.md`
-
-Clauth relay route families:
-
-- `/studio/debug/*`
-- `/studio/claude/*`
-
-## Native Local Debug Model
-
-Studio live editing must use the RDC-owned local debug system, not an external live-edit runtime:
-
-1. Studio starts a local session with `POST /studio/debug/start`.
-2. Studio embeds the returned local `devUrl` with debug query params.
-3. `/api/editor/local-debug` injects Studio's own `local-debug-browser.js` picker.
-4. Browser/user events go to `/studio/debug/:sessionId/events`.
-5. Claude Code polls `/studio/claude/:sessionId/poll` with `scripts/studio-debug-poll.mjs`.
-6. Claude edits source files directly and replies to `/studio/claude/:sessionId/reply`.
-7. HMR updates the iframe.
-
-The disposable proof target is:
-
-- `/editor/local/test`
-- `apps/studio/src/app/editor/local-test-target/page.tsx`
-
-Direct edits must make exactly one source edit unless impossible. Variant edits should return alternatives without editing unless explicitly instructed to apply one. Reference replacement requires an explicit reference. Notes must not edit source.
-
-## Token APIs
-
-- `GET /api/public/tokens/[slug]` returns legacy public token payload and CSS variables.
-- `GET /api/v2/tokens/[slug]` returns DTCG/M3 token JSON.
-- `GET /api/v2/tokens/[slug]/css` returns shadcn-compatible CSS vars.
-
-Palette APIs currently start here:
-
-- `apps/studio/src/app/api/palettes/route.ts`
-- `apps/studio/src/app/api/palettes/apply/route.ts`
-
-## Canonical Tables
-
-Current token and theme work should prefer v2 where available:
-
-- `global_design_tokens_v2`
-- `brand_token_overrides_v2`
-- `brand_semantic_tokens`
-- `brand_components`
-- `brand_patterns`
-- `token_inheritance_audit`
-
-Legacy/current website token tables:
-
-- `brand_token_overrides`
-- `brand_font_assignments`
-- `brand_fonts`
-
-Legacy read-only or migration tables:
-
-- `global_design_tokens`
-- `brand_colors`
-- `brand_typography`
-- `brand_spacing`
-
-Docs/narrative:
-
-- `brand_design_docs`
-
-Registry/hierarchy:
-
-- `brand_entities`
-- `org_entities`
-
-## Key Files
-
-- `apps/studio/src/contexts/BrandStudioContext.tsx`
-- `apps/studio/src/lib/token-resolver.ts`
-- `apps/studio/src/lib/token-resolver-v2.ts`
-- `apps/studio/src/lib/token-export.ts`
-- `packages/design-tokens/src/types.ts`
-- `packages/ui/src/components/WebsiteLayout.tsx`
-- `packages/ui/src/styles/website-base.css`
-
-## BrandStudioContext
-
-Child pages under `/brands/[id]/*` should use `useBrandStudio()` instead of re-fetching tokens. It provides:
-
-- `brand`
-- `resolved`
-- `setResolved`
-- `globals`
-- `overrides`
-- `loaded`
-
-## Token Rules
-
-- Use Studio tokens for every production design decision.
-- Never invent a brand slug. Query `brand_entities`.
-- Never modify locked governance tokens without an explicit governance decision.
-- Missing token protocol: create a work item, use closest existing token temporarily, and mark the gap.
-- Production code should use `var(--color-*)` or resolved Studio token output.
-
-## Palette Designer Boundary
-
-The forked Palette Designer is a separate tool. Studio should launch it only when installed/enabled/healthy. It should load and save through Palette Library APIs, then Studio should reflect saved palettes.
-
-Do not rebuild Palette Designer inside the colors page in the first pass.
-
-## Deprecated Routes
-
-Do not extend:
-
-- `/api/editor/render`
-- `/api/layout/scan` unless maintaining legacy scanner behavior
-- `/api/layout/sync`
+# Studio Model for RDC Design
+
+Studio is the token authority and live website editor for LIFEAI brands. It is not a page builder. The design skill must work with Studio's real routes, APIs, token tables, and editor/debug model.
+
+## Required Source Docs
+
+Read these before Studio design work:
+
+- `docs/systems/studio/ARCHITECTURE.md`
+- `apps/studio/CLAUDE.md`
+- `.claude/context/design-system-global.md`
+
+## Runtime Locations
+
+- local Studio: `http://localhost:3011`
+- staging Studio: `https://staged.studio.regendevcorp.com`
+- production Studio: `https://studio.regendevcorp.com`
+
+## Brand Pages
+
+- `/brands`
+- `/brands/new`
+- `/brands/[id]/colors`
+- `/brands/[id]/typography`
+- `/brands/[id]/spacing`
+- `/brands/[id]/diff`
+- `/brands/[id]/book`
+- `/brands/[id]/voice`
+- `/brands/[id]/assets`
+- `/brands/[id]/export`
+- `/brands/[id]/table-styles`
+
+## Editor Routes
+
+- `/editor`
+- `/editor/local/[brandSlug]`
+- `/editor/local-test-target`
+- legacy `/editor/[brandSlug]` may redirect to local editor unless `?legacy=1`
+
+Read local debug docs:
+
+- `docs/systems/studio/local-debug-agent.md`
+
+Clauth relay route families:
+
+- `/studio/debug/*`
+- `/studio/claude/*`
+
+## Native Local Debug Model
+
+Studio live editing must use the RDC-owned local debug system, not an external live-edit runtime:
+
+1. Studio starts a local session with `POST /studio/debug/start`.
+2. Studio embeds the returned local `devUrl` with debug query params.
+3. `/api/editor/local-debug` injects Studio's own `local-debug-browser.js` picker.
+4. Browser/user events go to `/studio/debug/:sessionId/events`.
+5. Claude Code polls `/studio/claude/:sessionId/poll` with `scripts/studio-debug-poll.mjs`.
+6. Claude edits source files directly and replies to `/studio/claude/:sessionId/reply`.
+7. HMR updates the iframe.
+
+The disposable proof target is:
+
+- `/editor/local/test`
+- `apps/studio/src/app/editor/local-test-target/page.tsx`
+
+Direct edits must make exactly one source edit unless impossible. Variant edits should return alternatives without editing unless explicitly instructed to apply one. Reference replacement requires an explicit reference. Notes must not edit source.
+
+## Token APIs
+
+- `GET /api/public/tokens/[slug]` returns legacy public token payload and CSS variables.
+- `GET /api/v2/tokens/[slug]` returns DTCG/M3 token JSON.
+- `GET /api/v2/tokens/[slug]/css` returns shadcn-compatible CSS vars.
+
+Palette APIs currently start here:
+
+- `apps/studio/src/app/api/palettes/route.ts`
+- `apps/studio/src/app/api/palettes/apply/route.ts`
+
+## Canonical Tables
+
+Current token and theme work should prefer v2 where available:
+
+- `global_design_tokens_v2`
+- `brand_token_overrides_v2`
+- `brand_semantic_tokens`
+- `brand_components`
+- `brand_patterns`
+- `token_inheritance_audit`
+
+Legacy/current website token tables:
+
+- `brand_token_overrides`
+- `brand_font_assignments`
+- `brand_fonts`
+
+Legacy read-only or migration tables:
+
+- `global_design_tokens`
+- `brand_colors`
+- `brand_typography`
+- `brand_spacing`
+
+Docs/narrative:
+
+- `brand_design_docs`
+
+Registry/hierarchy:
+
+- `brand_entities`
+- `org_entities`
+
+## Key Files
+
+- `apps/studio/src/contexts/BrandStudioContext.tsx`
+- `apps/studio/src/lib/token-resolver.ts`
+- `apps/studio/src/lib/token-resolver-v2.ts`
+- `apps/studio/src/lib/token-export.ts`
+- `packages/design-tokens/src/types.ts`
+- `packages/ui/src/components/WebsiteLayout.tsx`
+- `packages/ui/src/styles/website-base.css`
+
+## BrandStudioContext
+
+Child pages under `/brands/[id]/*` should use `useBrandStudio()` instead of re-fetching tokens. It provides:
+
+- `brand`
+- `resolved`
+- `setResolved`
+- `globals`
+- `overrides`
+- `loaded`
+
+## Token Rules
+
+- Use Studio tokens for every production design decision.
+- Never invent a brand slug. Query `brand_entities`.
+- Never modify locked governance tokens without an explicit governance decision.
+- Missing token protocol: create a work item, use closest existing token temporarily, and mark the gap.
+- Production code should use `var(--color-*)` or resolved Studio token output.
+
+## Palette Designer Boundary
+
+The forked Palette Designer is a separate tool. Studio should launch it only when installed/enabled/healthy. It should load and save through Palette Library APIs, then Studio should reflect saved palettes.
+
+Do not rebuild Palette Designer inside the colors page in the first pass.
+
+## Deprecated Routes
+
+Do not extend:
+
+- `/api/editor/render`
+- `/api/layout/scan` unless maintaining legacy scanner behavior
+- `/api/layout/sync`

package/skills/edit/SKILL.md

@@ -1,98 +1,98 @@
----
-name: rdc:edit
-description: "Usage `rdc:edit <site|brand|route|file>` — open the local website editor host for a target site, brand, route, or file. Resolves the target, launches or reuses the local editor host on port 3015, and opens the target in the browser when not under `RDC_TEST=1`."
----
-
-> **⚠️ OUTPUT CONTRACT (READ FIRST):** `guides/output-contract.md`
-> Checklist-only output. No tool-call narration. No raw MCP/JSON/log dumps.
-> One checklist upfront, updated in place, shown again at end with a 1-line verdict.
-
-> If dispatching subagents or running as a subagent: read `{PROJECT_ROOT}/.rdc/guides/agent-bootstrap.md` first (fallback: `{PROJECT_ROOT}/.rdc/guides/agent-bootstrap.md`).
-
-> **Sandbox contract:** This skill honors `RDC_TEST=1`. Under test, do not steal focus or rely on foreground-only browser automation; report the resolved editor URL instead.
-
-
-# rdc:edit — Local Website Editor Launcher
-
-## When to Use
-- The user wants to open a site, brand, route, or file in the local editor app
-- The user says "open this in the editor" or asks for the editor-host workflow
-- The target should be loaded in `@regen/editor-host` rather than Studio
-
-## Arguments
-- `rdc:edit <site|brand|route|file>` — resolve the target and open it in the local editor host
-
-## Procedure
-
-### 1. Read the local editor contract
-- Read `apps/editor/CLAUDE.md` before launching anything.
-- If the target is Studio-specific, prefer `rdc:design edit <target>` instead.
-
-### 2. Resolve the target
-- For known LIFEAI brand targets, map to the obvious brand/app pair first.
-- `prtrust.fund` and `dev.prtrust.fund` resolve to `brandSlug=prt` and `appSlug=prt`.
-- `test`, `studio_test`, and `studio-test` resolve to `brandSlug=test` and `appSlug=studio_test`.
-- If the target is a local file or route and the brand/app is unclear, ask one concise question.
-
-Resolve the **target dev server** (package + port) so the preview iframe has
-something live to load. Read the brand app's `package.json` `name` and its
-`dev` script port — never hard-code a stale port:
-
-| Target | App dir | Package (`name`) | Dev port | `targetUrl` |
-|--------|---------|------------------|----------|-------------|
-| `prt` / `prtrust.fund` | `apps/prt` | `@regen/prt-portal` | `3006` | `http://localhost:3006` |
-| `test` / `studio_test` | (bundled) | — (editor host serves it) | `3015` | auto (`/editor/local-test-target`) |
-
-For any other brand, derive the package name and port by reading
-`apps/<app>/package.json` (`name` field and the `--port` in the `dev` script).
-`brandSlug=test` needs no target server — the editor host serves the fixture
-on its own origin.
-
-### 3. Start or reuse BOTH servers (edit starts everything)
-`rdc:edit` must bring up everything the preview needs — the editor host AND the
-target brand's dev server. Start-or-reuse each: probe the port first, only
-launch if it is dead.
-
-**3a. Editor host (`http://localhost:3015`)**
-- Probe: `curl -s -o /dev/null -w "%{http_code}" http://localhost:3015/` — any
-  non-`000` means it is already up; reuse it.
-- Launch only if down (background, do not block the session):
-  ```powershell
-  pnpm --filter @regen/editor-host dev
-  ```
-
-**3b. Target brand dev server (skip for `brandSlug=test`)**
-- Probe the resolved dev port (e.g. `http://localhost:3006/`). Non-`000` =
-  already running; reuse it. `EADDRINUSE` on launch also means reuse — not an error.
-- Launch only if down (background), then health-wait on the port before opening:
-  ```powershell
-  pnpm --filter <package> dev
-  ```
-  Bounded health-wait only (no `for`/`seq`/`sleep` polling loops):
-  ```bash
-  until curl -s -o /dev/null http://localhost:<port>/; do sleep 2; done
-  ```
-- Open the editor page for the resolved target once BOTH report a live code:
-  ```txt
-  http://localhost:3015/editor/local/<brandSlug>?appSlug=<appSlug>&targetUrl=<targetUrl>
-  ```
-
-### 4. Open the page
-- Normal use: open the URL in the browser and confirm the editor loaded.
-  Open via PowerShell `Start-Process`, NOT `cmd start` — `cmd` treats the `&`
-  between query params as a command separator and truncates the URL:
-  ```powershell
-  Start-Process 'http://localhost:3015/editor/local/<brandSlug>?appSlug=<appSlug>&targetUrl=<targetUrl>'
-  ```
-- `RDC_TEST=1`: do not force a foreground browser action; report the exact editor URL and whether the target was resolved.
-
-### 5. Report the result
-- Return a concise line with:
-  - the resolved target
-  - the editor URL
-  - whether the page was opened or only prepared in test mode
-
-## Guardrails
-- Do not turn this into a full design audit.
-- Do not start Studio unless the target actually belongs there.
-- Do not do broad discovery when one target mapping is enough.
+---
+name: rdc:edit
+description: "Usage `rdc:edit <site|brand|route|file>` — open the local website editor host for a target site, brand, route, or file. Resolves the target, launches or reuses the local editor host on port 3015, and opens the target in the browser when not under `RDC_TEST=1`."
+---
+
+> **⚠️ OUTPUT CONTRACT (READ FIRST):** `guides/output-contract.md`
+> Checklist-only output. No tool-call narration. No raw MCP/JSON/log dumps.
+> One checklist upfront, updated in place, shown again at end with a 1-line verdict.
+
+> If dispatching subagents or running as a subagent: read `{PROJECT_ROOT}/.rdc/guides/agent-bootstrap.md` first (fallback: `{PROJECT_ROOT}/.rdc/guides/agent-bootstrap.md`).
+
+> **Sandbox contract:** This skill honors `RDC_TEST=1`. Under test, do not steal focus or rely on foreground-only browser automation; report the resolved editor URL instead.
+
+
+# rdc:edit — Local Website Editor Launcher
+
+## When to Use
+- The user wants to open a site, brand, route, or file in the local editor app
+- The user says "open this in the editor" or asks for the editor-host workflow
+- The target should be loaded in `@regen/editor-host` rather than Studio
+
+## Arguments
+- `rdc:edit <site|brand|route|file>` — resolve the target and open it in the local editor host
+
+## Procedure
+
+### 1. Read the local editor contract
+- Read `apps/editor/CLAUDE.md` before launching anything.
+- If the target is Studio-specific, prefer `rdc:design edit <target>` instead.
+
+### 2. Resolve the target
+- For known LIFEAI brand targets, map to the obvious brand/app pair first.
+- `prtrust.fund` and `dev.prtrust.fund` resolve to `brandSlug=prt` and `appSlug=prt`.
+- `test`, `studio_test`, and `studio-test` resolve to `brandSlug=test` and `appSlug=studio_test`.
+- If the target is a local file or route and the brand/app is unclear, ask one concise question.
+
+Resolve the **target dev server** (package + port) so the preview iframe has
+something live to load. Read the brand app's `package.json` `name` and its
+`dev` script port — never hard-code a stale port:
+
+| Target | App dir | Package (`name`) | Dev port | `targetUrl` |
+|--------|---------|------------------|----------|-------------|
+| `prt` / `prtrust.fund` | `apps/prt` | `@regen/prt-portal` | `3006` | `http://localhost:3006` |
+| `test` / `studio_test` | (bundled) | — (editor host serves it) | `3015` | auto (`/editor/local-test-target`) |
+
+For any other brand, derive the package name and port by reading
+`apps/<app>/package.json` (`name` field and the `--port` in the `dev` script).
+`brandSlug=test` needs no target server — the editor host serves the fixture
+on its own origin.
+
+### 3. Start or reuse BOTH servers (edit starts everything)
+`rdc:edit` must bring up everything the preview needs — the editor host AND the
+target brand's dev server. Start-or-reuse each: probe the port first, only
+launch if it is dead.
+
+**3a. Editor host (`http://localhost:3015`)**
+- Probe: `curl -s -o /dev/null -w "%{http_code}" http://localhost:3015/` — any
+  non-`000` means it is already up; reuse it.
+- Launch only if down (background, do not block the session):
+  ```powershell
+  pnpm --filter @regen/editor-host dev
+  ```
+
+**3b. Target brand dev server (skip for `brandSlug=test`)**
+- Probe the resolved dev port (e.g. `http://localhost:3006/`). Non-`000` =
+  already running; reuse it. `EADDRINUSE` on launch also means reuse — not an error.
+- Launch only if down (background), then health-wait on the port before opening:
+  ```powershell
+  pnpm --filter <package> dev
+  ```
+  Bounded health-wait only (no `for`/`seq`/`sleep` polling loops):
+  ```bash
+  until curl -s -o /dev/null http://localhost:<port>/; do sleep 2; done
+  ```
+- Open the editor page for the resolved target once BOTH report a live code:
+  ```txt
+  http://localhost:3015/editor/local/<brandSlug>?appSlug=<appSlug>&targetUrl=<targetUrl>
+  ```
+
+### 4. Open the page
+- Normal use: open the URL in the browser and confirm the editor loaded.
+  Open via PowerShell `Start-Process`, NOT `cmd start` — `cmd` treats the `&`
+  between query params as a command separator and truncates the URL:
+  ```powershell
+  Start-Process 'http://localhost:3015/editor/local/<brandSlug>?appSlug=<appSlug>&targetUrl=<targetUrl>'
+  ```
+- `RDC_TEST=1`: do not force a foreground browser action; report the exact editor URL and whether the target was resolved.
+
+### 5. Report the result
+- Return a concise line with:
+  - the resolved target
+  - the editor URL
+  - whether the page was opened or only prepared in test mode
+
+## Guardrails
+- Do not turn this into a full design audit.
+- Do not start Studio unless the target actually belongs there.
+- Do not do broad discovery when one target mapping is enough.

package/skills/env/SKILL.md

@@ -0,0 +1,141 @@
+---
+name: rdc:env
+description: "Usage `rdc:env [status|install|repair|update]` — Manage the LIFEAI environment harness: check status, install on a fresh box, repair broken services, or pull updates. Reads $LIFEAI_ENV/manifest.json as the source of truth. Use when: 'check the environment', 'install environment', 'repair environment', 'update environment', 'setup env', 'fix env', 'env status', or after a reboot/GPU crash."
+---
+
+> **⚠️ OUTPUT CONTRACT (READ FIRST):** `guides/output-contract.md`
+> Checklist-only output. No tool-call narration. No raw MCP/JSON/log dumps.
+> One checklist upfront, updated in place, shown again at end with a 1-line verdict.
+
+# rdc:env — Environment Harness Manager
+
+## When to Use
+- After a reboot or GPU crash — verify everything came back up
+- Setting up a fresh box — install all tools and services
+- Something is broken — repair services, MCPs, CodeFlow
+- Routine update — pull latest env repo and run drift check
+- "check the environment", "fix my setup", "install environment"
+
+## Subcommands
+
+| Command | What it does |
+|---------|-------------|
+| `status` (default) | Read-only check: env repo version, tool versions, MCP health, shim integrity, CodeFlow brain |
+| `install` | Full provision: clone env repo if missing, set LIFEAI_ENV, install tools, configure MCPs |
+| `repair` | Diagnose and fix: restart crashed services, rebuild stale dists, fix broken shims |
+| `update` | Pull latest env repo, re-run audit, report drift, refresh shims if new scripts added |
+
+## Procedure
+
+### Step 0: Resolve environment root
+
+```bash
+LIFEAI_ENV="${LIFEAI_ENV:-C:/Dev/lifeai-env}"
+```
+
+If `$LIFEAI_ENV` is not set AND the default path doesn't exist:
+- For `install`: clone the repo and set the env var
+- For all others: STOP with `BLOCKED: environment repo not found. Run: rdc:env install`
+
+Read `$LIFEAI_ENV/manifest.json` — this is the harness inventory.
+
+### Step 1: Environment repo state
+
+```bash
+git -C "$LIFEAI_ENV" fetch origin 2>/dev/null
+git -C "$LIFEAI_ENV" rev-list --count HEAD..origin/main
+```
+
+Report: version from manifest.json, commits behind origin, last pull date.
+
+For `update`: pull if behind. For `repair`: pull if behind (stale harness may be the cause).
+
+### Step 2: Tool versions (audit)
+
+Run the audit script:
+```bash
+pwsh.exe -NoProfile -ExecutionPolicy Bypass -File "$LIFEAI_ENV/audit/audit.ps1" -ProjectRoot "$PROJECT_ROOT"
+```
+
+Or read `$PROJECT_ROOT/environment.lock.json` and check each tool:
+
+| Tool | Check | Min Version |
+|------|-------|-------------|
+| node | `node --version` | 22.0.0 |
+| pnpm | `pnpm --version` | 10.0.0 |
+| pm2 | `pm2 --version` | 5.0.0 |
+| clauth | `curl -s http://127.0.0.1:52437/ping` | 1.30.0 |
+| rdc-skills | `npm list -g @lifeai/rdc-skills` | 0.25.0 |
+| gh | `gh --version` | 2.0.0 |
+
+For `install` and `repair`: install or upgrade any tool below min_version using the `install` command from the lock file. This includes rdc-skills itself — the environment repo is the orchestrator that keeps all tools current, including its own skill set. A `repair` or `install` that bumps rdc-skills will also restart the rdc-skills-mcp PM2 process so the new version is live immediately.
+
+### Step 3: Service health
+
+Check each service:
+
+| Service | Health Check | Repair |
+|---------|-------------|--------|
+| clauth daemon | `curl -s http://127.0.0.1:52437/ping` | `$LIFEAI_ENV/services/restart-clauth.bat` |
+| CodeFlow gateway | `curl -s http://127.0.0.1:3109/health` | `node $PROJECT_ROOT/scripts/codeflow-up.mjs` |
+| CodeFlow brain | `/health` → `health.state` should be `operational` | `node $PROJECT_ROOT/scripts/codeflow-up.mjs --restart` |
+| rdc-skills MCP | `pm2 list` shows rdc-skills-mcp online | `pm2 restart rdc-skills-mcp` |
+| PM2 daemon | `pm2 ping` | `pm2 resurrect` |
+| Docker | `docker info` | Start Docker Desktop |
+| Neo4j | `docker inspect codeflow-neo4j` | `docker compose -f $LIFEAI_ENV/services/codeflow/docker-compose.yml up -d` |
+
+For `status`: report only. For `repair`: fix each failing service in order (clauth first, then CodeFlow, then MCPs).
+
+### Step 4: MCP server verification
+
+Run the MCP checker:
+```bash
+pwsh.exe -NoProfile -ExecutionPolicy Bypass -File "$LIFEAI_ENV/services/install-mcps.ps1" -ProjectRoot "$PROJECT_ROOT"
+```
+
+For `repair`: add `-Fix` flag to auto-start missing local MCPs.
+
+### Step 5: Shim integrity
+
+Check that all monorepo shims point at valid targets:
+```bash
+pwsh.exe -NoProfile -ExecutionPolicy Bypass -File "$LIFEAI_ENV/provision.ps1" -ProjectRoot "$PROJECT_ROOT" -SkipTools -DryRun
+```
+
+Look for "broken shim" warnings. For `repair`: re-run provision.ps1 live.
+
+### Step 6: Agent readiness (final gate)
+
+```bash
+pnpm --filter @regen/codeflow startup:readiness
+```
+
+This is the same check the startup guard runs. Zero blockers = environment healthy.
+
+## Output Format
+
+```
+## rdc:env <command> — Environment Health
+
+| Check | Status | Detail |
+|-------|--------|--------|
+| Env repo | ✅ | v0.2.0, 0 behind origin |
+| LIFEAI_ENV | ✅ | C:/Dev/lifeai-env (Machine scope) |
+| Node | ✅ | v22.14.0 (min 22.0.0) |
+| pnpm | ✅ | 10.12.1 (min 10.0.0) |
+| clauth | ✅ | v1.30.2, unlocked |
+| CodeFlow | ✅ | v0.33.11, brain=dev, operational |
+| rdc-skills MCP | ✅ | v0.25.0, online |
+| Shims | ✅ | 47/47 valid |
+| Agent readiness | ✅ | 0 blockers |
+
+**Verdict: environment healthy (9/9 checks pass)**
+```
+
+For `repair`, append:
+```
+## Repairs Applied
+- [x] Restarted clauth daemon
+- [x] Rebuilt CodeFlow dist + restarted gateway
+- [ ] rdc-skills: already running
+```