@lifeaitools/rdc-skills 0.25.0 → 0.25.2

package/skills/design/SKILL.md

@@ -1,211 +1,211 @@
----
-name: rdc:design
-description: "Usage `rdc:design <topic>` — RDC-owned design work for Studio, Palette Library, and token-aware UI systems. Use for Rampant color work or design-system-first builds owned by the design cell. Not for general UI polish — use impeccable for that."
----
-
-> **⚠️ 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` per `guides/agent-bootstrap.md` § RDC_TEST Sandbox Contract. Destructive external calls, Supabase writes, git pushes, package publishes, and deploys are skipped under `RDC_TEST=1`.
-
-# rdc:design — RDC Design Skill
-
-RDC-owned design execution for Studio and LIFEAI interfaces. This skill is the Studio-aware design authority for RDC token, palette, theme, component, and local-debug work.
-
-## When to Use
-
-- Studio, Palette Library, brand-token, theme, component, or live-editor work
-- Any design task that must understand RDC's real token tables and Studio routes
+---
+name: rdc:design
+description: "Usage `rdc:design <topic>` — RDC-owned design work for Studio, Palette Library, and token-aware UI systems. Use for Rampant color work or design-system-first builds owned by the design cell. Not for general UI polish — use impeccable for that."
+---
+
+> **⚠️ 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` per `guides/agent-bootstrap.md` § RDC_TEST Sandbox Contract. Destructive external calls, Supabase writes, git pushes, package publishes, and deploys are skipped under `RDC_TEST=1`.
+
+# rdc:design — RDC Design Skill
+
+RDC-owned design execution for Studio and LIFEAI interfaces. This skill is the Studio-aware design authority for RDC token, palette, theme, component, and local-debug work.
+
+## When to Use
+
+- Studio, Palette Library, brand-token, theme, component, or live-editor work
+- Any design task that must understand RDC's real token tables and Studio routes
 - UI critique, audit, polish, colorize, type, layout, or craft work in `{PROJECT_ROOT}`
-- Agent-side color-system exploration using Rampa CLI
-- Preparing token-aware implementation instructions for frontend/backend/data agents
-
-## Arguments
-
-- `rdc:design` — show the command menu
-- `rdc:design edit <target>` — start a local source-edit session for a URL, app, brand, route, or file
-- `rdc:design studio <target>` — Studio-aware design task
-- `rdc:design tokens <brand-or-route>` — token model, resolver, export, or governance task
-- `rdc:design palette <brief>` — Palette Library or palette generation task
-- `rdc:design theme <brief>` — theme generation/application task
-- `rdc:design colorize <target>` — Rampa-assisted color-system work
-- `rdc:design audit <target>` — design quality audit
-- `rdc:design critique <target>` — UX/design critique
-- `rdc:design polish <target>` — final visual and interaction pass
-- `rdc:design craft <feature>` — shape and build a token-aware UI feature
-
-## Required References
-
-Load only what applies, but do not skip the Studio model for Studio/token/palette/theme work.
-
-| Task type | Required reference |
-|---|---|
-| Studio, tokens, palettes, themes, editor | `skills/design/reference/studio-model.md` |
-| Color generation, ramps, contrast, neutrals | `skills/design/reference/rampa.md` |
-| Ownership, operating boundary, attribution files | `skills/design/reference/ownership.md` |
-
-Project docs to read for Studio work:
-
-- `docs/systems/studio/ARCHITECTURE.md`
-- `apps/studio/CLAUDE.md`
-- `.claude/context/design-system-global.md`
-- affected route/component/source files
-
-## Procedure
-
-1. **Classify the task.**
-   - `edit` means start a local source-edit session. Do not show the generic command menu for `edit`.
-   - `studio`, `tokens`, `palette`, and `theme` always load the Studio model.
-   - `palette`, `theme`, and `colorize` also load the Rampa reference.
-   - Any task involving colors, palettes, ramps, contrast, neutrals, light/dark color pairs, status colors, chart colors, or theme colors loads the Rampa reference.
-   - `audit`, `critique`, `polish`, and `craft` load Studio model when the target is inside Studio or uses Studio tokens.
-
-2. **Read the actual system context.**
-   - For Studio: read `docs/systems/studio/ARCHITECTURE.md` and `apps/studio/CLAUDE.md`.
-   - For token work: read `.claude/context/design-system-global.md`.
-   - For app UI work: read the app-specific `CLAUDE.md` if present.
-
-3. **Find the source of truth before proposing changes.**
-   - Tokens: Studio APIs, resolver files, and Supabase token tables.
-   - Palette Library: Studio palette APIs and theme/palette model.
-   - Live editor: RDC Native Local Debug only — `/editor/local/*`, `/api/editor/local-debug`, `/studio/debug/*`, `/studio/claude/*`, and `scripts/studio-debug-poll.mjs`.
-   - Components: `@regen/ui`, Studio component registry, and existing local components.
-
-4. **For `edit`, start the local session directly.**
-   - Intent syntax:
-     ```powershell
-     rdc:design edit <url|domain|brand|app|file>
-     ```
-   - Required variables:
-     - `target`
-     - `brandSlug`
-     - `appSlug`
-     - `repoRoot`
-     - `cwd`
-     - `connectorBaseUrl`
-     - `studioOrigin`
-     - `modeDefault`
-   - Fill missing variables from the obvious target mapping before asking:
-     - `test`, `studio_test`, `studio-test` -> `--brand test --app studio_test`
-     - `prt`, `prt-portal`, `prtrust.fund`, `dev.prtrust.fund` -> `--brand prt --app prt`
-   - If the target is a file path and brand/app are not obvious, ask one concise question for the missing brand/app. Do not search broadly or show the generic command menu.
-   - Canonical start call:
-     ```powershell
-     curl.exe -s -X POST "http://127.0.0.1:52437/studio/debug/start" `
-       -H "Content-Type: application/json" `
-       -d "{\"brandSlug\":\"<brandSlug>\",\"appSlug\":\"<appSlug>\",\"repoRoot\":\"{PROJECT_ROOT}\",\"cwd\":\"{PROJECT_ROOT}\",\"modeDefault\":\"direct_edit\",\"startedBy\":\"claude-cli\"}"
-     ```
-   - Expected successful response shape:
-     ```json
-     {
-       "ok": true,
-       "sessionId": "studio-...",
-       "token": "...",
-       "devUrl": "http://localhost:3006",
-       "relayBaseUrl": "http://127.0.0.1:52437/studio/debug/studio-...",
-       "claudeBaseUrl": "http://127.0.0.1:52437/studio/claude/studio-...",
-       "pollCommand": "node scripts/studio-debug-poll.mjs --session ... --token ... --relay ..."
-     }
-     ```
-   - Construct the Studio attach URL exactly:
-     ```txt
-     http://localhost:3011/editor/local/<brandSlug>?attach=1&sessionId=<sessionId>&token=<token>
-     ```
-   - Never send the user to `/editor/local/<brandSlug>` without `attach=1&sessionId=...&token=...`.
-   - Canonical poll call:
-     ```powershell
-     curl.exe -s "http://127.0.0.1:52437/studio/claude/<sessionId>/poll?token=<token>&timeout=600000"
-     ```
-   - Canonical reply call:
-     ```powershell
-     curl.exe -s -X POST "http://127.0.0.1:52437/studio/claude/<sessionId>/reply" `
-       -H "Content-Type: application/json" `
-       -d "{\"token\":\"<token>\",\"eventId\":\"<eventId>\",\"status\":\"done\",\"message\":\"Edited <path>\",\"filesChanged\":[\"<path>\"]}"
-     ```
-   - Allowed terminal statuses are `done`, `error`, `blocked`, and `needs_reference`.
-   - Convenience helper, equivalent to the canonical start call plus attach URL construction:
-     ```powershell
-     node scripts/studio-debug-start.mjs --target <url|domain|brand|app|file> [--brand <slug>] [--app <slug>] [--mode direct_edit|variant_edit|reference_replace|note] [--studio-origin http://localhost:3011] [--connector http://127.0.0.1:52437] [--repo-root {PROJECT_ROOT}] [--cwd {PROJECT_ROOT}] [--dev-url <url>] [--dev-command <command>] [--no-launch]
-     ```
-   - Helper output contract:
-     ```txt
-     STUDIO_URL=http://localhost:3011/editor/local/<brandSlug>?attach=1&sessionId=...&token=...
-     POLL_COMMAND=node scripts/studio-debug-poll.mjs --session ... --token ... --relay ...
-     SESSION_FILE=.studio-debug/<sessionId>.json
-     ```
-   - If using the helper, run:
-     ```powershell
-     node scripts/studio-debug-start.mjs --target <target>
-     ```
-   - Return `STUDIO_URL` and `POLL_COMMAND` to the user. If operating as Claude CLI, open or instruct opening `STUDIO_URL`, then run `POLL_COMMAND`.
-   - After an event is received, edit the source directly and reply with the helper or canonical reply call:
-     ```powershell
-     node scripts/studio-debug-poll.mjs --session <sessionId> --token <token> --relay <claudeBaseUrl> --reply <eventId> done --file <path> --message "Edited <path>"
-     ```
-
-5. **Use Rampa only as proposal tooling.**
-   - Run Rampa CLI for color ramps, APCA/WCAG checks, tinted neutrals, status palettes, or data-viz palettes.
-   - Treat output as draft design material.
-   - Persist only after mapping into Studio token roles or Palette Library payloads.
-
-6. **Apply RDC design rules.**
-   - Use Studio tokens for production surfaces.
-   - Do not hardcode color/font/spacing when a token exists.
-   - Do not modify locked governance tokens.
-   - Keep product UIs compact, operational, and scannable.
-   - Avoid generic AI design patterns and card-heavy layouts.
-
-7. **Plan edits before mutating files.**
-   - State the files/routes/tables involved.
-   - Use RDC work-item protocol for non-trivial implementation.
-   - Keep unrelated installed skills and vendor artifacts untouched.
-
-8. **Verify.**
-   - Run scoped tests only.
-   - For Studio: prefer route smoke checks, token API checks, and browser screenshots when UI changed.
+- Agent-side color-system exploration using Rampa CLI
+- Preparing token-aware implementation instructions for frontend/backend/data agents
+
+## Arguments
+
+- `rdc:design` — show the command menu
+- `rdc:design edit <target>` — start a local source-edit session for a URL, app, brand, route, or file
+- `rdc:design studio <target>` — Studio-aware design task
+- `rdc:design tokens <brand-or-route>` — token model, resolver, export, or governance task
+- `rdc:design palette <brief>` — Palette Library or palette generation task
+- `rdc:design theme <brief>` — theme generation/application task
+- `rdc:design colorize <target>` — Rampa-assisted color-system work
+- `rdc:design audit <target>` — design quality audit
+- `rdc:design critique <target>` — UX/design critique
+- `rdc:design polish <target>` — final visual and interaction pass
+- `rdc:design craft <feature>` — shape and build a token-aware UI feature
+
+## Required References
+
+Load only what applies, but do not skip the Studio model for Studio/token/palette/theme work.
+
+| Task type | Required reference |
+|---|---|
+| Studio, tokens, palettes, themes, editor | `skills/design/reference/studio-model.md` |
+| Color generation, ramps, contrast, neutrals | `skills/design/reference/rampa.md` |
+| Ownership, operating boundary, attribution files | `skills/design/reference/ownership.md` |
+
+Project docs to read for Studio work:
+
+- `docs/systems/studio/ARCHITECTURE.md`
+- `apps/studio/CLAUDE.md`
+- `.claude/context/design-system-global.md`
+- affected route/component/source files
+
+## Procedure
+
+1. **Classify the task.**
+   - `edit` means start a local source-edit session. Do not show the generic command menu for `edit`.
+   - `studio`, `tokens`, `palette`, and `theme` always load the Studio model.
+   - `palette`, `theme`, and `colorize` also load the Rampa reference.
+   - Any task involving colors, palettes, ramps, contrast, neutrals, light/dark color pairs, status colors, chart colors, or theme colors loads the Rampa reference.
+   - `audit`, `critique`, `polish`, and `craft` load Studio model when the target is inside Studio or uses Studio tokens.
+
+2. **Read the actual system context.**
+   - For Studio: read `docs/systems/studio/ARCHITECTURE.md` and `apps/studio/CLAUDE.md`.
+   - For token work: read `.claude/context/design-system-global.md`.
+   - For app UI work: read the app-specific `CLAUDE.md` if present.
+
+3. **Find the source of truth before proposing changes.**
+   - Tokens: Studio APIs, resolver files, and Supabase token tables.
+   - Palette Library: Studio palette APIs and theme/palette model.
+   - Live editor: RDC Native Local Debug only — `/editor/local/*`, `/api/editor/local-debug`, `/studio/debug/*`, `/studio/claude/*`, and `scripts/studio-debug-poll.mjs`.
+   - Components: `@regen/ui`, Studio component registry, and existing local components.
+
+4. **For `edit`, start the local session directly.**
+   - Intent syntax:
+     ```powershell
+     rdc:design edit <url|domain|brand|app|file>
+     ```
+   - Required variables:
+     - `target`
+     - `brandSlug`
+     - `appSlug`
+     - `repoRoot`
+     - `cwd`
+     - `connectorBaseUrl`
+     - `studioOrigin`
+     - `modeDefault`
+   - Fill missing variables from the obvious target mapping before asking:
+     - `test`, `studio_test`, `studio-test` -> `--brand test --app studio_test`
+     - `prt`, `prt-portal`, `prtrust.fund`, `dev.prtrust.fund` -> `--brand prt --app prt`
+   - If the target is a file path and brand/app are not obvious, ask one concise question for the missing brand/app. Do not search broadly or show the generic command menu.
+   - Canonical start call:
+     ```powershell
+     curl.exe -s -X POST "http://127.0.0.1:52437/studio/debug/start" `
+       -H "Content-Type: application/json" `
+       -d "{\"brandSlug\":\"<brandSlug>\",\"appSlug\":\"<appSlug>\",\"repoRoot\":\"{PROJECT_ROOT}\",\"cwd\":\"{PROJECT_ROOT}\",\"modeDefault\":\"direct_edit\",\"startedBy\":\"claude-cli\"}"
+     ```
+   - Expected successful response shape:
+     ```json
+     {
+       "ok": true,
+       "sessionId": "studio-...",
+       "token": "...",
+       "devUrl": "http://localhost:3006",
+       "relayBaseUrl": "http://127.0.0.1:52437/studio/debug/studio-...",
+       "claudeBaseUrl": "http://127.0.0.1:52437/studio/claude/studio-...",
+       "pollCommand": "node scripts/studio-debug-poll.mjs --session ... --token ... --relay ..."
+     }
+     ```
+   - Construct the Studio attach URL exactly:
+     ```txt
+     http://localhost:3011/editor/local/<brandSlug>?attach=1&sessionId=<sessionId>&token=<token>
+     ```
+   - Never send the user to `/editor/local/<brandSlug>` without `attach=1&sessionId=...&token=...`.
+   - Canonical poll call:
+     ```powershell
+     curl.exe -s "http://127.0.0.1:52437/studio/claude/<sessionId>/poll?token=<token>&timeout=600000"
+     ```
+   - Canonical reply call:
+     ```powershell
+     curl.exe -s -X POST "http://127.0.0.1:52437/studio/claude/<sessionId>/reply" `
+       -H "Content-Type: application/json" `
+       -d "{\"token\":\"<token>\",\"eventId\":\"<eventId>\",\"status\":\"done\",\"message\":\"Edited <path>\",\"filesChanged\":[\"<path>\"]}"
+     ```
+   - Allowed terminal statuses are `done`, `error`, `blocked`, and `needs_reference`.
+   - Convenience helper, equivalent to the canonical start call plus attach URL construction:
+     ```powershell
+     node scripts/studio-debug-start.mjs --target <url|domain|brand|app|file> [--brand <slug>] [--app <slug>] [--mode direct_edit|variant_edit|reference_replace|note] [--studio-origin http://localhost:3011] [--connector http://127.0.0.1:52437] [--repo-root {PROJECT_ROOT}] [--cwd {PROJECT_ROOT}] [--dev-url <url>] [--dev-command <command>] [--no-launch]
+     ```
+   - Helper output contract:
+     ```txt
+     STUDIO_URL=http://localhost:3011/editor/local/<brandSlug>?attach=1&sessionId=...&token=...
+     POLL_COMMAND=node scripts/studio-debug-poll.mjs --session ... --token ... --relay ...
+     SESSION_FILE=.studio-debug/<sessionId>.json
+     ```
+   - If using the helper, run:
+     ```powershell
+     node scripts/studio-debug-start.mjs --target <target>
+     ```
+   - Return `STUDIO_URL` and `POLL_COMMAND` to the user. If operating as Claude CLI, open or instruct opening `STUDIO_URL`, then run `POLL_COMMAND`.
+   - After an event is received, edit the source directly and reply with the helper or canonical reply call:
+     ```powershell
+     node scripts/studio-debug-poll.mjs --session <sessionId> --token <token> --relay <claudeBaseUrl> --reply <eventId> done --file <path> --message "Edited <path>"
+     ```
+
+5. **Use Rampa only as proposal tooling.**
+   - Run Rampa CLI for color ramps, APCA/WCAG checks, tinted neutrals, status palettes, or data-viz palettes.
+   - Treat output as draft design material.
+   - Persist only after mapping into Studio token roles or Palette Library payloads.
+
+6. **Apply RDC design rules.**
+   - Use Studio tokens for production surfaces.
+   - Do not hardcode color/font/spacing when a token exists.
+   - Do not modify locked governance tokens.
+   - Keep product UIs compact, operational, and scannable.
+   - Avoid generic AI design patterns and card-heavy layouts.
+
+7. **Plan edits before mutating files.**
+   - State the files/routes/tables involved.
+   - Use RDC work-item protocol for non-trivial implementation.
+   - Keep unrelated installed skills and vendor artifacts untouched.
+
+8. **Verify.**
+   - Run scoped tests only.
+   - For Studio: prefer route smoke checks, token API checks, and browser screenshots when UI changed.
    - For CLI prompt work: run `node {RDC_SKILLS_ROOT}/scripts/rdc-design-cli.mjs <command> <brief>` and inspect the generated report under `.rdc/reports/rdc-design-cli/`.
-
-## Command Menu
-
-| Command | Purpose |
-|---|---|
-| `edit` | Start a local source-edit session for a URL, app, brand, route, or file |
-| `studio` | Studio-aware design/build task with token, route, and editor context |
-| `tokens` | Diagnose or design token usage, resolver flow, API/export, governance |
-| `palette` | Palette Library work, palette generation, external Palette Designer handoff |
-| `theme` | Theme creation/application/export against Studio's canonical model |
-| `colorize` | Rampa-assisted color relationships and contrast checks |
-| `audit` | Technical and visual audit |
-| `critique` | UX/design review |
-| `polish` | Final detail pass |
-| `craft` | Shape and build a token-aware interface |
-
-## CLI Helper
-
-Use the local helper to see exactly how much instruction text the skill is generating before sending it through an agent:
-
-```powershell
+
+## Command Menu
+
+| Command | Purpose |
+|---|---|
+| `edit` | Start a local source-edit session for a URL, app, brand, route, or file |
+| `studio` | Studio-aware design/build task with token, route, and editor context |
+| `tokens` | Diagnose or design token usage, resolver flow, API/export, governance |
+| `palette` | Palette Library work, palette generation, external Palette Designer handoff |
+| `theme` | Theme creation/application/export against Studio's canonical model |
+| `colorize` | Rampa-assisted color relationships and contrast checks |
+| `audit` | Technical and visual audit |
+| `critique` | UX/design review |
+| `polish` | Final detail pass |
+| `craft` | Shape and build a token-aware interface |
+
+## CLI Helper
+
+Use the local helper to see exactly how much instruction text the skill is generating before sending it through an agent:
+
+```powershell
 node {RDC_SKILLS_ROOT}/scripts/rdc-design-cli.mjs studio "audit the Studio palette page"
 node {RDC_SKILLS_ROOT}/scripts/rdc-design-cli.mjs palette "generate a PRT palette workflow"
 node {RDC_SKILLS_ROOT}/scripts/rdc-design-cli.mjs --json theme "RDC earth-forward light theme"
-```
-
-The helper writes logs to:
-
-```text
+```
+
+The helper writes logs to:
+
+```text
 {RDC_SKILLS_ROOT}/.rdc/reports/rdc-design-cli/
-```
-
-Each run includes character count, word count, approximate token count, references loaded, and the final prompt text.
-
-## Boundaries
-
-- Do not edit unrelated installed skills.
-- Do not rename this skill or create duplicate aliases for it.
-- Do not use external live-edit runtimes as Studio's live-edit execution path.
-- Do not persist Rampa output directly to production without Studio token mapping.
-- Do not fork or ship Palette Designer until its license is verified.
-- Do not use Studio's deprecated `/api/editor/render` route.
+```
+
+Each run includes character count, word count, approximate token count, references loaded, and the final prompt text.
+
+## Boundaries
+
+- Do not edit unrelated installed skills.
+- Do not rename this skill or create duplicate aliases for it.
+- Do not use external live-edit runtimes as Studio's live-edit execution path.
+- Do not persist Rampa output directly to production without Studio token mapping.
+- Do not fork or ship Palette Designer until its license is verified.
+- Do not use Studio's deprecated `/api/editor/render` route.

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
+```