@lifeaitools/rdc-skills 0.35.5 → 0.35.6

package/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "rdc",
-  "version": "0.35.5",
+  "version": "0.35.6",
   "description": "RDC typed-agent dispatch skill suite for Claude Code — plan, build, review, overnight unattended builds with work-item tracking and TDD enforcement.",
   "author": {
     "name": "LIFEAI",

package/commands/flow.md

@@ -49,7 +49,7 @@ rdc:flow normal                   # clear — back to no flow declared
 ### 1. Read the current state
 
 ```bash
-node -e "import('file:///C:/Dev/lifeai-env/hooks/lib/rdc-flow.mjs').then(m=>console.log(JSON.stringify(m.currentState(),null,2)))"
+node -e "import(require('url').pathToFileURL(process.env.LIFEAI_ENV + '/hooks/lib/rdc-flow.mjs').href).then(m=>console.log(JSON.stringify(m.currentState(),null,2)))"
 ```
 
 `currentState()` reads BOTH axes at once — the declared flow AND any live `rdc-mode.mjs` hotfix/maintenance window — because a relaxed mode overrides a required flow (loosest state wins) and a status check that only showed flow would miss that override entirely. Report `flow` (or `null` if nothing declared — the fail-closed default), `flowReason`/`flowSetBy`/`flowSetAt` when set, and `mode` (`normal` unless a hotfix/maintenance window is open), with `modeReason`/`modeMinutesLeft` when it isn't.
@@ -57,7 +57,7 @@ node -e "import('file:///C:/Dev/lifeai-env/hooks/lib/rdc-flow.mjs').then(m=>cons
 ### 2. Setting a plain work-shape flow — no reason required
 
 ```bash
-node -e "import('file:///C:/Dev/lifeai-env/hooks/lib/rdc-flow.mjs').then(m=>console.log(JSON.stringify(m.setFlow(process.argv[1],{setBy:process.argv[2]}),null,2)))" "<flow>" "<session-id>"
+node -e "import(require('url').pathToFileURL(process.env.LIFEAI_ENV + '/hooks/lib/rdc-flow.mjs').href).then(m=>console.log(JSON.stringify(m.setFlow(process.argv[1],{setBy:process.argv[2]}),null,2)))" "<flow>" "<session-id>"
 ```
 
 ### 3. Setting hotfix or maintenance — a reason is REQUIRED
@@ -65,7 +65,7 @@ node -e "import('file:///C:/Dev/lifeai-env/hooks/lib/rdc-flow.mjs').then(m=>cons
 Refuse to proceed without one — `setFlow` throws on an empty reason for these two values, by design, same as `setMode` always did: an unexplained disarm is how a temporary state becomes permanent.
 
 ```bash
-node -e "import('file:///C:/Dev/lifeai-env/hooks/lib/rdc-flow.mjs').then(m=>console.log(JSON.stringify(m.setFlow('hotfix',{reason:process.argv[1],setBy:process.argv[2]}),null,2)))" "<reason>" "<session-id>"
+node -e "import(require('url').pathToFileURL(process.env.LIFEAI_ENV + '/hooks/lib/rdc-flow.mjs').href).then(m=>console.log(JSON.stringify(m.setFlow('hotfix',{reason:process.argv[1],setBy:process.argv[2]}),null,2)))" "<reason>" "<session-id>"
 ```
 
 Then state plainly, in the checklist: **which guards are now relaxed, that the safety set is still armed, and that this stays active until explicitly cleared (no TTL — active management, not a silent timer).**
@@ -73,7 +73,7 @@ Then state plainly, in the checklist: **which guards are now relaxed, that the s
 ### 4. Returning to normal
 
 ```bash
-node -e "import('file:///C:/Dev/lifeai-env/hooks/lib/rdc-flow.mjs').then(m=>{m.clearFlow();console.log('cleared')})"
+node -e "import(require('url').pathToFileURL(process.env.LIFEAI_ENV + '/hooks/lib/rdc-flow.mjs').href).then(m=>{m.clearFlow();console.log('cleared')})"
 ```
 
 Do this **as soon as the incident is over**, or the moment the declared work-shape changes.

package/commands/mode.md

@@ -70,7 +70,7 @@ rdc:mode normal                       # close it early
 ### 1. Read the current mode
 
 ```bash
-node -e "import('file:///C:/Dev/lifeai-env/hooks/lib/rdc-mode.mjs').then(m=>console.log(JSON.stringify(m.currentMode(),null,2)))"
+node -e "import(require('url').pathToFileURL(process.env.LIFEAI_ENV + '/hooks/lib/rdc-mode.mjs').href).then(m=>console.log(JSON.stringify(m.currentMode(),null,2)))"
 ```
 
 Report `mode`, and when not normal also `reason`, `setBy`, and `minutesLeft`.
@@ -84,7 +84,7 @@ unexplained disarm is how a temporary state becomes permanent, and the reason is
 the entire content of the audit line.
 
 ```bash
-node -e "import('file:///C:/Dev/lifeai-env/hooks/lib/rdc-mode.mjs').then(m=>console.log(JSON.stringify(m.setMode('hotfix',{reason:process.argv[1],minutes:Number(process.argv[2]||60),setBy:process.argv[3]}),null,2)))" "<reason>" "<minutes>" "<session-id>"
+node -e "import(require('url').pathToFileURL(process.env.LIFEAI_ENV + '/hooks/lib/rdc-mode.mjs').href).then(m=>console.log(JSON.stringify(m.setMode('hotfix',{reason:process.argv[1],minutes:Number(process.argv[2]||60),setBy:process.argv[3]}),null,2)))" "<reason>" "<minutes>" "<session-id>"
 ```
 
 Then state plainly, in the checklist: **which guards are now off, that the safety
@@ -93,7 +93,7 @@ set is still armed, and the exact wall-clock time the window closes.**
 ### 3. Returning to normal
 
 ```bash
-node -e "import('file:///C:/Dev/lifeai-env/hooks/lib/rdc-mode.mjs').then(m=>{m.clearMode();console.log('normal')})"
+node -e "import(require('url').pathToFileURL(process.env.LIFEAI_ENV + '/hooks/lib/rdc-mode.mjs').href).then(m=>{m.clearMode();console.log('normal')})"
 ```
 
 Do this **as soon as the incident is over**. The window expiring on its own is

package/commands/open.md

@@ -0,0 +1,84 @@
+---
+name: open
+description: >-
+  Usage `rdc:open [<slug>]` — orient before working. Answers where you are (repo, worktree, branch, dirty state) and what the target is (runtime, port, host, deploy path) from the registry, then names the harness shape to use. Run this first in any session that will change something.
+---
+
+> **⚠️ OUTPUT CONTRACT (READ FIRST):** `guides/output-contract.md`
+> Checklist-only output. No tool-call narration. No raw MCP/JSON/log dumps.
+
+# rdc:open — you are here, this is the thing, use this shape
+
+## Why this exists
+
+Orientation ran **3.4× production work** across a measured 36-hour window —
+47.6% of tool calls establishing position and identity, 14.1% actually changing
+something. `git rev-parse` alone was 316 calls, 6% of everything.
+
+Cross-session rediscovery was **1.4%**. That number is the point: agents are not
+forgetting what they learned, they are working new ground almost every time and
+nothing tells them where they are. This is a surfacing problem, not a memory
+problem, so caching buys nothing and an opening statement buys everything.
+
+## When to Use
+
+- **First call of any session that will change something.** Before the first
+  read, not after the third `git status`.
+- When you are handed a slug and do not know its runtime, port, or host.
+- After a compaction, when position facts have aged out of context.
+- Before any deploy — `rdc:deploy` assumes you already know the target's shape.
+
+Not needed for a pure conversation turn.
+
+## What it answers
+
+| Question | Source | Never |
+|---|---|---|
+| which repo / worktree / branch am I in | `git rev-parse`, `git status` | assumed from a hardcoded path |
+| is my tree clean, am I behind | `git status -sb` | inferred from elapsed time |
+| what IS this slug | `get_deployment('<slug>')` | guessed from the directory name |
+| runtime, port, PM2 name, host | the registry | inferred from files on disk |
+| who depends on it | the registry | assumed to be nothing |
+
+**Two guesses this replaces, both measured wrong in practice:** filesystem
+inference said `node-build` where the registry says `ts-server`; and
+directory-name-as-slug fails outright — `packages/codeflow` is `codeflow-mcp`,
+`apps/admin` is `portal`.
+
+## Steps
+
+1. **Position.** `node scripts/orient.mjs` — repo, worktree, branch @ sha,
+   upstream, dirty count. Relative paths from here are correct by construction;
+   a hardcoded `C:/Dev/regen-root/...` from a lane points at a *different
+   checkout*.
+2. **Target.** `node scripts/orient.mjs <slug>` — resolves the slug through
+   `get_deployment`, printing runtime, port, host, deploy path and dependents.
+   `monorepo_path` NULL means a standalone repo, not in this tree.
+3. **Harness.** Name the shape the target's class implies:
+
+   | class | build | dev | prod |
+   |---|---|---|---|
+   | `apps/<name>` | `pnpm --filter @regen/<name> build` | PM2 @ Vultr | Coolify |
+   | `packages/<name>` | `pnpm --filter @regen/<name> build` | imported | `npm publish` |
+   | `sites/`, `models/` | static/vite | PM2 @ Vultr | Coolify |
+   | standalone | its own tooling | — | Coolify |
+
+4. **State the ground in one line** and start. Do not re-derive it later in the
+   turn.
+
+## Checklist
+
+```
+[ ] position resolved — repo, worktree, branch, dirty count
+[ ] target resolved from the registry (or: no slug given, position only)
+[ ] harness shape named for the target's class
+[ ] blockers noted — behind upstream, dirty tree, service down
+```
+
+## Related
+
+- `rdc:flow` — declares what KIND of work this is. `rdc:open` says where you are;
+  `rdc:flow` says what you are doing. Both, in that order.
+- `rdc:status` — open epics and queue. That is the work; this is the ground.
+- `$LIFEAI_ENV/docs/GATES-GUARDS-DENIES.md` — when a guard stops you, that names
+  the shape that works.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@lifeaitools/rdc-skills",
-  "version": "0.35.5",
+  "version": "0.35.6",
   "description": "RDC typed-agent dispatch skill suite for Claude Code - plan, build, review, overnight builds",
   "keywords": [
     "claude-code",

package/skills/collab/SKILL.md

@@ -230,7 +230,7 @@ most common failure and it fails at the guard layer, not the prompt layer.
 > version of this table said the opposite.** Managed identity is an 8-field record
 > (`lane, role, repoIdentity, ownerPid, ownerStartFingerprint, sessionId,
 > leaseEpoch, ownerToken`) built by `buildStartupIdentity()` in
-> [`pool/codex-topology.mjs`](file:///C:/Dev/lifeai-env/pool/codex-topology.mjs)
+> [`pool/codex-topology.mjs`](file:///C:/Dev/lifeai/node_modules/@lifeai/lifeai-env/pool/codex-topology.mjs)
 > and minted **only by the interactive launcher**, which also claims the lease.
 > `codex exec` has no lane-claim path, so it cannot produce that record — which
 > means **a headless Codex peer cannot write in any lane, including its own**.
@@ -245,7 +245,7 @@ most common failure and it fails at the guard layer, not the prompt layer.
 > fires when there is **no lease at all** (`ownerMatchesLease` returns false for a
 > null lease), so it will send you hunting a conflicting owner that does not exist.
 
-file:///C:/Dev/lifeai-env/pool/codex-topology.mjs
+file:///C:/Dev/lifeai/node_modules/@lifeai/lifeai-env/pool/codex-topology.mjs
 | **`local-llm`** | local endpoint per `.claude/context/clauth.md`; credential via `curl -s http://127.0.0.1:52437/v/<service>` | none (no repo attachment) | Small context windows: send the contract and the open points, never the whole document. Link paths instead of pasting files. |
 | **`claude-agent`** | `Agent` tool, or `claude -p --bare` / `claude --bg` | **`isolation: "worktree"` as an actual tool parameter** if it will commit — a prose claim of isolation is inert | Parallel agents on a shared checkout race on `git stash` and `.git/index`. See `.claude/rules/subagent-credentials.md`. |
 | **`claude-ai`** | chitchat MCP (`chitchat_send` / `chitchat_poll` / `chitchat_reply`) + SSE | session-scoped | Messages evaporate when the session stops — export durable decisions to TinTin. |

package/skills/env/SKILL.md

@@ -14,17 +14,39 @@ description: "Usage `rdc:env [status|install|repair|update]` — Manage the LIFE
 - 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
+- Routine update — bring the harness current and run a drift check
 - "check the environment", "fix my setup", "install environment"
 
+## The harness arrives by one of two channels — find out which BEFORE acting
+
+`$LIFEAI_ENV` is **not** necessarily a git repo, and on a normal box it is not.
+
+| channel | what `$LIFEAI_ENV` is | who owns freshness |
+|---|---|---|
+| **npm** (the normal box) | an installed package, e.g. `C:/Dev/lifeai/node_modules/@lifeai/lifeai-env` | `npm` — `env-boot` installs into the owning prefix at session start |
+| **git** (the publishing box) | a checkout of `LIFEAI/environment` | `land.mjs` → fetch → `env-install` |
+
+Every `git` command in this skill applies to the **git** channel only. Against an
+npm install they fail outright — `fatal: not a git repository` — because there is
+no `.git` there at all. Ask first:
+
+```bash
+node "$LIFEAI_ENV/machines/env-boot.mjs" check
+```
+
+It reports the installed version, the published version, and which channel this
+box is on, and changes nothing. Do not infer the channel from the path: the git
+tree at `C:/Dev/lifeai-env` still exists on the publishing box alongside the npm
+install, so a path that looks familiar proves nothing.
+
 ## 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 |
+| `status` (default) | Read-only check: channel + harness version, tool versions, MCP health, shim integrity, CodeFlow brain |
+| `install` | Full provision: install the harness 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 |
+| `update` | Bring the harness current for its channel, re-run audit, report drift, refresh shims if new scripts added |
 
 ## Procedure
 
@@ -35,21 +57,42 @@ LIFEAI_ENV="${LIFEAI_ENV:-C:/Dev/lifeai-env}"
 ```
 
 If `$LIFEAI_ENV` is not set AND the default path doesn't exist:
-- For `install`: clone the repo and set the env var
-- For all others: STOP with `BLOCKED: environment repo not found. Run: rdc:env install`
+- For `install`: install the harness (see the channel table above — npm on a
+  normal box) and set the env var. `provision.ps1` is self-locating
+  (`$EnvRoot = $PSScriptRoot`), so running it *from* an install is what points
+  `LIFEAI_ENV` at that install. Machine scope needs elevation; without it it
+  falls back to User scope and says so.
+- For all others: STOP with `BLOCKED: environment harness not found. Run: rdc:env install`
 
 Read `$LIFEAI_ENV/manifest.json` — this is the harness inventory.
 
-### Step 1: Environment repo state
+### Step 1: Harness state — channel first, then freshness
 
 ```bash
-git -C "$LIFEAI_ENV" fetch origin 2>/dev/null
-git -C "$LIFEAI_ENV" rev-list --count HEAD..origin/main
+node "$LIFEAI_ENV/machines/env-boot.mjs" check
 ```
 
-Report: version from manifest.json, commits behind origin, last pull date.
+One command, both channels, no mutation. It prints the installed version, the
+published version, and — on an npm hub outside `npm root -g` — the prefix an
+update would target.
+
+Report: version from manifest.json, the channel, and how far behind it is.
+
+**For `update` and `repair`, bring it current by its own channel:**
+
+```bash
+# npm channel — env-boot derives the owning prefix itself. Do NOT hand-roll a
+# prefix, and do NOT use a bare `npm install -g`: on a hub outside `npm root -g`
+# that silently updates a DIFFERENT directory and the hub never moves.
+node "$LIFEAI_ENV/machines/env-boot.mjs"
+
+# git channel (publishing box only)
+git -C "$LIFEAI_ENV" pull --ff-only origin main
+```
 
-For `update`: pull if behind. For `repair`: pull if behind (stale harness may be the cause).
+> **Never report a version comparison as a freshness verdict without saying which
+> channel produced it.** On a git hub `env-boot` deliberately does not ask npm at
+> all — the two versions differing there is expected, not a broken publish.
 
 ### Step 2: Tool versions (audit)
 
@@ -124,8 +167,8 @@ This is the same check the startup guard runs. Zero blockers = environment healt
 
 | Check | Status | Detail |
 |-------|--------|--------|
-| Env repo | ✅ | v0.2.0, 0 behind origin |
-| LIFEAI_ENV | ✅ | C:/Dev/lifeai-env (Machine scope) |
+| Harness | ✅ | v0.8.119, npm channel, current |
+| LIFEAI_ENV | ✅ | C:/Dev/lifeai/node_modules/@lifeai/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 |