openplanr 2.2641.0 → 2.2641.2

package/docs/CROSS_RUNTIME_SETUP.md

@@ -14,8 +14,8 @@ run guided setup:
 
 ```bash
 cd my-project
-planr setup
-planr doctor
+openplanr setup
+openplanr doctor
 ```
 
 Setup configures the OpenPlanr skills bundled with the installed CLI. Your coding
@@ -27,9 +27,9 @@ already provides planning utilities.
 ## Preview, apply, and migrate
 
 ```bash
-planr setup --dry-run
-planr setup
-planr doctor
+openplanr setup --dry-run
+openplanr setup
+openplanr doctor
 ```
 
 Guided setup detects Claude Code, Codex, and Cursor, explains unavailable shell
@@ -58,29 +58,29 @@ does this on its own. Restart Claude Code when setup says a plugin changed.
 
 | Channel | Purpose | Status |
 | --- | --- | --- |
-| `npm i -g openplanr`, then `planr setup` | Primary installation; the plugin is pinned to the CLI | Available |
+| `npm i -g openplanr`, then `openplanr setup` | Primary installation; the plugin is pinned to the CLI | Available |
 | `openplanr/marketplace` | Optional direct Claude Code installation | Available; can trail the npm release |
 | Anthropic marketplace listing | Vendor discovery and trust | Not yet listed |
 | OpenAI Plugins Directory | Vendor discovery for Codex and supported ChatGPT surfaces | Not yet listed |
 
 The release workflow projects each published `openplanr` Claude plugin into
 `openplanr/marketplace`; the source stays in this repository. Use one Claude Code
-channel per machine: either `planr setup` or
+channel per machine: either `openplanr setup` or
 `/plugin marketplace add openplanr/marketplace`, not both.
 
 For CI and provisioning, supply choices explicitly:
 
 ```bash
-planr setup --runtime auto --scope user --yes
-planr setup --runtime codex --scope project --yes
-planr setup --runtime all --scope both --yes
-planr runtime update claude --scope user --yes
+openplanr setup --runtime auto --scope user --yes
+openplanr setup --runtime codex --scope project --yes
+openplanr setup --runtime all --scope both --yes
+openplanr runtime update claude --scope user --yes
 ```
 
 Repeated setup is idempotent. To restore the last pre-setup state:
 
 ```bash
-planr runtime rollback
+openplanr runtime rollback
 ```
 
 Installing or updating one adapter is additive: it keeps every other managed
@@ -88,7 +88,7 @@ adapter and preserves each adapter's existing scope. For example, adding Codex
 at user scope does not widen an existing project-only Cursor installation.
 
 Setup installs the bundled OpenPlanr skills for the selected coding agents.
-`planr doctor` reports managed-file drift and runtime availability.
+`openplanr doctor` reports managed-file drift and runtime availability.
 
 ### Exact runtime packages and thin project entries
 
@@ -146,7 +146,7 @@ scopes adds project policy pointing to that discovery instead of duplicate skill
 An existing saved project-only choice remains recorded for later scope changes.
 Guided setup asks once to confirm the listed replacement and apply setup. For
 non-interactive use, review `--dry-run --verbose`, then add `--replace-managed`.
-Use `planr runtime rollback` to restore the previous file state.
+Use `openplanr runtime rollback` to restore the previous file state.
 
 ## Project stack overrides
 
@@ -169,20 +169,20 @@ reports a missing lens as a visible issue instead of blocking the rest of the re
 The validator is optional editing help for any generated note:
 
 ```bash
-planr operate validate-note <note.md> --profile advisor|challenger|chair|board-report --contract-version 2.0.0 --json
+openplanr operate validate-note <note.md> --profile advisor|challenger|chair|board-report --contract-version 2.0.0 --json
 ```
 
 Omit `--contract-version` to auto-detect current v2 and historical v1 notes.
 
 The durable Operate runtime is separate. Discover its exact registered domain
-identity with `planr operate domains --json`; neither setup nor the runtime
+identity with `openplanr operate domains --json`; neither setup nor the runtime
 guesses a domain version. Its issued executors receive a prepared packet and use
 only:
 
 ```bash
-planr operate assignment prepare <assignmentId> --actor <agentId> --runtime codex --json
-planr operate assignment validate <packetId> --content-file <resultPath|-> --json
-planr operate assignment submit <packetId> --content-file <resultPath|-> --json
+openplanr operate assignment prepare <assignmentId> --actor <agentId> --runtime codex --json
+openplanr operate assignment validate <packetId> --content-file <resultPath|-> --json
+openplanr operate assignment submit <packetId> --content-file <resultPath|-> --json
 ```
 
 The packet contains exact issued inputs, schema paths, evidence matrix, rubric,
@@ -198,24 +198,24 @@ other managed project installation depends on them.
 ## Troubleshooting and upgrades
 
 ```bash
-planr doctor --strict --json
-planr setup --dry-run
-planr upgrade status
-planr upgrade apply
+openplanr doctor --strict --json
+openplanr setup --dry-run
+openplanr upgrade status
+openplanr upgrade apply
 ```
 
-- Missing or stale skills: inspect doctor output, then re-run `planr setup`.
+- Missing or stale skills: inspect doctor output, then re-run `openplanr setup`.
   Known owned bytes are repaired transactionally; unknown or modified files are
   preserved and reported as `E_MIGRATION_CONFLICT`.
-- First Cycle rejects `--domain-version`: run `planr operate domains --json`
+- First Cycle rejects `--domain-version`: run `openplanr operate domains --json`
   and copy the exact domain identity. Operate Protocol `2.0.0` is not a domain
   version.
 - Assignment prepare/validate/submit fails: use the returned machine `code` and
   `problem`. The CLI intentionally omits host paths and stacks; author only the
   returned `resultPath` and keep `packetId` unchanged.
-- CLI/skill parity is incompatible: run `planr upgrade status`, then the
-  explicit `planr upgrade apply`, then the commands it lists for your coding
-  agents, and `planr doctor --strict --json` again.
+- CLI/skill parity is incompatible: run `openplanr upgrade status`, then the
+  explicit `openplanr upgrade apply`, then the commands it lists for your coding
+  agents, and `openplanr doctor --strict --json` again.
 
 ## Offline, remote, and SSH use
 
@@ -264,7 +264,7 @@ default-profile bundle stays in place. A repair in one profile
 cannot retire another profile's direct skills. Run the command with the same
 `CODEX_HOME` as the Codex session you want to configure.
 
-`planr doctor --json` includes `codexDiscovery`: the effective profile, configuration
+`openplanr doctor --json` includes `codexDiscovery`: the effective profile, configuration
 and ownership paths, saved discovery mode, and each installed OpenPlanr skill's
 entrypoint, complete source hash, skill version and Protocol version. Thin entries
 also pin the complete package inventory digest; shared support is verified against
@@ -274,19 +274,19 @@ reported without claiming which one an already-open Codex session loaded. Disabl
 or historical plugin cache copies are evidence of previous installations, not
 proof of enabled duplicate skills.
 
-Use `planr setup --runtime codex --dry-run` or `planr doctor --fix` to preview
+Use `openplanr setup --runtime codex --dry-run` or `openplanr doctor --fix` to preview
 installer-owned repairs in that profile. Review the changes and restart Codex to
 reload its skills. Do not manually delete native plugin caches. Unknown files and
 hand edits retain the existing ownership/conflict protections.
 
-`planr upgrade status` labels its release-metadata source. `stale-cache` means the
+`openplanr upgrade status` labels its release-metadata source. `stale-cache` means the
 registry request failed and a previous result was reused; compatibility with that
 cached set does not confirm the latest release. `cache` means recently cached
 metadata was used without a new registry request. Only `network` is a fresh check.
 
-`planr runtime update <agent>` refreshes only the named agent, retaining its saved
+`openplanr runtime update <agent>` refreshes only the named agent, retaining its saved
 scope and Codex discovery mode. An explicit `--scope` changes that agent's scope;
 the preview includes any retirement of unchanged managed project files and keeps
 their exact backup for rollback. Shared project lock records and other agents' owned
-files remain present. To deliberately change a Codex mode, use `planr setup` with
+files remain present. To deliberately change a Codex mode, use `openplanr setup` with
 `--skill-mode` and review its transition preview.

package/docs/TROUBLESHOOTING.md

@@ -5,8 +5,8 @@ Common issues and how to resolve them.
 Start with the unified health check:
 
 ```bash
-planr doctor --json
-planr setup --dry-run
+openplanr doctor --json
+openplanr setup --dry-run
 ```
 
 `doctor --fix` preserves each managed coding agent's saved installation scope and
@@ -38,13 +38,13 @@ actually selected it. A selected runtime that disappears remains a warning.
   project before selecting project scope. Use `--scope user` only for an integration
   that supports it; Cursor requires a valid project.
 - `E_RUNTIME_AMBIGUOUS`: pass `--runtime` or set a project default.
-- `E_LOCK_INCOMPATIBLE`: run the exact `planr runtime update ...` command shown.
+- `E_LOCK_INCOMPATIBLE`: run the exact `openplanr runtime update ...` command shown.
 - `E_MIGRATION_CONFLICT`: a managed file changed after setup; preview, preserve
-  the edit, or use `planr runtime rollback`.
+  the edit, or use `openplanr runtime rollback`.
 - `E_CLAUDE_PLUGIN_INSPECTION_FAILED`: update Claude Code so its plugin manager
-  is available, then rerun `planr setup --runtime claude --scope user`.
+  is available, then rerun `openplanr setup --runtime claude --scope user`.
 - `E_CLAUDE_PLUGIN_UPDATE_FAILED`: verify GitHub/marketplace connectivity, run
-  `planr runtime update claude --scope user`, and restart Claude Code.
+  `openplanr runtime update claude --scope user`, and restart Claude Code.
 - `E_PROVENANCE_WRITE`: repair permissions, then append an explicit recovery
   event; doctor never invents history silently.
 
@@ -52,7 +52,7 @@ If doctor reports `runtime-claude-plugins`, the installed plugin version or
 manifest identity does not match the compatible release. Run:
 
 ```bash
-planr runtime update claude --scope user
+openplanr runtime update claude --scope user
 ```
 
 Review and confirm the listed marketplace and plugin operations, then restart
@@ -66,8 +66,8 @@ state and paths live under `~/.planr/runtime/state.json`; the committed project
 lock contains only versions and compatibility capabilities.
 
 If an older installer created `~/CLAUDE.md`, `~/AGENTS.md`, Cursor rules, or a
-home-directory runtime lock, `planr doctor` reports `home-project-install`.
-Run `planr doctor --fix` to preview removal. Only recorded OpenPlanr-owned bytes
+home-directory runtime lock, `openplanr doctor` reports `home-project-install`.
+Run `openplanr doctor --fix` to preview removal. Only recorded OpenPlanr-owned bytes
 are removed; user-scope adapters and hand-written content are retained.
 
 ---
@@ -76,23 +76,23 @@ are removed; user-scope adapters and hand-written content are retained.
 
 ### A skill is not found in the host
 
-Confirm setup targeted that host and scope (`planr doctor --json` lists every
+Confirm setup targeted that host and scope (`openplanr doctor --json` lists every
 managed installation), then restart the host so it reloads its skills. Codex uses
-one install mode at a time; preview with `planr setup --runtime codex --dry-run`
+one install mode at a time; preview with `openplanr setup --runtime codex --dry-run`
 before switching modes.
 
 ### A skill asks for an API key or runs a planning command
 
 That is an old projection. Current skills reason inside the coding agent and call
-only deterministic `planr` utilities. Run `planr setup` again, restart the host, and
-check `planr upgrade status`.
+only deterministic `openplanr` utilities. Run `openplanr setup` again, restart the host, and
+check `openplanr upgrade status`.
 
 ### The agent does not pick the right skill
 
 Generate the host guidance so the agent sees every skill and its triggers:
 
 ```bash
-planr rules generate --target claude   # or codex, cursor, all
+openplanr rules generate --target claude   # or codex, cursor, all
 ```
 
 Then ask for `/planr:openplanr` (Claude Code) or `$planr:openplanr` (Codex), which
@@ -103,13 +103,13 @@ routes a request to the best skill.
 Initialize OpenPlanr in the project first:
 
 ```bash
-planr init
+openplanr init
 ```
 
 If you're running from a subdirectory, use `--project-dir`:
 
 ```bash
-planr status --project-dir /path/to/project
+openplanr status --project-dir /path/to/project
 ```
 
 ---
@@ -123,7 +123,7 @@ with `--minimal` omits it. Install the full package and verify again:
 
 ```bash
 npm install -g openplanr@latest
-planr doctor
+openplanr doctor
 ```
 
 ### `E_ARTIFACT_STALE_REVIEW`
@@ -134,7 +134,7 @@ silently. If the older feedback is still useful, rerun the import with
 
 ### A remote or SSH browser cannot reach the local review
 
-`planr artifact` intentionally binds to `127.0.0.1`. Use `--no-open --json`,
+`openplanr artifact` intentionally binds to `127.0.0.1`. Use `--no-open --json`,
 then forward the printed port over SSH. Do not bind the review server publicly.
 
 ### An artifact dependency is rejected
@@ -157,17 +157,17 @@ privacy and sharing model.
 If artifacts were renamed or moved manually, cross-references may break. Run:
 
 ```bash
-planr sync --dry-run    # preview what would change
-planr sync              # fix broken links
+openplanr sync --dry-run    # preview what would change
+openplanr sync              # fix broken links
 ```
 
 ### "Stale link" warnings
 
-A parent artifact links to a child that no longer exists on disk. `planr sync` removes these automatically.
+A parent artifact links to a child that no longer exists on disk. `openplanr sync` removes these automatically.
 
 ### "Missing link" warnings
 
-A child artifact references a parent, but the parent doesn't list the child. `planr sync` adds the missing link.
+A child artifact references a parent, but the parent doesn't list the child. `openplanr sync` adds the missing link.
 
 ---
 
@@ -191,7 +191,7 @@ The override directory must mirror the default template structure (e.g., `my-tem
 
 ### "GitHub CLI (gh) is not installed"
 
-The `planr github` commands require the GitHub CLI. Install it:
+The `openplanr github` commands require the GitHub CLI. Install it:
 
 ```bash
 # macOS
@@ -221,7 +221,7 @@ git remote add origin https://github.com/your-org/your-repo.git
 The linked GitHub issue was deleted. The CLI creates a new issue on the next push. If you see this error during sync, re-push the artifact:
 
 ```bash
-planr github push EPIC-001
+openplanr github push EPIC-001
 ```
 
 ### Push creates duplicate issues
@@ -244,7 +244,7 @@ issue through the [issue forms](https://github.com/openplanr/OpenPlanr/issues/ne
 with:
 
 - the command or skill invocation and the full output
-- `planr --version` and `planr doctor --json` (doctor redacts secrets; check anyway)
+- `openplanr --version` and `openplanr doctor --json` (doctor redacts secrets; check anyway)
 - the host and its version, your operating system, and `node --version`
 
 
@@ -255,10 +255,10 @@ selected `PLANR_HOME` (default `~/.planr`). Keep that cache available when worki
 offline, and regenerate local entries with setup when moving machines or changing
 homes. Native plugin packages and downloaded standalone skills remain complete.
 
-Run `planr doctor --json` to distinguish discovery metadata drift from a missing
-or changed package closure. `planr doctor --fix` uses the same preview, backup,
+Run `openplanr doctor --json` to distinguish discovery metadata drift from a missing
+or changed package closure. `openplanr doctor --fix` uses the same preview, backup,
 ownership checks and transaction as setup. It preserves the saved scope and
-Codex mode. `planr runtime update <agent>` updates only that agent.
+Codex mode. `openplanr runtime update <agent>` updates only that agent.
 
 A partially copied exact cache can resume from the installed CLI. Modified cache
 bytes, edited discovery entries and unknown files are preserved as conflicts;

package/install.ps1

@@ -21,8 +21,8 @@ $installArgs += "openplanr@$Version"
 & npm @installArgs
 if ($LASTEXITCODE -ne 0) { exit $LASTEXITCODE }
 
-$installedVersion = (& planr --version).Trim()
+$installedVersion = (& openplanr --version).Trim()
 Write-Host "`nOpenPlanr $installedVersion installed successfully.`n"
 Write-Host 'Next:'
 Write-Host '  cd C:\path\to\your\project'
-if ($Minimal) { Write-Host '  planr setup --minimal' } else { Write-Host '  planr setup' }
+if ($Minimal) { Write-Host '  openplanr setup --minimal' } else { Write-Host '  openplanr setup' }

package/install.sh

@@ -42,12 +42,12 @@ else
   npm install --global --no-audit --no-fund --loglevel=error "openplanr@$VERSION"
 fi
 
-INSTALLED_VERSION=$(planr --version)
+INSTALLED_VERSION=$(openplanr --version)
 printf '\n%s\n\n' "OpenPlanr $INSTALLED_VERSION installed successfully."
 printf '%s\n' 'Next:'
 printf '%s\n' '  cd /path/to/your/project'
 if [ "$MINIMAL" -eq 1 ]; then
-  printf '%s\n' '  planr setup --minimal'
+  printf '%s\n' '  openplanr setup --minimal'
 else
-  printf '%s\n' '  planr setup'
+  printf '%s\n' '  openplanr setup'
 fi

package/lib/host-packages/adapter-registry.json

@@ -2,12 +2,12 @@
   "kind": "host-native-adapter-registry",
   "schemaVersion": "1.0.0",
   "protocolVersion": "1.8.0",
-  "pipelineVersion": "0.55.11",
-  "pluginVersion": "2.2641.0",
+  "pipelineVersion": "0.57.0",
+  "pluginVersion": "2.2641.2",
   "adapters": [
     {
       "id": "claude-code",
-      "version": "2.2641.0",
+      "version": "2.2641.2",
       "capabilityLevel": "product",
       "installScopes": [
         "user",
@@ -19,7 +19,7 @@
     },
     {
       "id": "codex",
-      "version": "2.2641.0",
+      "version": "2.2641.2",
       "capabilityLevel": "product",
       "installScopes": [
         "user",
@@ -31,7 +31,7 @@
     },
     {
       "id": "cursor",
-      "version": "2.2641.0",
+      "version": "2.2641.2",
       "capabilityLevel": "workflow",
       "installScopes": [
         "project"

package/lib/host-packages/capability-map.json

@@ -1,7 +1,7 @@
 {
   "kind": "openplanr-capability-map",
   "schemaVersion": "1.0.0",
-  "pluginVersion": "2.2641.0",
+  "pluginVersion": "2.2641.2",
   "families": [
     {
       "id": "planning",
@@ -295,7 +295,7 @@
       "description": "Diagnose OpenPlanr CLI, pipeline, runtime-adapter, installation, and lock health. Use when setup, discovery, versions, generated assets, or runtime behavior seems wrong.",
       "useWhen": [
         "Diagnose OpenPlanr installation, runtime, adapter, version, or lock health",
-        "Check why planr setup or upgrade is unhealthy"
+        "Check why openplanr setup or upgrade is unhealthy"
       ],
       "notFor": [
         "Diagnose an application bug",
@@ -505,31 +505,31 @@
   "agents": [
     {
       "id": "planr-backend",
-      "description": "Use this agent when implementing a Tech task from the task file (Type=Tech — task-2.md, or sole task-1.md when no PNG). Services, controllers, DTOs, DB queries — backend only; never touches UI. For Step 0.2 entity scaffolding from schema.json use entity-scaffold-agent instead."
+      "description": "Implement the server side of a task or request — services, controllers, DTOs, entities, middleware, persistence, and their tests. Use for Tech tasks and other backend work; never for UI files."
     },
     {
       "id": "planr-database",
-      "description": "Use this agent when scanning a live database schema. READ-ONLY introspection that produces output/db/schema.json from PostgreSQL, MySQL, MSSQL, SQLite, or MongoDB."
+      "description": "Introspect a live database schema read-only and write the snapshot output/db/schema.json for PostgreSQL, MySQL, MSSQL, SQLite, or MongoDB. Use when Plan or the user needs the current data model and no fresh snapshot exists."
     },
     {
       "id": "planr-designer",
-      "description": "Use this agent when PNG mockups for a feature need to be analyzed into a structured design specification. Vision-based extraction of colors, typography, components, and layout into a 10-section design-spec.md."
+      "description": "Analyze UI mockup images for a feature into a structured ten-section design specification (colors, typography, spacing, components, layout). Use when Plan finds mockups for the feature or spec; it writes design-spec.md only, never code or stories."
     },
     {
       "id": "planr-devops",
-      "description": "Use this agent when generating infrastructure config (docker-compose.yml, Dockerfiles, .env.example, CI workflow stubs) from the projects stack. Generates files only — never deploys, never pushes images, never calls cloud APIs."
+      "description": "Generate infrastructure configuration (docker-compose.yml, Dockerfiles, .env.example, CI workflow stubs) that matches the project's stack. Writes files only — never deploys, pushes images, or calls cloud APIs."
     },
     {
       "id": "planr-documentation",
-      "description": "Use this agent when creating or updating human-readable product and engineering documentation from the request, repository, planning context, and implemented behavior. Cross-references intent and code, flags material drift, and never generates application code."
+      "description": "Create or update human-readable product and engineering documentation from the request, repository, planning context, and implemented behavior. Cross-references intent and code, flags material drift, and never generates application code."
     },
     {
       "id": "planr-entity-scaffold",
-      "description": "Step 0.2 only — generate ORM entity / DbContext (or equivalent) scaffolding from output/db/schema.json into output/src/. Not for `/ship` Tech tasks; use backend-agent for those."
+      "description": "Generate ORM entity or DbContext scaffolding (Prisma schema, TypeORM entities, EF Core DbContext, or the stack's equivalent) from a database schema snapshot. Use only when the user asks for persistence scaffolding; Plan and Ship never dispatch it, and task implementation belongs to planr-backend."
     },
     {
       "id": "planr-frontend",
-      "description": "Use this agent when implementing a UI task (Type=UI, task-1.md). Generates production-grade React/Next.js/Vue components, pages, and styles in src/features/{name}/. Frontend code only — never touches services, controllers, DTOs, or DB."
+      "description": "Implement the UI side of a task or request — components, pages, layouts, routes, styling, client-side state, form handling, and API wiring, with their tests. Use for UI tasks; never for services, controllers, DTOs, or database code."
     },
     {
       "id": "planr-qa",

package/lib/host-packages/claude/.claude-plugin/marketplace.json

@@ -5,14 +5,14 @@
     "name": "OpenPlanr"
   },
   "metadata": {
-    "version": "2.2641.0",
+    "version": "2.2641.2",
     "description": "Generated local OpenPlanr package."
   },
   "plugins": [
     {
       "name": "planr",
       "source": "./openplanr",
-      "version": "2.2641.0",
+      "version": "2.2641.2",
       "description": "Close the loop from intent to delivery. Plan, design, build, review, and operate from durable context in your repository.",
       "strict": true
     }

package/lib/host-packages/claude/openplanr/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "planr",
   "displayName": "OpenPlanr",
-  "version": "2.2641.0",
+  "version": "2.2641.2",
   "description": "Close the loop from intent to delivery. Plan, design, build, review, and operate from durable context in your repository.",
   "author": {
     "name": "OpenPlanr",