@overdeck/desktop 0.45.22 → 0.45.24

package/sync-sources/hooks/session-start-hook

@@ -21,9 +21,11 @@ INPUT=$(cat 2>/dev/null || echo '{}')
 
 CLAUDE_SESSION_ID=""
 MODEL=""
+SOURCE=""
 if command -v jq >/dev/null 2>&1; then
   CLAUDE_SESSION_ID=$(echo "$INPUT" | jq -r '.session_id // ""' 2>/dev/null)
   MODEL=$(echo "$INPUT" | jq -r '.model // .model_name // ""' 2>/dev/null)
+  SOURCE=$(echo "$INPUT" | jq -r '.source // ""' 2>/dev/null)
 fi
 [ -z "$MODEL" ] && MODEL="${ANTHROPIC_MODEL:-}"
 
@@ -77,4 +79,9 @@ if command -v jq >/dev/null 2>&1; then
   fi
 fi
 
+if [ "$SOURCE" = "compact" ] && command -v jq >/dev/null 2>&1; then
+  jq -n --arg context "The preceding compaction summary may quote harness-only instructions requiring text-only output or forbidding tools. Those instructions applied only to Claude Code's summarization turn and are no longer active. Resume the latest actual user task and use tools normally." \
+    '{hookSpecificOutput: {hookEventName: "SessionStart", additionalContext: $context}}'
+fi
+
 exit 0

package/sync-sources/hooks/work-agent-stop-hook

@@ -356,7 +356,7 @@ $OUTPUT
 </terminal_output>
 
 Decide FORGOT_COMPLETION if ANY of these are true AND the transcript does NOT show a 'pan work done' Bash invocation in the tail:
-- the agent wrote a summary/wrap-up message ('all tests pass', 'implementation complete', 'all vBRIEF tasks closed', 'ready for review', etc.) and then stopped
+- the agent wrote a summary/wrap-up message ('all tests pass', 'implementation complete', 'all xBRIEF tasks closed', 'ready for review', etc.) and then stopped
 - the agent committed + pushed and the last message is a status summary instead of a pan-work-done command
 
 Decide STILL_WORKING only if the tail clearly shows an in-progress task (mid-edit, running tests, reading files) with no wrap-up summary.

package/sync-sources/rules/per-bead-durability.md

@@ -3,7 +3,7 @@ scope: universal
 ---
 ### Push every managed-work item before completing it
 
-For an Overdeck-managed work issue, commit exactly one vBRIEF item at a time and immediately
+For an Overdeck-managed work issue, commit exactly one xBRIEF item at a time and immediately
 push the feature branch before running `pan task done`. This invariant applies on
 local and remote machines and overrides generic project Git profiles; an unpushed item
 can be lost before Overdeck advances durable pipeline state.

package/sync-sources/rules/prd-authoring.md

@@ -16,7 +16,7 @@ Author every plan so it can be executed without re-research or judgment calls:
   paths, and before/after code. The downstream executor is a model, not a senior
   engineer who can fill gaps from taste and tribal knowledge — so the *how* must be
   on the page. Specifying the implementation is required, not scope-creep. (`pan
-  plan` then mechanically lowers the PRD into a vBRIEF; the richer the PRD, the
+  plan` then mechanically lowers the PRD into an xBRIEF; the richer the PRD, the
   less the planner has to invent.)
 
 - **Glossary first.** Define every term of art the document uses before using it.

package/sync-sources/skills/feature-work/SKILL.md

@@ -9,7 +9,7 @@ When implementing a new feature:
 
 ## 1. Understand Requirements
 - Read the Linear/GitHub issue thoroughly
-- Check for an associated PRD draft at `<projectRoot>/.pan/drafts/<ISSUE-ID>.md` and the workspace vBRIEF at `.pan/spec.vbrief.json`
+- Check for an associated PRD draft at `<projectRoot>/.pan/drafts/<ISSUE-ID>.md` and the workspace xBRIEF at `.pan/spec.vbrief.json`
 - Identify acceptance criteria
 - Clarify ambiguities BEFORE coding
 

package/sync-sources/skills/okf/README.md

@@ -15,14 +15,21 @@ Embedding commands also need Ollama or an API key for the selected provider.
 
 Overdeck users receive this skill through `pan sync`.
 
-Standalone Claude Code users can copy-install it:
+Standalone Claude Code users install it from the mirror repo, [eltmon/okf](https://github.com/eltmon/okf) — symlink so `git pull` updates it in place:
 
 ```bash
+git clone https://github.com/eltmon/okf.git ~/Projects/okf
 mkdir -p ~/.claude/skills
-cp -R sync-sources/skills/okf ~/.claude/skills/okf
+ln -s ~/Projects/okf ~/.claude/skills/okf
 ```
 
-The copied skill remains portable. Its core scripts do not import Overdeck and require only git, gh, Python 3, and PyYAML for non-embedding workflows.
+Or copy-install instead of symlinking:
+
+```bash
+cp -R ~/Projects/okf ~/.claude/skills/okf
+```
+
+The skill remains portable. Its core scripts do not import Overdeck and require only git, gh, Python 3, and PyYAML for non-embedding workflows.
 
 ## 5-Minute Quickstart
 
@@ -61,6 +68,7 @@ The copied skill remains portable. Its core scripts do not import Overdeck and r
 | Command | Summary |
 | --- | --- |
 | `/okf init` | Create or connect the knowledge bundle and pointer file. |
+| `/okf open [--no-install] [--no-browser]` | Open the configured bundle in the local visual knowledge viewer. |
 | `/okf author "<topic>"` | Write or update one concept for one idea. |
 | `/okf convert <path>` | Convert existing docs into OKF without destructive edits. |
 | `/okf sync [--topic "<focus>"]` | Update concepts from code or documentation diffs. |

package/sync-sources/skills/okf/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: okf
-description: Maintain a project knowledge wiki in Open Knowledge Format with /okf init, author, convert, sync, study, retro, extract, validate, lint, and embed.
+description: Maintain a project knowledge wiki in Open Knowledge Format with /okf init, open, author, convert, sync, study, retro, extract, validate, lint, and embed.
 triggers:
   - /okf
   - okf
@@ -26,6 +26,7 @@ The bundle is the source of truth. Keep changes small, cited, and PR-gated. Dete
 | Command | Purpose | Primary references |
 | --- | --- | --- |
 | `/okf init` | Create or connect a project knowledge bundle. | `references/workflow.md`, `references/spec.md` |
+| `/okf open [--no-install] [--no-browser]` | Open the configured bundle in the local visual knowledge viewer. | `references/overdeck.md` |
 | `/okf author "<topic>"` | Write or refresh one focused concept. | `templates/concept.md`, `references/taxonomy.md`, `references/model-bridges.md` |
 | `/okf convert <path>` | Convert existing docs into OKF concepts without deleting originals. | `references/conversion.md` |
 | `/okf sync [--topic "<focus>"]` | Update concepts from code or documentation changes. | `references/workflow.md`, `references/model-bridges.md` |
@@ -80,6 +81,16 @@ Create a knowledge bundle and pointer file.
 - Add exactly one discovery line to `CLAUDE.md` or `AGENTS.md`, preserving it without duplication on repeated init.
 - Future resolution order is host project config `knowledge_repo`, then `.okf.yml`, then a clear error telling the user to run `/okf init`.
 
+## `/okf open [--no-install] [--no-browser]`
+
+Open the configured bundle in the local visual knowledge viewer.
+
+- Resolve the bundle from `.okf.yml`; under Overdeck, the canonical resolver also honors the project's `knowledge_repo` setting.
+- When `pan` is available, delegate to `pan knowledge open` and pass through `--no-install` and `--no-browser`.
+- By default, an explicit open request progressively installs the separately licensed GPL-3.0 `@inkeep/open-knowledge` program. `--no-install` requires an existing `ok` binary instead.
+- The viewer is an arm's-length subprocess served over HTTP. Overdeck launches it against a disposable snapshot, reuses healthy lock-reported processes, and never lets viewer edits touch the canonical PR-gated bundle.
+- Never import, require, or bundle `@inkeep/open-knowledge` into the portable OKF scripts or Overdeck packages.
+
 ## `/okf author "<topic>"`
 
 Write or update one concept for one idea.

package/sync-sources/skills/okf/docs/USAGE.md

@@ -16,6 +16,21 @@ Create a knowledge bundle.
 - `--dir <path>`: use any external directory.
 - `--local <subdir>`: create an in-repo bundle.
 
+## `/okf open [--no-install] [--no-browser]`
+
+Open the configured bundle in the local visual viewer.
+
+```bash
+/okf open
+/okf open --no-install
+/okf open --no-browser
+```
+
+- Resolves the bundle from `.okf.yml` (or Overdeck's `knowledge_repo` setting).
+- Delegates to `pan knowledge open` when Overdeck is available.
+- Progressively installs the separate GPL-3.0 `ok` program only after the explicit open request; `--no-install` opts out.
+- `--no-browser` starts or reuses the viewer and prints its URL without launching a browser.
+
 ## `/okf author "<topic>"`
 
 Write or update one concept.

package/sync-sources/skills/okf/references/overdeck.md

@@ -11,6 +11,34 @@ Overdeck is available only when:
 
 Detection is by command execution, never by Python or TypeScript imports.
 
+## OpenKnowledge Viewer Runtime
+
+`pan knowledge open` and the dashboard Knowledge page use an assisted Node.js 24 resolution flow for the OpenKnowledge viewer. Overdeck first reuses a working `ok`, then checks `OVERDECK_OPEN_KNOWLEDGE_NODE`, then searches installed runtimes under nvm, fnm, Volta, mise, and asdf. If a download is required, the operator sees the exact setup steps and must consent before they run; shell profiles and the ambient/default Node.js version remain unchanged. A fresh nvm bootstrap suppresses profile edits and restores or removes the `default` alias to match its pre-setup state.
+
+Set `OVERDECK_OPEN_KNOWLEDGE_NODE=/absolute/path/to/node` to pin the viewer to a specific Node.js 24+ binary. Overdeck rejects relative overrides and resolves the absolute path before writing the shim, so the override affects only the separate `ok` subprocess and cannot drift with `PATH`.
+
+## Optional OpenKnowledge MCP Registration
+
+The dashboard viewer and `pan knowledge open` never register an MCP server. Their unattended initialization always uses `ok init --no-mcp --no-skills`, so opening the viewer cannot change an editor or agent configuration.
+
+MCP registration is a separate, explicit operator action. From the resolved knowledge-bundle root, run:
+
+```bash
+ok init --mcp --no-skills --scope user
+```
+
+Use `--scope project` for repository-local configuration, or `--scope both` for both locations. OpenKnowledge v0.34 writes the supported native formats:
+
+| Client | User scope | Project scope |
+| --- | --- | --- |
+| Claude Code | `~/.claude.json` | `.mcp.json` |
+| Codex | `~/.codex/config.toml` | `.codex/config.toml` |
+| Cursor | `~/.cursor/mcp.json` | `.cursor/mcp.json` |
+
+OpenKnowledge registers only clients it detects. Start or install the intended client, then rerun the explicit command if its config root was previously absent. Review the reported paths before restarting the client; registration is opt-in and Overdeck never performs it automatically.
+
+`/okf init` and `ok init` are different commands: `/okf init` creates or connects an OKF knowledge bundle, while the upstream `ok init` command scaffolds OpenKnowledge's local `.ok/` runtime files and optionally registers MCP clients.
+
 ## Retro Feedstock
 
 When Overdeck is detected, `/okf retro` may mine observations for the issue:

package/sync-sources/skills/pan/SKILL.md

@@ -38,7 +38,8 @@ LIFECYCLE VERBS (top-level)
   pan wipe <id>            Destructive reset-to-Todo for an issue
   pan close <id>           Close-out ceremony for completed issues
   pan plan <id>            Create execution plan
-  pan plan finalize <id>   Materialize plan to vBRIEF tasks
+  pan plan finalize <id>   Finalize the xBRIEF plan
+  pan task <subcommand>    Read and update xBRIEF item state
   pan issues               List and triage work across trackers
 
 OBSERVATION
@@ -70,7 +71,6 @@ ADMIN (PLUMBING)
   pan admin specialists <cmd> Review/test/merge agents
   pan admin remote <cmd>      Fly.io infra
   pan admin db <cmd>          Database seeding
-  pan admin vBRIEF tasks <cmd>       vBRIEF tasks CLI management
   pan admin config <cmd>      Configuration management
   pan admin hooks install     Install Claude Code heartbeat hooks
   pan admin tldr <cmd>        TLDR daemon management

package/sync-sources/skills/pan-admin-config/SKILL.md

@@ -45,5 +45,6 @@ Settings page or edit `~/.overdeck/config.yaml` directly.
 ## See Also
 
 - `pan admin migrate-config` — migrate legacy settings.json → config.yaml
+- `pan admin state migrate-xbrief <project> [--dry-run]` — migrate state files to xBRIEF envelopes and extensions
 - `pan admin tracker <cmd>` — tracker-specific operations
 - `pan doctor` — verify configuration is valid

package/sync-sources/skills/pan-approve/SKILL.md

@@ -17,7 +17,7 @@ allowed-tools:
 
 `pan approve` was a legacy CLI command that bypassed critical infrastructure:
 - **Merge queue** — no serialization, could collide with concurrent merges
-- **Post-merge lifecycle** — no Docker cleanup, label cleanup, stash cleanup, vBRIEF tasks compaction
+- **Post-merge lifecycle** — no Docker cleanup, label cleanup, stash cleanup, xBRIEF task-state compaction
 - **Idempotency guards** — no protection against the infinite loop (PAN-328)
 - **Verification gate** — no post-rebase quality checks
 

package/sync-sources/skills/pan-close/SKILL.md

@@ -57,7 +57,7 @@ pan close PAN-1234 --force --accept-deploy
 Runs the close-out ceremony after mechanically checking review, tests, branch verification,
 forge merge, post-merge lifecycle, main verification, deployment, and teardown. Merge
 moves the issue to canonical state `verifying_on_main`; close-out is the deliberate final
-step that completes the vBRIEF, archives planning artifacts, applies final cleanup, closes
+step that completes the xBRIEF, archives planning artifacts, applies final cleanup, closes
 the tracker issue, and clears review status.
 
 Close-out is lighter than `pan wipe`: it preserves history and follows the configured

package/sync-sources/skills/pan-doctor/SKILL.md

@@ -47,7 +47,7 @@ pan doctor
 # ✓ Skills directory exists
 # ✓ tmux available
 # ✓ Docker available
-# ⚠ orphan-proposed-specs: proposed vBRIEF specs without work agents, grouped by project with remediation hints
+# ⚠ orphan-proposed-specs: proposed xBRIEF specs without work agents, grouped by project with remediation hints
 ```
 
 ### 2. Check Configuration

package/sync-sources/skills/pan-flywheel/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: pan-flywheel
-description: "pan flywheel — start, pause, resume, stop, inspect, emit, and report on the singleton Fix-All Flywheel orchestrator"
+description: "pan flywheel — start, pause, resume, complete, stop, inspect, emit, and report on the singleton Fix-All Flywheel orchestrator"
 triggers:
   - pan flywheel
   - flywheel orchestrator
@@ -24,6 +24,7 @@ The Flywheel is not an issue-scoped work agent. It runs as `flywheel-orchestrato
 ```bash
 pan flywheel start
 pan flywheel start --brief docs/flywheel-brief.md
+pan flywheel start --orders <book-id>
 pan flywheel config --get
 pan flywheel config --get flywheel.require_uat_before_merge
 pan flywheel config --set flywheel.auto_pickup_backlog=true
@@ -32,6 +33,8 @@ pan flywheel status
 pan flywheel status --json
 pan flywheel pause
 pan flywheel resume
+pan flywheel complete
+pan flywheel complete --force
 pan flywheel stop
 pan flywheel abort
 pan flywheel emit-status --file latest.json
@@ -45,12 +48,15 @@ pan flywheel report
 ```bash
 pan flywheel start
 pan flywheel start --brief docs/flywheel-brief.md
+pan flywheel start --orders <book-id>
 ```
 
 Starts `flywheel-orchestrator` and opens a new run under `~/.overdeck/flywheel/runs/<runId>/`.
 
 Use the default brief unless the user gives a specific markdown brief. The default is `docs/flywheel-brief.md`. The command validates that the brief path stays inside the project root.
 
+`--orders <book-id>` validates a ready order book, stamps the book binding into the run launch metadata, and marks the book running only after the Flywheel start gate succeeds. Validation or gate failures leave the book ready.
+
 ### Config
 
 ```bash
@@ -84,6 +90,17 @@ pan flywheel resume
 
 If the Flywheel is already paused or already running, these commands report the current gate state and exit successfully.
 
+### Complete
+
+```bash
+pan flywheel complete
+pan flywheel complete --force
+```
+
+Completes an orders-bound run after every book item is closed or parked. The command refuses a non-drained book and names each remaining issue unless `--force` is passed. It writes `report.md`, adds `## Retrospective` from the run's `retro.md` when present or the exact no-findings line otherwise, commits any `docs/FLYWHEEL-STATE.md` change, clears the active-run gate, and marks the book complete.
+
+Continuation is mechanical: the next ready book in queue order starts in-process; when no book is ready and `flywheel.auto_pickup_backlog=true`, a bookless backlog run starts; otherwise the command stays stopped and emits `needs-you: pipeline idle — no order book queued and auto-pickup is off`.
+
 ### Stop
 
 ```bash

package/sync-sources/skills/pan-knowledge/SKILL.md

@@ -9,6 +9,7 @@ triggers:
   - knowledge sync
   - knowledge study
   - knowledge retro
+  - knowledge open
 allowed-tools:
   - Bash
   - Read
@@ -30,6 +31,8 @@ pan knowledge PAN-123 --focus "auth flow"    # Study a topic, then sync
 pan knowledge PAN-123 --retro                # Capture retro knowledge, then sync
 pan knowledge PAN-123 --model claude-sonnet-5  # Override the knowledge role model
 pan knowledge PAN-123 --effort high          # Raise reasoning effort for the agent
+pan knowledge open                           # Open this project's OKF bundle in the viewer
+pan knowledge open --no-install --no-browser # Never install or launch a browser
 ```
 
 ## What It Does
@@ -51,6 +54,13 @@ The command first tries to ensure `mnemos` is available on `PATH` (installing it
 on demand if necessary) and ingest the resolved bundle. If mnemos is unavailable,
 it resolves the installed `okf` skill and falls back to its bundled `scripts/` directory.
 
+`pan knowledge open` resolves the current project's bundle through
+`projects.yaml` or `.okf.yml`, progressively installs the separately licensed
+`@inkeep/open-knowledge` program when needed, starts or reuses a verified viewer
+against a disposable snapshot, and opens the URL. Viewer edits never touch the
+canonical PR-gated bundle. Use `--no-install` to require a preinstalled `ok` binary and
+`--no-browser` to print the URL without launching a browser.
+
 ## When to Use
 
 - After merging a feature to capture knowledge that would have helped the work

package/sync-sources/skills/pan-new-project/SKILL.md

@@ -3,7 +3,7 @@ name: pan-new-project
 description: >
   Complete setup for registering a new project with Overdeck. Handles
   project registration, issue prefix, workspace config, trust setup,
-  vBRIEF tasks init, tracker config, and validates against working projects.
+  xBRIEF task support init, tracker config, and validates against working projects.
 triggers:
   - new project
   - add new project
@@ -31,7 +31,7 @@ license: "MIT"
 Sets up a new project for Overdeck management. This is the ONLY correct
 way to add a new project. Do NOT just run `pan project add` alone — it
 creates a skeleton entry that breaks planning agents, workspace creation,
-issue routing, and vBRIEF tasks.
+issue routing, and xBRIEF task support.
 
 ---
 
@@ -185,16 +185,14 @@ extra config needed beyond `issue_prefix` in projects.yaml.
 
 For **GitLab** projects, TBD — not yet supported in dashboard polling.
 
-### Step 5: Initialize vBRIEF tasks
+### Step 5: Verify xBRIEF Task Support
+
+No per-project task database initialization is required. xBRIEF plan items become the executable checklist after planning, and `pan task` reads and updates their state through the canonical state door.
 
 ```bash
-cd <project-path>
-git config vBRIEF tasks.role agent
+pan task --help >/dev/null && echo "PASS: pan task available"
 ```
 
-New worktrees inherit this automatically since Overdeck now sets it during
-workspace creation (`workspace-manager.ts` and `worktree.ts`).
-
 ### Step 6: Create workspaces/ Directory
 
 ```bash
@@ -250,8 +248,8 @@ console.log(d.projects?.['<path>']?.hasTrustDialogAccepted
 grep 'GITHUB_REPOS' ~/.overdeck.env | grep -q '<PREFIX>' && \
   echo "PASS: in GITHUB_REPOS" || echo "FAIL: not in GITHUB_REPOS"
 
-# 5. vBRIEF tasks configured
-cd <path> && git config vBRIEF tasks.role && echo "PASS" || echo "FAIL: vBRIEF tasks.role not set"
+# 5. xBRIEF task command available
+pan task --help >/dev/null && echo "PASS" || echo "FAIL: pan task unavailable"
 
 # 6. workspaces/ exists
 test -d <path>/workspaces && echo "PASS" || echo "FAIL: no workspaces/"
@@ -278,7 +276,7 @@ Tracker:        GitHub (<owner/repo>)
 Workspace type: <type>
 Tests:          <command>
 Trusted:        Yes
-vBRIEF tasks:          Configured
+xBRIEF task support:   Available through pan task
 Dashboard:      Issues visible
 
 Validation: 8/8 checks passed

package/sync-sources/skills/pan-orders/SKILL.md

@@ -0,0 +1,33 @@
+---
+name: pan-orders
+description: "pan orders — create, inspect, edit, and start Flywheel order books"
+triggers:
+  - pan orders
+  - order book
+  - special orders
+allowed-tools:
+  - Bash
+  - Read
+---
+
+# pan orders
+
+Use `pan orders` to manage the operator-owned order book that scopes a Flywheel campaign.
+
+```bash
+pan orders create "Campaign name"
+pan orders list
+pan orders show <id>
+pan orders add <id> <issue...>
+pan orders add <id> <issue...> --lane B --after <issue> --reverify
+pan orders remove <id> <issue>
+pan orders move <id> <issue> --lane A --order 2
+pan orders start <id>
+```
+
+- `create` makes a draft book with a date-and-name id.
+- `add` defaults to Lane A. `--after` must name an item already in the target lane. `--reverify` requires PRD re-verification before pickup.
+- `move` accepts `--lane <A|B>`, `--order <n>`, or both.
+- `start` validates and starts the same orders-bound path as Flywheel start; validation blocks leave the book unchanged.
+
+Order-book reads and mutations go through the canonical resolver and writer. Do not edit `orders/*.json` directly.

package/sync-sources/skills/pan-oversee/SKILL.md

@@ -27,7 +27,7 @@ Supervise an agent working on an issue through the **entire lifecycle**:
 `spawn/resume → work → completion → review → feedback loop → test → merge-ready`
 
 This is NOT passive monitoring. You are actively:
-- **Watching for bugs at every stage** — dashboard rendering, agent spawning, workspace creation, vBRIEF tasks lifecycle, specialist handoffs, status transitions, terminal output, API responses
+- **Watching for bugs at every stage** — dashboard rendering, agent spawning, workspace creation, xBRIEF tasks lifecycle, specialist handoffs, status transitions, terminal output, API responses
 - **Documenting everything** — no bug is too small. If something flickers, logs a warning, shows stale data, or doesn't match expected state, that's a finding
 - **Fixing infrastructure bugs** when they block progress, then continuing the test
 - **Filing or updating GitHub issues** (PAN-XXX) for every bug found
@@ -92,12 +92,12 @@ echo "Completed: ${COMPLETED:-NO}"
 REVIEW_STATUS=$(curl -s http://localhost:3011/api/review/$ISSUE_ID/status 2>/dev/null)
 echo "Review status: $REVIEW_STATUS"
 
-# 6b. Branch-portable vBRIEF pipeline mirror (corroborating, not authoritative)
+# 6b. Branch-portable xBRIEF pipeline mirror (corroborating, not authoritative)
 PIPELINE_MIRROR=""
 if [ -n "$WS_PATH" ] && [ -f "$WS_PATH/.pan/spec.vbrief.json" ]; then
   PIPELINE_MIRROR=$(jq -c '.plan.metadata.pipeline // empty' "$WS_PATH/.pan/spec.vbrief.json" 2>/dev/null)
 fi
-echo "vBRIEF pipeline mirror: ${PIPELINE_MIRROR:-NONE}"
+echo "xBRIEF pipeline mirror: ${PIPELINE_MIRROR:-NONE}"
 
 # 7. Specialist activity?
 SPECIALISTS=$(curl -s http://localhost:3011/api/specialists 2>/dev/null)
@@ -106,7 +106,7 @@ echo "Specialists: $SPECIALISTS"
 
 ### Phase Decision Matrix
 
-Based on the checks above, determine the current phase. Treat `REVIEW_STATUS` and other live SQLite-backed API status as authoritative; use the branch-portable vBRIEF `plan.metadata.pipeline` mirror as a corroborating signal when API status is missing, stale, or ambiguous. If the mirror disagrees with the API, log a bug and prefer the API.
+Based on the checks above, determine the current phase. Treat `REVIEW_STATUS` and other live SQLite-backed API status as authoritative; use the branch-portable xBRIEF `plan.metadata.pipeline` mirror as a corroborating signal when API status is missing, stale, or ambiguous. If the mirror disagrees with the API, log a bug and prefer the API.
 
 | Condition | Current Phase | Jump To |
 |-----------|--------------|---------|
@@ -344,7 +344,7 @@ When you find a bug in the Overdeck infrastructure:
 Be thorough. All of these are findings worth logging:
 - Dashboard shows wrong status, stale data, or flickers
 - Agent state file says one thing, dashboard shows another
-- vBRIEF tasks not created, duplicated, or disappearing
+- xBRIEF tasks not created, duplicated, or disappearing
 - Specialist doesn't wake up or takes too long
 - Terminal output garbled or missing
 - API returns unexpected response

package/sync-sources/skills/pan-plan/SKILL.md

@@ -18,7 +18,7 @@ allowed-tools:
 
 # Overdeck Planning Lifecycle
 
-`pan plan <id>` is the plan-ONLY verb: it starts a planning session for an issue and produces a PRD and vBRIEF, but it does not start the work agent. Use `pan start <id>` when you want planning and work in one command.
+`pan plan <id>` is the plan-ONLY verb: it starts a planning session for an issue and produces a PRD and xBRIEF, but it does not start the work agent. Use `pan start <id>` when you want planning and work in one command.
 
 Use `--auto` when the user wants the planning agent to run non-interactively and infer defensible defaults. Use `--probe` when the plan needs an adversarial pre-finalize self-pass; `--effort high` enables the same probe instructions automatically.
 
@@ -85,13 +85,13 @@ What it does:
 2. Validates the tasks already stored in `plan.items[]`, including their declared dependencies.
 3. Flips the spec's `plan.status` from `draft` to `proposed`.
 4. Calls the dashboard's complete-planning endpoint to promote the canonical spec into `<projectRoot>/.pan/specs/`, commit it on main, push, transition the tracker state to Planned, and terminate the planning session — same flow as `pan plan done` and the dashboard Done button.
-5. Returns a summary of finalized vBRIEF tasks and promotion status, or JSON with `--json`.
+5. Returns a summary of finalized xBRIEF tasks and promotion status, or JSON with `--json`.
 
-Use `-w <path>` to point at another workspace. Use `--no-promote` to leave the spec at `status=proposed` without promoting (rare; for humans who want to review the plan in the dashboard before clicking Done). Finalize runs vBRIEF quality lint by default; use `--no-quality-lint` only as a loud one-run emergency bypass when the plan must be promoted despite known quality issues.
+Use `-w <path>` to point at another workspace. Use `--no-promote` to leave the spec at `status=proposed` without promoting (rare; for humans who want to review the plan in the dashboard before clicking Done). Finalize runs xBRIEF quality lint by default; use `--no-quality-lint` only as a loud one-run emergency bypass when the plan must be promoted despite known quality issues.
 
 ### PRD-first gate
 
-Finalize and complete-planning refuse to promote a plan unless a **PRD draft** of at least 20 lines exists for the issue. `roles/plan.md` has always required the PRD as the first artifact; this gate makes it mechanical. The gate searches, in order, for `<ISSUE-ID>.md` (uppercase then lowercase) under `<projectRoot>/.pan/drafts/` then `<workspace>/.pan/drafts/`; the first existing file with ≥20 lines satisfies it. A found-but-thinner draft fails with its line count; a fully missing draft fails naming the canonical path to write. `pan start <id> --auto` is structurally exempt (it synthesizes a minimal vBRIEF and never POSTs complete-planning, so the gate cannot block it). Use `--no-prd` (on `finalize` or `done`) only for a genuinely trivial issue that went through interactive planning anyway — it prints a yellow `⚠ PRD gate SKIPPED` warning and tells the endpoint to skip the check too.
+Finalize and complete-planning refuse to promote a plan unless a **PRD draft** of at least 20 lines exists for the issue. `roles/plan.md` has always required the PRD as the first artifact; this gate makes it mechanical. The gate searches, in order, for `<ISSUE-ID>.md` (uppercase then lowercase) under `<projectRoot>/.pan/drafts/` then `<workspace>/.pan/drafts/`; the first existing file with ≥20 lines satisfies it. A found-but-thinner draft fails with its line count; a fully missing draft fails naming the canonical path to write. `pan start <id> --auto` is structurally exempt (it synthesizes a minimal xBRIEF and never POSTs complete-planning, so the gate cannot block it). Use `--no-prd` (on `finalize` or `done`) only for a genuinely trivial issue that went through interactive planning anyway — it prints a yellow `⚠ PRD gate SKIPPED` warning and tells the endpoint to skip the check too.
 
 ## Completing planning (`pan plan done`)
 
@@ -101,7 +101,7 @@ Finalize and complete-planning refuse to promote a plan unless a **PRD draft** o
 pan plan done PAN-1071
 ```
 
-This promotes the workspace vBRIEF to `<projectRoot>/.pan/specs/`, syncs vBRIEF tasks, and transitions the tracker state to Planned. It is subject to the same PRD-first gate as `finalize`; pass `--no-prd` only for a genuinely trivial issue.
+This promotes the workspace xBRIEF to `<projectRoot>/.pan/specs/`, syncs xBRIEF tasks, and transitions the tracker state to Planned. It is subject to the same PRD-first gate as `finalize`; pass `--no-prd` only for a genuinely trivial issue.
 
 ## Related commands
 
@@ -112,5 +112,5 @@ This promotes the workspace vBRIEF to `<projectRoot>/.pan/specs/`, syncs vBRIEF
 ## See also
 
 - `roles/plan.md` — planning role prompt.
-- `docs/VBRIEF.md` — vBRIEF schema, artifact locations, lifecycle states.
+- `docs/XBRIEF.md` — xBRIEF schema, artifact locations, lifecycle states.
 - `docs/SKILLS-CONVENTION.md` — skill/CLI naming convention.

package/sync-sources/skills/pan-quickstart/SKILL.md

@@ -374,7 +374,7 @@ After completing this quick start, you have:
 
 ### Productivity Tips
 - Use dashboard to monitor multiple agents
-- Set up vBRIEF tasks for task tracking
+- Use xBRIEF plan items through `pan task` for task tracking
 - Configure git hooks for automated workflows
 - Create custom skills for your team's processes
 

package/sync-sources/skills/pan-recap/SKILL.md

@@ -130,14 +130,14 @@ gh issue list --state closed --search "closed:>=$SINCE_DATE" --limit 50 \
 ```
 
 Also scan real commits on `main` (drop the bookkeeping noise — `chore(records)`,
-`chore(state)`, `chore(vBRIEF tasks)` are per-issue state syncs, not work):
+`chore(state)` and `chore(records)` are per-issue state syncs, not work):
 
 ```bash
 echo "=== substantive commits on origin/main ==="
 git fetch -q origin main 2>/dev/null
 git log origin/main --since="$HOURS hours ago" --no-merges \
   --pretty='%h %ad %s' --date=format:'%m-%d %H:%M' \
-  | grep -vE 'chore\((records|state|vBRIEF tasks)\)' | head -40
+  | grep -vE 'chore\((records|state)\)' | head -40
 ```
 
 ### 2. What's in flight — active agents and in-review work

package/sync-sources/skills/pan-review/SKILL.md

@@ -90,7 +90,7 @@ all reviewers + the test specialist sign off; humans only click the button.
 
 ## See also
 
-- `pan show <id>` — inspect work agent state, vBRIEF status, recent activity
+- `pan show <id>` — inspect work agent state, xBRIEF status, recent activity
 - `pan done <id>` — signal initial work completion (from the worker side)
 - `pan code-review` skill — orchestrated parallel code review with synthesis
 - `roles/review.md` — the review role's frontmatter and prompt

package/sync-sources/skills/pan-start/SKILL.md

@@ -31,6 +31,7 @@ pan start PAN-123 --fresh  # Drop the saved session and start a new one (e.g. sw
 pan start PAN-123 --harness codex  # Explicitly use the Codex harness
 pan start PAN-123 --model gpt-5.6-sol --swarm off --review-mode full
 pan start PAN-123 --review-model gpt-5.6-sol  # Pin the convoy review model
+pan start PAN-123 --plan-model k3 --model k3  # Auto-plan AND work on Kimi k3
 pan start PAN-123 --remote --tier durable  # Remote Fly.io workspace with persistent volume
 pan start PAN-123 --remote --tier ephemeral  # Remote Fly.io workspace that winds down on stale heartbeat
 ```
@@ -40,10 +41,10 @@ pan start PAN-123 --remote --tier ephemeral  # Remote Fly.io workspace that wind
 `pan start <id>` is the single paved-road entry point: it takes an issue from whatever
 state it is in to running work.
 
-- **No plan exists** — `pan start` auto-plans (non-interactive), materializes vBRIEF tasks, and
+- **No plan exists** — `pan start` auto-plans (non-interactive), materializes xBRIEF tasks, and
   starts the work agent when planning finalizes.
 - **Plan exists** — `pan start` creates the workspace if needed and spawns the work agent
-  from the existing vBRIEF and vBRIEF tasks.
+  from the existing xBRIEF and xBRIEF tasks.
 - **Already running** — `pan start` exits 0 with a no-op message naming `pan tell <id>` for
   messaging and the tmux attach command.
 
@@ -52,7 +53,7 @@ Planning depth is controlled by `--plan`:
 ```bash
 pan start PAN-1071 --plan interactive   # Q&A planning first, then work
 pan start PAN-1071 --plan auto          # non-interactive planning, then work (default)
-pan start PAN-1071 --plan skip          # synthesize a minimal vBRIEF and vBRIEF tasks, then work
+pan start PAN-1071 --plan skip          # synthesize a minimal xBRIEF and xBRIEF tasks, then work
 ```
 
 The default planning mode comes from `planning.default_mode` in `~/.overdeck/config.yaml`;
@@ -63,6 +64,9 @@ Start-time policy flags are persisted on the issue before planning or work begin
 sets the durable work-model override used by later respawns, `--swarm` accepts `off`, `auto`,
 or `always`, `--review-mode` accepts `quick`, `full`, or `none`, and `--review-model` pins the
 model used by the review convoy. Omitted flags leave existing and inherited policy untouched.
+When this start also kicks off planning (no plan exists yet), `--plan-model <model>` overrides
+the planning agent's model for that session only — it is a one-shot override, not persisted
+policy, and it never changes the work agent's model (`--model`).
 
 If an agent is paused, `pan start <id>` refuses to spawn until you run `pan unpause <id>`.
 Use `--force` only when you intentionally want to clear that pause gate and start anyway.

package/sync-sources/skills/pan-swarm/SKILL.md

@@ -5,7 +5,7 @@ description: Start and recover Overdeck swarm slots for planned issues with `pan
 
 # Pan Swarm
 
-Use `pan swarm` when an issue has a finalized vBRIEF plan and the operator wants Deacon-managed parallel slot execution.
+Use `pan swarm` when an issue has a finalized xBRIEF plan and the operator wants Deacon-managed parallel slot execution.
 
 ## Start a Swarm
 

package/sync-sources/skills/pan-sync/SKILL.md

@@ -286,7 +286,7 @@ These names are reserved by Overdeck. Don't use them for custom skills:
 
 **Pan operations:** `pan-down`, `pan-help`, `pan-install`, `pan-issue`, `pan-plan`, `pan-quickstart`, `pan-setup`, `pan-status`, `pan-up`, `pan-config`, `pan-tracker`, `pan-projects`, `pan-sync`, `pan-docker`, `pan-network`, `pan-approve`, `pan-tell`, `pan-kill`, `pan-doctor`, `pan-diagnose`, `pan-logs`, `pan-rescue`
 
-**Workflow skills:** `vBRIEF tasks`, `bug-fix`, `code-review`, `code-review-performance`, `code-review-security`, `dependency-update`, `feature-work`, `incident-response`, `onboard-codebase`, `refactor`, `release`, `session-health`, `skill-creator`, `web-design-guidelines`, `work-complete`
+**Workflow skills:** `pan-task`,  `bug-fix`, `code-review`, `code-review-performance`, `code-review-security`, `dependency-update`, `feature-work`, `incident-response`, `onboard-codebase`, `refactor`, `release`, `session-health`, `skill-creator`, `web-design-guidelines`, `work-complete`
 
 ## Related Skills
 

package/sync-sources/skills/pan-task/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: pan-task
-description: "pan task <verb> <issue> — claim and complete vBRIEF checklist items"
+description: "pan task <verb> <issue> — claim and complete xBRIEF checklist items"
 triggers:
   - pan task
   - claim task
@@ -11,7 +11,7 @@ allowed-tools:
 
 # pan task
 
-Run the requested task command now. Task state belongs to one issue's vBRIEF checklist.
+Run the requested task command now. Task state belongs to one issue's xBRIEF checklist.
 
 ```bash
 pan task next PAN-123