create-harness-vibe-coding 0.8.8 → 0.8.9

package/templates/common/.claude/agents/task-scribe.md

@@ -0,0 +1,70 @@
+---
+name: task-scribe
+description: Use to maintain Harness task state, heartbeat, dispatch ledger, evidence pointers, and compact PLAN/PROGRESS updates. Small-fast chore agent. Never edits source code.
+tools: Read, Grep, Glob, Write, Edit
+model: haiku
+---
+
+# Task Scribe
+
+You are a task-state maintenance agent for this project harness. You own durable task tracking. You never make product, architecture, or scope decisions.
+
+## Load First
+
+- `Harness/tasks/<task-id>/STATE.json` (when active)
+- `Harness/tasks/<task-id>/PLAN.md` (when active)
+- `Harness/tasks/<task-id>/PROGRESS.md` (when active)
+- `Harness/PROGRESS.md` (when syncing global task index)
+- `Harness/tasks/<task-id>/ARTIFACTS.md` (when tracking evidence)
+- `Harness/tasks/<task-id>/NOTES.md` (when recording structured notes)
+
+## Write Scope
+
+Allowed writes ONLY:
+- `Harness/PROGRESS.md` — update Active Task, Task Index rows
+- `Harness/tasks/<task-id>/STATE.json` — update per controller structured update (phase, gate, queues, dispatchLedger, nextAction, acceptance, decisions, risks, artifacts)
+- `Harness/tasks/<task-id>/PLAN.md` — update Goal, Decisions, Scope, Context, Memory Preflight, Agents, Verification, Risks sections (controller-supplied structured updates only)
+- `Harness/tasks/<task-id>/PROGRESS.md` — update Status, Heartbeat, Tasks, Changes, Verification, Notes sections
+- `Harness/tasks/<task-id>/ARTIFACTS.md` — record evidence pointers
+- `Harness/tasks/<task-id>/NOTES.md` — record structured notes
+
+Forbidden:
+- Source code (any file outside the Harness/tasks/ capsule and Harness/PROGRESS.md)
+- Product/architecture decisions
+- AC or scope changes (unless controller provides exact structured update)
+- Memory files (Harness/memory/*) — delegated to memory-master
+- MEMORY.md index — delegated to memory-master
+
+## Compact Heartbeat
+
+Maintain `PROGRESS.md#Heartbeat` with:
+- Phase and active wave
+- Blocker (if any)
+- Next action
+- Evidence path (file pointer, not full evidence content)
+- Dispatch ledger summary: agent, role, model tier, status, evidence pointer
+
+## Dispatch Ledger
+
+Track subagent dispatch in `PROGRESS.md` or `PLAN.md#Agents`:
+- agent name, role, model tier, readSet, writeSet, status, evidence path
+- Keep rows compact — one line per dispatch
+
+## Return Format
+
+Return <= 200 tokens:
+```
+Files written: [paths]
+Updated sections: [list]
+Next action: [one line]
+Blocked: [true/false — if true, what is missing]
+```
+
+## Rules
+
+- Never guess missing information. If controller-supplied data is incomplete, return BLOCKED with what is needed.
+- If STATE.json, PLAN.md, and PROGRESS.md conflict (different phase, different gate status), return BLOCKED with the specific conflict. Do not resolve contradictions.
+- Keep every entry compact — one or two lines per section update.
+- Do not duplicate. If a section already has the exact information, skip it.
+- Do not reorder existing entries without controller instruction.
+- Do not delete entries unless controller explicitly says "delete".

package/templates/common/.claude/commands/wf-help.md

@@ -6,15 +6,19 @@ do not dispatch agents, and do not edit files.
 | Command | Type | Usage | Purpose |
 | --- | --- | --- | --- |
 | `/wf-help` | direct command | `/wf-help` | Show this command table. |
-| `/wf <task>` | workflow skill | `/wf fix failing login flow` | Standard acceptance-driven workflow for long, uncertain, multi-file, browser/API, or recovery work. |
-| `/wf-max <task>` | workflow skill | `/wf-max refactor auth module` | WF strict superset: complete role chain plus maximum fan-out, CEO -> Manager -> Worker dispatch, cross-CLI overflow when the current runtime agent pool is exhausted. |
+| `/wf <task>` | workflow skill | `/wf fix failing login flow` | Tiered WF: WF-Light (low-risk, planner/test/verifier), WF-Standard (multi-file, compact ACs), WF-Full (high-risk/cross-layer, full role chain). |
+| `/wf-max <task>` | workflow skill | `/wf-max refactor auth module` | WF-Max-Useful default (fan-out only where independent), WF-Max-Strict override (unconditional fan-out). |
 | `/wf-auto` | workflow skill | `/wf-auto` | Perpetual adaptive auto-optimization using project evidence, dynamic probes, risk obligations, evidence ledger, and confirmation-based exhaustion. |
 | `/wf-auto-spark` | workflow skill | `/wf-auto-spark` | Perpetual inspiration mode with roadmap anchoring and external spark search. |
 | `/wf-review <focus>` | workflow skill | `/wf-review security and test coverage` | Cross-model peer review through the other CLI; use for second opinions and risk checks. |
 | `/wf-learn` | workflow skill | `/wf-learn` | Force context-master -> memory-master learning cycle after repeated failures or closeout. |
 | `/wf-readme <task>` | workflow skill | `/wf-readme polish quickstart` | Preserve, merge, or improve README docs without trampling existing project documentation. |
-| `/wf-update` | workflow skill | `/wf-update` | Check/apply Harness scaffold updates with safe file classification and conflict handling. |
+| `/wf-update` | direct command | `/wf-update` | Check/apply Harness scaffold updates with safe file classification and conflict handling. |
 | `/wf-remove` | workflow skill | `/wf-remove` | Safely remove Harness files while preserving project/user data unless explicitly purged. |
 
 Source of truth: `Harness/README.md#Skill Commands` plus installed skills under
-`.claude/skills/`.
+`.claude/skills/` (Claude Code) or `.agents/skills/` (Codex). In OpenCode the
+same skills load from `.claude/skills/`, `.agents/skills/`, and `.opencode/skills/`.
+In OpenCode, every workflow command above is also visible as a thin command
+wrapper under `.opencode/commands/` (e.g. `/wf`, `/wf-max`); each wrapper only
+routes to the matching skill adapter and does not duplicate the workflow.

package/templates/common/.claude/commands/wf-update.md

@@ -0,0 +1,24 @@
+# /wf-update
+
+Run the Harness update checker script. Do not invoke a skill or start WF mode.
+
+## Flow
+
+1. Run `node Harness/scripts/wf-update-check.mjs --json` and use the `agent` block as the action plan.
+2. Preserve all PRESERVE files. Never overwrite user task, memory, research, README, package, or architecture files.
+3. If `agent.safeApplyCommand` is present, run it to apply SAFE/NEW files first.
+4. For conflicts, compare local with `templateHint` or `remoteUrl`, decide merge/keep-local/overwrite, and record via `--accept-local`, `--accept-merged`, or `--accept-template`.
+5. Run `node Harness/scripts/wf-update-check.mjs --finalize` after all conflicts resolved.
+6. After update, run `node Harness/scripts/validate-harness.mjs` and `node Harness/scripts/scan-clean.mjs`.
+
+Codex users without a direct command surface: use `$wf-update` (skill path) or `node Harness/scripts/wf-update-check.mjs`.
+
+## Recovery
+
+If the script reports `Harness/.harness-version not found` or the update checker script itself is missing (`Harness/scripts/wf-update-check.mjs`), the Harness install predates version-tracking. Recover by regenerating missing infrastructure without overwriting user files:
+
+```
+npx create-harness-vibe-coding@latest <project-name> . -y --on-conflict skip
+```
+
+This creates missing Harness files while preserving CLAUDE.md, README.md, tasks, memory, research, and all user data. After recovery, re-run the update check.

package/templates/common/.claude/rules/ecc/common.md

@@ -7,7 +7,9 @@ alwaysApply: true
 
 ## Context
 
-- Start with `CLAUDE.md`, `Harness/MEMORY.md`, and `Harness/README.md`.
+- Start with `CLAUDE.md`. When `Harness/` exists, also read `Harness/memory/startup-hints.md` (L2 lightweight digest, not full router).
+- When the user explicitly invokes a `/wf-*` command, load `Harness/MEMORY.md` and `Harness/README.md`.
+- For simple single-step tasks without `/wf-*`, operate in direct mode: skip the Harness router and execute directly.
 - Do not bulk-read `Harness/`. Load by router trigger.
 - Keep `Harness/tasks/<task-id>/PROGRESS.md` and `Harness/tasks/<task-id>/PLAN.md` current when work has multiple steps, files, or agents.
 - project files are the only durable communication channel. chat/subagent transcript state is non-authoritative.
@@ -20,6 +22,13 @@ alwaysApply: true
 - Bug fix: reproduction first.
 - Before release, add CI for the chosen stack and run the full verification path.
 
+## Low-Noise Progress
+
+- Keep intermediate user updates to 1-2 short sentences.
+- Do not recap plans, paste logs, or narrate obvious file reads while working.
+- Put the detailed summary in the final response: files changed, verification, risks, and commit hash when relevant.
+- During long-running work, report only phase changes, blockers, failed commands, or user decisions needed.
+
 ## Subagents
 
 - Use `Harness/subagents.md` before orchestrating multiple agents.
@@ -33,10 +42,14 @@ alwaysApply: true
 
 ## Memory
 
+- Detect memory candidates when user says: `remember`, `next time`, `don't`, `do not`, `never`, `always`, `I prefer`, `I want you to`, `记住`, `下次`, `以后`, `不要再`, `总是`, `永远不要`, `我偏好`, `我希望你以后`.
+- Explicit user preference that is clear, safe, and scoped can be written to L3 immediately without waiting for `/wf-learn`.
+- Use `Harness/memory/routes.md` for deterministic route matching before loading detailed L3 memory.
 - Record a lightweight reflection in `Harness/memory/tool-usage-reflections.md` when the same tool/use pattern fails 3+ times.
 - Record repeated user corrections or durable preferences in `Harness/memory/user-corrections-preferences.md` when the user corrects the same assumption/pattern 2+ times.
 - Record reusable review/debug lessons in `Harness/memory/agent-lessons-patterns.md`.
-- Keep memory entries concise and never include secrets.
+- Never record task logs, process summaries, one-time emotions, transient notes, raw logs, or secrets.
+- Keep memory entries compact and default to no date; only add date/timestamp for superseded, conflicting, or time-sensitive entries.
 
 ## Security
 

package/templates/common/.claude/settings.json

@@ -29,5 +29,18 @@
       "Read(**/*.key)",
       "Read(**/*.pem)"
     ]
+  },
+  "hooks": {
+    "UserPromptSubmit": [
+      {
+        "matcher": "",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "node -e \"const fs=require('fs'),p=require('path'),cp=require('child_process');let d=process.env.CLAUDE_PROJECT_DIR||process.cwd();for(;;){const s=p.join(d,'Harness','scripts','wf-auto-update-prompt.mjs');if(fs.existsSync(s)){const r=cp.spawnSync(process.execPath,[s,'--format','claude'],{stdio:'inherit',cwd:d,env:process.env});process.exitCode=(r.status==null)?0:r.status;break}const u=p.dirname(d);if(u===d)break;d=u}\""
+          }
+        ]
+      }
+    ]
   }
 }

package/templates/common/.claude/skills/subagent-orchestrator/SKILL.md

@@ -8,6 +8,12 @@ description: Use when work needs bounded subagent coordination, parallel read-on
 This skill is runtime-neutral. Claude Code and Codex expose different
 subagent surfaces; follow the same Harness role contract either way.
 
+## Memory Preflight
+
+1. Direct simple tasks and `/wf-help` are exempt.
+2. For non-direct work, load `CLAUDE.md`, `Harness/MEMORY.md` index only, then `Harness/README.md` before planning, dispatch, edits/deletes, validation, or peer review.
+3. Load `Harness/memory/*` only when `MEMORY_PROTOCOL.md` scenario hints match; otherwise record "memory hints: none".
+
 ## Load
 
 - `Harness/subagents.md`
@@ -16,7 +22,7 @@ subagent surfaces; follow the same Harness role contract either way.
 - `Harness/agent-workflow.md`
 - `Harness/PROGRESS.md`
 - Active `Harness/tasks/<task-id>/PROGRESS.md` and `PLAN.md`, when present
-- `Harness/WF.md` when in `/wf`, `wf mode`, `workflow mode`, or `wk mode`
+- `Harness/WF.md` when in explicit `/wf`, `$wf`, or `/skills wf`
 
 ## Runtime Mapping
 
@@ -36,9 +42,7 @@ subagent surfaces; follow the same Harness role contract either way.
   integrates returns, and owns final verification.
 - Subagents or bounded passes are readers and reporters unless a write set is
   explicitly assigned and disjoint.
-- Explicit WF/WK mode requires complete role-chain coverage from intake through
-  final acceptance: plan, research/docs research as needed, architecture, test,
-  implement, independent validation, cross-review, reflector, and accept.
+- Explicit WF/WF-MAX requires tier-specific role coverage per `Harness/WF.md`.
 - Every dispatch needs role, goal, mode, read set, write set, forbidden scope,
   injected docs, dependencies, evidence, stop condition, and return format.
 - Prefer parallel read-only exploration first. Serialize writers unless write

package/templates/common/.claude/skills/wf/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: wf
-description: Use for /wf in Claude Code, $wf or /skills wf in Codex, or any long, uncertain, multi-file, migration, recovery, or architecture-heavy task that should follow Harness WF mode.
+description: Use for /wf in Claude Code, $wf or /skills wf in Codex. WF is explicit only — the user must type /wf, $wf, or /skills wf to enter.
 ---
 
 # WF Mode Adapter
@@ -15,10 +15,16 @@ This skill is a thin tool adapter. The authoritative workflow lives in
 - Codex app may also list enabled skills in the `/` menu, depending on the
   current surface and feature state.
 
+## Memory Preflight
+
+1. Direct simple tasks and `/wf-help` are exempt.
+2. For non-direct work, load `CLAUDE.md`, `Harness/MEMORY.md` index only, then `Harness/README.md` before planning, dispatch, edits/deletes, validation, or peer review.
+3. Load `Harness/memory/*` only when `MEMORY_PROTOCOL.md` scenario hints match; otherwise record "memory hints: none".
+
 ## Load
 
 1. `CLAUDE.md`
-2. `Harness/MEMORY.md`
+2. `Harness/MEMORY.md` (index only per Memory Preflight)
 3. `Harness/README.md`
 4. `Harness/PROGRESS.md`
 5. `Harness/WF.md`
@@ -27,14 +33,15 @@ This skill is a thin tool adapter. The authoritative workflow lives in
 ## Rules
 
 - Create or update a task capsule under `Harness/tasks/<task-id>/`.
+- Select the right WF tier: WF-Light (low-risk, planner/test/verifier), WF-Standard (multi-file, compact ACs, one review lens), WF-Full (high-risk/cross-layer, full role chain).
 - Run the WF loop from `Harness/WF.md`: intake, bounded exploration, second
   plan, implementation, review, verification, recovery, and closeout.
-- For explicit WF invocation, schedule the complete role chain at intake:
+- **Tier-aware acceptance**:
+  - **WF-Light**: planner + test-writer + implementer + verifier suffice. Verification passes = closeout. Cross-review and reflector are NOT mandatory unless risk triggers them.
+  - **WF-Standard**: one independent review lens required. Reflector may be triggered by risk.
+  - **WF-Full**: cross-review + reflector PASS required before final acceptance.
+- WF-Full requires the complete role chain at intake:
   plan, research/docs research as needed, architecture, test, implement,
-  independent validation, cross-review, reflector, and final acceptance. Use
-  real subagents when the runtime supports them; otherwise record bounded-pass
-  fallback coverage in the task plan.
-- Do not mark accepted until cross-review passes and the reflector returns
-  PASS.
+  independent validation, cross-review, reflector, and final acceptance.
 - Keep `Harness/tasks/<task-id>/PROGRESS.md#Heartbeat` current before long
   commands, after failures, and at closeout.

package/templates/common/.claude/skills/wf-auto/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: wf-auto
-description: Perpetual adaptive auto-optimization mode. Selects probes from project evidence instead of a fixed angle count. Inherits WF acceptance gates and subagent orchestration per cycle. Use for Claude /wf-auto, Codex $wf-auto, auto mode, or unbounded self-directed optimization.
+description: Perpetual adaptive auto-optimization mode. Selects probes from project evidence instead of a fixed angle count. Inherits WF acceptance gates and subagent orchestration per cycle. Use for Claude /wf-auto, Codex $wf-auto. Explicit only — the user must type /wf-auto, $wf-auto, or /skills wf-auto.
 ---
 
 # WF Auto - Perpetual Auto-Optimization
@@ -18,7 +18,8 @@ description: Perpetual adaptive auto-optimization mode. Selects probes from proj
 
 - Claude `/wf-auto`
 - Codex `$wf-auto`
-- `wf auto`, `auto mode`, or a request for continuous self-directed improvement
+
+Do not use unless the user explicitly invokes `/wf-auto`, `$wf-auto`, or `/skills wf-auto`. The phrases "auto mode", "never stop", "self-improve", "continuous optimize", "unbounded self-directed optimization" are NOT triggers — only an explicit command token enters WF-AUTO.
 
 Do not use when the user gives a bounded task, requests maximum parallelism
 (`/wf-max`), needs an urgent production hotfix, or the codebase is tiny enough

package/templates/common/.claude/skills/wf-learn/SKILL.md

@@ -10,9 +10,13 @@ consolidates. Use the active runtime's available subagent mechanism when
 present, otherwise emulate the same roles as bounded passes and record that
 fallback.
 
+**Note:** Explicit user preferences (remember/next time/never/always/记住/下次/不要再) can be written immediately via candidate detection without waiting for `/wf-learn`. `/wf-learn` is for proactive pattern consolidation and closeout extraction.
+
 ## Load
 
 - `Harness/MEMORY.md`
+- `Harness/memory/routes.md`
+- `Harness/memory/startup-hints.md`
 - `Harness/memory/tool-usage-reflections.md`
 - `Harness/memory/user-corrections-preferences.md`
 - `Harness/memory/agent-lessons-patterns.md`
@@ -22,8 +26,11 @@ fallback.
 
 1. Analyze the session for repeated failures, durable user corrections, and
    reusable review/debug lessons.
-2. Deduplicate against existing memory.
-3. Write only concise, durable, non-secret lessons to `Harness/memory/*`.
+2. Check `Harness/memory/routes.md` for existing entries before writing.
+3. Deduplicate against existing memory.
+4. Write only concise, durable, non-secret lessons to `Harness/memory/*`.
+   Use compact format (default no date):
+   `- When <scenario>: <rule>. Avoid <over-application>. Signals: <signals>.`
 
 ## Return
 

package/templates/common/.claude/skills/wf-max/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: wf-max
-description: Use for /wf-max in Claude Code, $wf-max or /skills wf-max in Codex, or maximum-parallelism Harness work with WF strict-superset gates and CEO -> manager -> worker decomposition.
+description: Use for /wf-max in Claude Code, $wf-max or /skills wf-max in Codex. WF-MAX is explicit only — the user must type /wf-max, $wf-max, or /skills wf-max.
 ---
 
 # WF-MAX Adapter
@@ -13,10 +13,16 @@ routes and summarizes hard constraints.
 - Claude Code: `/wf-max [task]`
 - Codex: `$wf-max` or `/skills` then choose `wf-max`
 
+## Memory Preflight
+
+1. Direct simple tasks and `/wf-help` are exempt.
+2. For non-direct work, load `CLAUDE.md`, `Harness/MEMORY.md` index only, then `Harness/README.md` before planning, dispatch, edits/deletes, validation, or peer review.
+3. Load `Harness/memory/*` only when `MEMORY_PROTOCOL.md` scenario hints match; otherwise record "memory hints: none".
+
 ## Load
 
 1. `CLAUDE.md`
-2. `Harness/MEMORY.md`
+2. `Harness/MEMORY.md` (index only per Memory Preflight)
 3. `Harness/README.md`
 4. `Harness/WF-MAX.md`
 5. `Harness/subagents.md`
@@ -25,20 +31,32 @@ routes and summarizes hard constraints.
 
 ## Rules
 
-WF-MAX is a WF strict superset: every WF role, gate, and acceptance rule still
-applies, then execution expands through:
+WF-MAX inherits the selected WF tier and the shared WF-KERNEL gates
+(`Harness/WF-KERNEL.md`), then expands safe parallelism. WF-Max-Useful is
+default; WF-Max-Strict only on explicit strict request. Execution expands
+through:
 
 1. Global mode: `wf-max`
 2. Agent role: `ceo | manager | worker | reviewer | verifier | reflector`
 3. Dispatch permission: `writeSet`, `forbidden`, `verification`
 
+WF-Max-Useful (default): `/wf-max` fans out only where write sets or review
+lenses are meaningfully independent. Overhead > 0.30 degrades the wave.
+
+WF-Max-Strict (explicit override): user says `--strict`, `strict wf-max`, or
+`strict mode`. Unconditional fan-out per the original span formula.
+
 - CEO reads, plans, dispatches, synthesizes, and writes task state only. CEO
   never edits production source.
 - Workers edit only the dispatch `writeSet`; outside write set is blocked.
 - Managers coordinate and synthesize. Reviewers read/report only.
 - D-GATE is mandatory before implementation waves: dispatch table, AC IDs,
   disjoint file claims, self-audit, and reviewer plan.
-- Final acceptance requires verifier evidence, cross-review, and reflector PASS.
+- Final acceptance is tier-aware per `Harness/WF-KERNEL.md`:
+  - WF-Light + `/wf-max`: verification + state evidence suffices unless risk
+    triggers review/reflector.
+  - WF-Standard + `/wf-max`: verifier evidence + one independent review PASS.
+  - WF-Full or risk-triggered `/wf-max`: cross-review PASS + reflector PASS.
 
 ## Fan-Out Discipline
 

package/templates/common/.claude/skills/wf-update/SKILL.md

@@ -1,14 +1,17 @@
 ---
 name: wf-update
-description: Use for /wf-update in Claude Code, $wf-update or /skills wf-update in Codex, or any request to check for or apply Harness scaffold updates.
+description: Codex compatibility: use $wf-update or /skills wf-update in Codex. In Claude Code and OpenCode, /wf-update is a direct command (see .claude/commands/wf-update.md and .opencode/commands/wf-update.md).
 ---
 
 # WF Update Adapter
 
+This skill is a Codex compatibility shim plus script-flow reference. Claude Code and OpenCode handle `/wf-update` as a direct command; do not route them through this skill.
+
 ## Invocation
 
-- Claude Code: use `/wf-update` or select the `wf-update` skill.
 - Codex CLI or IDE: use `$wf-update` or `/skills` then choose `wf-update`.
+- Claude Code: `/wf-update` is a direct command. Use `.claude/commands/wf-update.md`, not this skill.
+- OpenCode: `/wf-update` is a direct command. Use `.opencode/commands/wf-update.md`, not this skill.
 
 ## Load
 
@@ -37,6 +40,16 @@ description: Use for /wf-update in Claude Code, $wf-update or /skills wf-update
    JSON plan has zero conflicts.
 6. After update, run the validator and then scan-clean.
 
+## Recovery
+
+If `Harness/scripts/wf-update-check.mjs` is missing (old install without updater), or `Harness/.harness-version` is missing or corrupted, do NOT reinstall from scratch. Recover by regenerating missing infrastructure:
+
+```
+npx create-harness-vibe-coding@latest <project-name> . -y --on-conflict skip
+```
+
+The `--on-conflict skip` policy preserves all existing user files (CLAUDE.md, README.md, tasks, memory, research, architecture) and only creates missing Harness infrastructure files. After recovery, re-run the update check.
+
 ## Return
 
 Report version, SAFE/NEW updates, conflicts and decisions, preserved files,

package/templates/common/.codex/hooks.json

@@ -0,0 +1,17 @@
+{
+  "hooks": {
+    "UserPromptSubmit": [
+      {
+        "hooks": [
+          {
+            "type": "command",
+            "command": "node \"$(git rev-parse --show-toplevel)/Harness/scripts/wf-auto-update-prompt.mjs\" --format codex",
+            "commandWindows": "powershell -NoProfile -ExecutionPolicy Bypass -Command \"$root=(git rev-parse --show-toplevel 2>$null); if (-not $root) { $root=(Get-Location).Path }; node (Join-Path $root 'Harness/scripts/wf-auto-update-prompt.mjs') --format codex\"",
+            "statusMessage": "Checking Harness updates",
+            "timeout": 35
+          }
+        ]
+      }
+    ]
+  }
+}