create-harness-vibe-coding 0.8.9 → 0.8.10

package/README-CN.md

@@ -61,7 +61,7 @@ Agent 读取本 README 后，按项目状态选择安装路径：
 | `/wf-max <任务>` | 任务可拆成多个互不冲突的部分，需要最大并行度 | 在完整 WF 链路上增加 CEO → Manager → Worker 分工和并行波次 | `/wf-max 并行升级前端、后端和文档` |
 | `/wf-auto` | 希望 Agent 持续自我优化，通过自适应探测选择 | 持续执行优化循环，每轮保留计划、证据和反馈 | `/wf-auto 优化这个项目的稳定性` |
 | `/wf-auto-spark` | 需要外部灵感、竞品方向或长期路线图 | 搜索外部 spark，绑定 North Star 和里程碑，限制偏离范围 | `/wf-auto-spark 探索产品增长方向` |
-| `/wf-review [重点]` | 需要第二意见、跨模型审查或上线前复核 | 调用其他 Agent 做独立审查，并按严重程度反馈 | `/wf-review 重点检查安全和数据丢失` |
+| `/wf-review [重点]` | 需要第二意见、同行审查或上线前复核 | 优先调用可用 peer CLI；没有时使用独立 reviewer 角色，并按严重程度反馈 | `/wf-review 重点检查安全和数据丢失` |
 | `/wf-learn` | 同类错误反复出现，或一次任务结束后要沉淀经验 | 汇总上下文、记忆和项目经验，形成下一次可复用规则 | `/wf-learn 总结这次返修原因` |
 | `/wf-browser <任务>` | 浏览器冒烟、E2E、截图、表单或页面验证 | 使用真实浏览器完成操作并提供截图、追踪和验证证据 | `/wf-browser 验证登录和支付流程` |
 | `/wf-readme <任务>` | README、安装文档、架构图或项目说明需要重写 | 保留事实，整理结构，补充安装和使用说明 | `/wf-readme 优化中文 README` |

package/README.md

@@ -72,7 +72,7 @@ When in doubt, use `/wf-help`. It returns the full command table. Use `/wf` for
 | `/wf-max <task>` | The task splits into independent work and needs maximum parallelism | Adds CEO → Manager → Worker roles and parallel waves to the full WF chain | `/wf-max upgrade frontend, backend, and docs in parallel` |
 | `/wf-auto` | You want continuous self-directed optimization with adaptive probe selection | Runs repeated optimization cycles with plans, evidence, and feedback | `/wf-auto improve this project's stability` |
 | `/wf-auto-spark` | You need external inspiration, competitive direction, or a long-term roadmap | Searches for sparks, anchors work to a North Star and milestones, and guards scope drift | `/wf-auto-spark explore product growth directions` |
-| `/wf-review [focus]` | You need a second opinion, cross-model review, or a pre-release check | Runs an independent review and classifies findings by severity | `/wf-review focus on security and data loss` |
+| `/wf-review [focus]` | You need a second opinion, peer review, or a pre-release check | Uses a peer CLI when available, otherwise an independent reviewer role, and classifies findings by severity | `/wf-review focus on security and data loss` |
 | `/wf-learn` | The same mistakes keep recurring or a completed task needs to become reusable knowledge | Consolidates context, memory, and project lessons | `/wf-learn summarize why this task needed rework` |
 | `/wf-browser <task>` | Browser smoke tests, E2E, screenshots, forms, or UI verification | Uses a real browser and returns screenshots, traces, and evidence | `/wf-browser verify login and checkout` |
 | `/wf-readme <task>` | README, install docs, architecture diagrams, or project docs need work | Preserves facts while improving structure, setup, and usage guidance | `/wf-readme improve the Chinese README` |

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "create-harness-vibe-coding",
-  "version": "0.8.9",
+  "version": "0.8.10",
   "description": "Scaffold a 0-1 product harness for AI-assisted research, PRD, planning, architecture, build, test, and feedback loops",
   "type": "module",
   "bin": {
@@ -20,6 +20,7 @@
     "build:version": "node scripts/build-version.mjs",
     "prepush": "node scripts/pre-push-check.mjs",
     "test": "node --test tests/*.test.js",
+    "test:e2e": "node tests/e2e-wf-scripts.test.mjs",
     "test:smoke": "node --test tests/cli-smoke.test.js",
     "pack:smoke": "node --test tests/pack-smoke.test.js"
   },

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

@@ -10,7 +10,7 @@ do not dispatch agents, and do not edit files.
 | `/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-review <focus>` | workflow skill | `/wf-review security and test coverage` | Peer CLI review through Claude/Codex/OpenCode, with reviewer subagent fallback. |
 | `/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` | direct command | `/wf-update` | Check/apply Harness scaffold updates with safe file classification and conflict handling. |

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

@@ -31,9 +31,9 @@
     ]
   },
   "hooks": {
-    "UserPromptSubmit": [
+    "SessionStart": [
       {
-        "matcher": "",
+        "matcher": "startup|resume|clear",
         "hooks": [
           {
             "type": "command",

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

@@ -31,8 +31,8 @@ subagent surfaces; follow the same Harness role contract either way.
 - Codex: use the available subagent tool or role mechanism in the current
   surface. If unavailable, emulate the same roles as separate bounded passes.
 - WF-MAX cross-CLI overflow: prefer the current runtime's subagents first; if that pool
-  is exhausted, overflow to the other CLI with explicit dispatch packets
-  (Codex -> `claude -p`, Claude -> available Codex CLI such as `codex exec`)
+  is exhausted, overflow to a peer CLI with explicit dispatch packets
+  (`claude -p`, `codex exec`, or `opencode run --agent <role> --dir .`)
   before bounded-pass fallback.
 - In every runtime, record fallback and role coverage in the task plan.
 

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

@@ -70,9 +70,9 @@ WF-Max-Strict (explicit override): user says `--strict`, `strict wf-max`, or
   or global Codex config.
 - Keep `agents.max_depth = 1` unless the user explicitly approves recursive
   delegation.
-- If the current runtime is exhausted, overflow to the other CLI with explicit
-  dispatch packets: Codex -> `claude -p`; Claude -> available Codex CLI such as
-  `codex exec`.
+- If the current runtime is exhausted, overflow to a peer CLI with explicit
+  dispatch packets: `claude -p`, `codex exec`, or
+  `opencode run --agent <role> --dir .`.
 - Do not rely on undocumented config, environment variables, forked/derived
   conversations, Codex++, local patches, or third-party forks as stable ways to
   remove subagent limits.

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

@@ -1,34 +1,85 @@
 ---
 name: wf-review
-description: Use for /wf-review in Claude Code, $wf-review or /skills wf-review in Codex, peer review, second opinion, or cross-model review.
+description: Use for /wf-review in Claude Code or OpenCode, $wf-review or /skills wf-review in Codex, peer review, second opinion, cross-runtime review, or independent reviewer subagent review.
 ---
 
 # WF Review Adapter
 
-Use the other available agent CLI for independent review. Never simulate a
-cross-model review with the same model.
+Prefer an independent peer runtime for review. If no other CLI is available,
+use the installed reviewer role as a separate subagent context. Never label a
+same-runtime reviewer or bounded role pass as cross-model review.
 
 ## Invocation
 
 - Claude Code: use `/wf-review [focus]` or select the `wf-review` skill.
 - Codex CLI or IDE: use `$wf-review` or `/skills` then choose `wf-review`.
+- OpenCode: use `/wf-review [focus]`; the `.opencode/commands/wf-review.md`
+  wrapper routes here.
 
-## CLI Direction
+## Authority
 
-| Runtime | Command |
-| --- | --- |
-| Claude Code -> Codex | `git diff | codex exec "<5-dimension review prompt>"` |
-| Codex -> Claude Code | `git diff | claude -p "<5-dimension review prompt>"` |
-| Only one CLI | Warn user. Do not self-review. |
+The main agent is the controller. It owns final decisions, accepted/rejected
+findings, fixes, release claims, and user-facing recommendations. Review
+agents only provide evidence-backed suggestions.
+
+## Runtime Selection
+
+1. Build one review prompt containing the relevant diff, task acceptance
+   criteria, changed-file list, validation evidence, and the review dimensions.
+2. Detect available CLIs (`claude`, `codex`, `opencode`) with the platform's
+   normal command lookup.
+3. Prefer a CLI that is not the current runtime. If several exist, prefer a
+   different model/provider when known; otherwise use the first available in
+   the table below.
+4. If no other CLI exists, dispatch the installed `reviewer` role as a separate
+   subagent context. For WF-MAX or broad/high-risk changes, use
+   `review-manager` to split spec/code/security/performance dimensions when the
+   runtime supports nested subagents.
+5. If neither a peer CLI nor a subagent surface exists, warn that WF-REVIEW is
+   degraded and perform only a controller review; do not count it as
+   independent review.
+
+| Current runtime | Preferred peer CLI | Secondary peer CLI | Same-runtime fallback |
+| --- | --- | --- | --- |
+| Claude Code | `codex exec "<review prompt>"` | `opencode run --agent reviewer --dir . "<review prompt>"` | Claude `reviewer` subagent |
+| Codex | `claude -p "<review prompt>"` | `opencode run --agent reviewer --dir . "<review prompt>"` | Codex subagent or bounded `reviewer` role pass |
+| OpenCode | `claude -p "<review prompt>"` | `codex exec "<review prompt>"` | `opencode run --agent reviewer --dir . "<review prompt>"` or OpenCode `reviewer` subagent |
+| Unknown | any available peer CLI, preferring `claude`, then `codex`, then `opencode` | next available peer CLI | installed `reviewer` role subagent |
+
+OpenCode note: `opencode run [message..]` is the non-interactive CLI path and
+`--agent reviewer` selects the installed `.opencode/agents/reviewer.md` role.
 
 ## Review Dimensions
 
 Cover correctness, security, architecture, performance, and tests. Classify
-findings as Critical, High, Medium, or Low. Return raw peer output first, then
-your severity-classified synthesis.
+findings as Critical, High, Medium, or Low. Return raw peer or subagent output
+first, then the controller's severity-classified synthesis.
+
+## Reviewer Role Fallback
+
+When using a same-runtime subagent fallback, dispatch a real role packet instead
+of an ad hoc prompt:
+
+```text
+Role: reviewer
+AgentName: reviewer
+Mode: read-only
+Objective: review the current diff for correctness, security, architecture,
+performance, tests, and spec/AC compliance
+Read set: changed files, tests, task PLAN/PROGRESS, Harness/agent-workflow.md,
+Harness/subagents.md, Harness/dispatch.md, architecture docs when affected
+Write set: none
+Forbidden: file edits, git mutations, formatting-only advice, ungrounded claims
+ReturnSchema: findings by severity, file/line refs, missing verification,
+open questions, closeout recommendation
+```
+
+If the runtime exposes `review-manager`, use it only when the diff is broad
+enough to benefit from multiple reviewer dimensions. The controller must
+deduplicate reviewer output and decide what to accept.
 
 ## Context
 
 Include the relevant diff, `Harness/architecture.md` when architecture is in
 scope, and any task acceptance criteria. If the diff is too large, ask for a
-narrower scope before invoking the other CLI.
+narrower scope before invoking a peer CLI or reviewer subagent.

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

@@ -1,14 +1,14 @@
 {
   "hooks": {
-    "UserPromptSubmit": [
+    "SessionStart": [
       {
+        "matcher": "startup|resume|clear",
         "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
+            "command": "node -e \"const fs=require('fs'),p=require('path'),cp=require('child_process');let d=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','codex'],{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}\"",
+            "timeout": 35,
+            "statusMessage": "Checking Harness updates"
           }
         ]
       }

package/templates/common/.harness-version

@@ -1,19 +1,19 @@
 {
-  "generator": "0.8.9",
-  "generated": "2026-07-17T09:52:12.208Z",
+  "generator": "0.8.10",
+  "generated": "2026-07-21T04:52:37.663Z",
   "options": [],
   "autoCheck": true,
   "source": "https://raw.githubusercontent.com/zingspark/create-harness-vibe-coding/main/templates/common/",
   "checksums": {
-    ".agents/skills/subagent-orchestrator/SKILL.md": "sha256-a896ff4133fdde522be8a186e26efcf65969d5db279e6ad8bc561a9a2c111ad3",
+    ".agents/skills/subagent-orchestrator/SKILL.md": "sha256-8d9e8c0db4647bcf168a5f99c8b2ea97d154bfca30e78ffd1cc5a98ce185bb1d",
     ".agents/skills/tdd/SKILL.md": "sha256-1e2ec0b54a5cf5b071800b0f2e5672a128a42471e16f70f00bb4c0a07a3617cb",
     ".agents/skills/wf-auto-spark/SKILL.md": "sha256-a00cde5842e5f1d6d69826c59972ebdcfbc2c291b43fc37523e42ec02e4788e4",
     ".agents/skills/wf-auto/SKILL.md": "sha256-f3f288f52766a0f59ec4f2018029c8169782ac440b525f4c1040724ca8482bf3",
     ".agents/skills/wf-learn/SKILL.md": "sha256-2ca977967e62847ac3b763bcce00dc6bb2e8dec28569a1ab6ee413625f8e8779",
-    ".agents/skills/wf-max/SKILL.md": "sha256-3449350938645945f54202200315ee5ec0c5f21ed34cdbaa856a5b669d17e73e",
+    ".agents/skills/wf-max/SKILL.md": "sha256-0cabb44a67ce47beaeae4c2bba9a8a31a9340199c7684b57a1f9e9b7e2eb622e",
     ".agents/skills/wf-readme/SKILL.md": "sha256-4d34ee3b6b305fa2581f5d8cb31e9152759f3df8bf8fa08efbb43782f128bdcd",
     ".agents/skills/wf-remove/SKILL.md": "sha256-21ebef1a1fa8645d094c8ceeca78b33f036b6c42cda6db8be425d38d9e91af75",
-    ".agents/skills/wf-review/SKILL.md": "sha256-cc6d536ec6de25546a0ba96e686f195da50ed11bc03763a76ef46d77243d3537",
+    ".agents/skills/wf-review/SKILL.md": "sha256-ab1122cbc9612ba734f98736e5479d7777206293d011d5471aaa34d1da35dae6",
     ".agents/skills/wf-update/SKILL.md": "sha256-6fa16fd5a526969837b9fd5fcae6aed55eec5ccd755e0a9cddcb7065878f61d8",
     ".agents/skills/wf/SKILL.md": "sha256-53225645b593f4cf060781590f9b3025cf17315baad4e2acce850cc4cd972f97",
     ".claude/agents/architect-manager.md": "sha256-d98c3a2d044d5216d9bcde217b4359b1c33f5be152416e242807652ddcd2868b",
@@ -35,23 +35,23 @@
     ".claude/agents/tdd-guide.md": "sha256-d7c7ad3f61f6a6dc73cfa54ffe7e215ded0421a3058654a01731d1a5d5f4c336",
     ".claude/agents/test-writer.md": "sha256-724866d627f193caaf060ec6af97b1d54c2df2d5c5f937e78fc3c53c7f798b16",
     ".claude/agents/verifier.md": "sha256-d501a505b97e679daa89ee1d910ee185edc42ba57d58203e962b1c5a844c0872",
-    ".claude/commands/wf-help.md": "sha256-3a9783211a72d5c490e6014d263b44aed39f45d93f7463ec26b0b3d79844094d",
+    ".claude/commands/wf-help.md": "sha256-aaaa6834c6cb61d2ecbeb41ad8fcf77de10ac1638b2009a3822284c01cf41fac",
     ".claude/commands/wf-update.md": "sha256-1988e82eb60311b8208367e3c8e22e6222ae05f4b0f645fa9a0e426790705c12",
     ".claude/rules/ecc/common.md": "sha256-e5f046d02ec9f5d326088f608c63758632d9a5f6c67688b20e065b6380884992",
-    ".claude/settings.json": "sha256-7dd4a92963e2336cf738a10d1cf68fb6facc0c03f32c6af0ca62f388a48e14a3",
-    ".claude/skills/subagent-orchestrator/SKILL.md": "sha256-a896ff4133fdde522be8a186e26efcf65969d5db279e6ad8bc561a9a2c111ad3",
+    ".claude/settings.json": "sha256-99e8552584b8e71e3e11b4b760c3bfbf8c1b18dadda7ec3f6e3c46f88d9ea513",
+    ".claude/skills/subagent-orchestrator/SKILL.md": "sha256-8d9e8c0db4647bcf168a5f99c8b2ea97d154bfca30e78ffd1cc5a98ce185bb1d",
     ".claude/skills/tdd/SKILL.md": "sha256-1e2ec0b54a5cf5b071800b0f2e5672a128a42471e16f70f00bb4c0a07a3617cb",
     ".claude/skills/wf-auto-spark/SKILL.md": "sha256-a00cde5842e5f1d6d69826c59972ebdcfbc2c291b43fc37523e42ec02e4788e4",
     ".claude/skills/wf-auto/SKILL.md": "sha256-f3f288f52766a0f59ec4f2018029c8169782ac440b525f4c1040724ca8482bf3",
     ".claude/skills/wf-learn/SKILL.md": "sha256-2ca977967e62847ac3b763bcce00dc6bb2e8dec28569a1ab6ee413625f8e8779",
-    ".claude/skills/wf-max/SKILL.md": "sha256-3449350938645945f54202200315ee5ec0c5f21ed34cdbaa856a5b669d17e73e",
+    ".claude/skills/wf-max/SKILL.md": "sha256-0cabb44a67ce47beaeae4c2bba9a8a31a9340199c7684b57a1f9e9b7e2eb622e",
     ".claude/skills/wf-readme/SKILL.md": "sha256-4d34ee3b6b305fa2581f5d8cb31e9152759f3df8bf8fa08efbb43782f128bdcd",
     ".claude/skills/wf-remove/SKILL.md": "sha256-21ebef1a1fa8645d094c8ceeca78b33f036b6c42cda6db8be425d38d9e91af75",
-    ".claude/skills/wf-review/SKILL.md": "sha256-cc6d536ec6de25546a0ba96e686f195da50ed11bc03763a76ef46d77243d3537",
+    ".claude/skills/wf-review/SKILL.md": "sha256-ab1122cbc9612ba734f98736e5479d7777206293d011d5471aaa34d1da35dae6",
     ".claude/skills/wf-update/SKILL.md": "sha256-6fa16fd5a526969837b9fd5fcae6aed55eec5ccd755e0a9cddcb7065878f61d8",
     ".claude/skills/wf/SKILL.md": "sha256-53225645b593f4cf060781590f9b3025cf17315baad4e2acce850cc4cd972f97",
     ".codex/config.toml": "sha256-e0af046982c6dbc535c52b19610d16ce9aba08a17dd29f11b74cc8dad8371145",
-    ".codex/hooks.json": "sha256-b20527714f82130d67a7e3aca50ced148c8311c81a9731c91f23275a6248143c",
+    ".codex/hooks.json": "sha256-3200c42c2da434c07cd6ab1ce86f8845ab46a1ed9a25b65117b2b2b42056c725",
     ".opencode/agents/architect-manager.md": "sha256-7ea3ce5254638e15c9a9c342eafcaa1c98d5fbf0323ea2111cd6397580581eb1",
     ".opencode/agents/architect.md": "sha256-bd876678ef08ef848523ec639095e099b9d8e587794827fba4763dc82ed3f6c4",
     ".opencode/agents/codebase-explorer.md": "sha256-e72cf6f8c2f4247f2dfd027c94b43fe67f0fe5e6f851ec2400c8094ac343a7ef",
@@ -73,15 +73,15 @@
     ".opencode/agents/verifier.md": "sha256-7a415b3e8ae440838cfd113ef3cbd1c66ab6496e45c9ef90af0d878e3ebc1ee4",
     ".opencode/commands/wf-auto-spark.md": "sha256-febe76ec28b1650886a81d79e19ec53db725da3ed7777cf739ec8e2bbc5d6564",
     ".opencode/commands/wf-auto.md": "sha256-8e27d4d567a980d4d6a2ed0832c4f1f7f7439f172ea03a79c9d24468d01fdf38",
-    ".opencode/commands/wf-help.md": "sha256-ddef1dcc671bcafb0f4f4adb08d0b0ab247e5228613e0f9b2e3b082c7db44652",
+    ".opencode/commands/wf-help.md": "sha256-2776d41e78577896f90f0de3ebdbc032ab9808b96c17ebecbff1319d4e6142b1",
     ".opencode/commands/wf-learn.md": "sha256-dc8e75ef4b2c2ef90c749a23dc2cd99eaf2727955d0670bdb2d6f24086f6d0ed",
     ".opencode/commands/wf-max.md": "sha256-39ebd1e0252b9b72a16a539c8f2afd678bf63aad38c4b964238b287c359a49a2",
     ".opencode/commands/wf-readme.md": "sha256-276e80255bd38f51e17b158650d182401304bf06388407d259f47850306556e8",
     ".opencode/commands/wf-remove.md": "sha256-fe9823152c4f74e66b151e352de7167436d1bc47376c2a688d190391931d300a",
-    ".opencode/commands/wf-review.md": "sha256-c092f15ae3950c30598976005d41853c64daf2181be37bcc4bcefc61b727006e",
+    ".opencode/commands/wf-review.md": "sha256-4bd59f66bc96c2773868e63c37cbacf39dd521555e997c0b60d50538ef2d5dbd",
     ".opencode/commands/wf-update.md": "sha256-1988e82eb60311b8208367e3c8e22e6222ae05f4b0f645fa9a0e426790705c12",
     ".opencode/commands/wf.md": "sha256-d86cf20a78c37757f76aed7e252475fb82e7597cd55c6a4c916441b3b75fe9af",
-    ".opencode/plugins/harness-wf-status.mjs": "sha256-ac36601165fd4a6acc54beb2a574148c2ff45c0f85b1a36ecac50435a9e94a02",
+    ".opencode/plugins/harness-wf-status.mjs": "sha256-ee0987cec5530c34784c619a803562d7085ae26fe5d199fde7ce42c2bed4724e",
     "AGENTS.md": "sha256-fad176931742a5080e073d1ddba99a3eabb67e8c42bebb132df99a51ca6a184d",
     "CLAUDE.md": "sha256-1aa2e672f7f423d0011f65b0dda707bdd7f9db2a83ad54650bb444fb086eabaa",
     "Harness/ACCEPTANCE_PROTOCOL.md": "sha256-0f7a21a1fbfdca6e5f28f3297b61c3446e3bdd552a2143c7032d6271a4e26103",
@@ -89,32 +89,32 @@
     "Harness/DEBUG_PROTOCOL.md": "sha256-ed80de0e3e1a40dbb9fd0bdead9174f1650e1833027f3d7fb4bb5884142e03f7",
     "Harness/ECC-GUIDE.md": "sha256-136e60327813609516c6c10e2a5254d7d300e1631ba80d33fb375fdf3800ca7e",
     "Harness/HARNESS_BRIDGE.md": "sha256-681dbeca9a590bbeb3a0c01b044e40e642e6d640632d8611064eb897ada8a48d",
-    "Harness/MEMORY.md": "sha256-9b2e15ac95e067a735ed90e40946404509b58eafde38671dc6455f68c41f010d",
+    "Harness/MEMORY.md": "sha256-4cbb881b3e9893e917861dc250afaedf5b88da6c99626a9c7f6abb8132841b09",
     "Harness/MEMORY_PROTOCOL.md": "sha256-c8cda68bf25fbf7152c6049959a8bd6d39453976a651a1c4a9d3f7e349f823c4",
-    "Harness/README.md": "sha256-8ea8e392900b89c2d7d90a466d61b742753bb0322541821d91dd0cb1e13f5b73",
+    "Harness/README.md": "sha256-4c8f30de9face43960088d240127860b43a2b821d1988c23a9cd1c0502ba35f7",
     "Harness/SETUP.md": "sha256-008472ad2be5681e2616af29ad57cccbca122065de7bddfe22c683e3470d9fd5",
     "Harness/TASK_ARCHIVE.md": "sha256-d815f2c99a7dc98b9956bb876e9ee07dfb66a283c758124d7b4eb8965dea1f6a",
     "Harness/TDD-GUIDE.md": "sha256-602084530fd0dea7499a023ce75738351e5d97a0c222b64d405f36da6b59a162",
-    "Harness/WF-AUTO-ANGLES.md": "sha256-ff9c684860cef7a6d0c16aa4b825663a1cd18b10befe8a7320621c28bbfe4ae6",
+    "Harness/WF-AUTO-ANGLES.md": "sha256-b9641d871f728e8112ad0d8c7f87bcbec0a06aa572c5f3060efdd26496abdf9b",
     "Harness/WF-AUTO-SPARK.md": "sha256-8fc879261f71f81c5a64e37a6aed8b72fd78ca01c5c9f318a15f4a0a594b4783",
-    "Harness/WF-AUTO.md": "sha256-dff89e2c2348b329cbbf42391667748b61fe152a991daab297d10db6a67f243f",
+    "Harness/WF-AUTO.md": "sha256-7898a38ee9ce9cf1c49aa7e3603c17afc68544981dca7d91e2e4149ca2fc5aea",
     "Harness/WF-KERNEL.md": "sha256-97c626574f62dceaa590829d99e46889b86cab5658d7827c704788e4afdda030",
-    "Harness/WF-MAX.md": "sha256-861961501887b5c9b34444fce985aa567c5d32b94fcefd5f73db6a8c3e10d7cd",
+    "Harness/WF-MAX.md": "sha256-a125dddc1e6a854f71fc360dd4fff7d576dbdd4e6141d29de2f5787d6f48b5e0",
     "Harness/WF-STATE.md": "sha256-80fdaa4b133a9f632a252e4d2fca51bb96f9f9779dab2bc6f3d791d0d2d3aae8",
     "Harness/WF.md": "sha256-199f6c3899cf0d8c86d65fd61e90e85ee9f8aa4c8fc56889f995f05e11987816",
     "Harness/agent-workflow.md": "sha256-a91c3732ffb545506cec88c875d76ebe92248d0714da3e398d2a13b06349bef4",
     "Harness/context-loading.md": "sha256-7dacdc7cbf6748f063db65e31fff1ff7992dc7fd8c72c389f6560e7e0d65ff06",
-    "Harness/dispatch.md": "sha256-03cd1a668293eb2f1992e472d170cc445b000adf5dd1c75e116deed0ad4deeba",
+    "Harness/dispatch.md": "sha256-36b2b0814241384ea1aa6ee6ebb0434aba63eeacd6abfbdd678c0032e16e3631",
     "Harness/extension.md": "sha256-ff93616aaa5ad232b6a32ac6c98bb1a3a08ee5da2ddad92eb9090f5b8e9e3e47",
     "Harness/lifecycle.md": "sha256-a2d025e52f3b4412d8439083aca0d2cf7a4458ad0e30de4fc6465f990379190f",
     "Harness/research/README.md": "sha256-956c154df01cb9376972eb8b88bb3be0fe4e2dda802a72457c0126e3476fa755",
     "Harness/scripts/archive-tasks.mjs": "sha256-07bba20c2f4b3baae737b8b9a951125a48e37dd482a1f1ca122b9cf88e90e956",
-    "Harness/scripts/scan-clean.mjs": "sha256-b3530e825530a2673a40536d3844fabac94a7884480e751ddae2dffacdcbb189",
-    "Harness/scripts/validate-harness.mjs": "sha256-72a020e3f469de08e8a75eb79c5038d9092a490b7b1ce5e80d71c8c066a4bb13",
-    "Harness/scripts/wf-auto-update-prompt.mjs": "sha256-45861ab8285f28c883b23548ff2c64987c2a9b7cb7bb0fab01760147007b54b5",
-    "Harness/scripts/wf-remove.mjs": "sha256-df7f3fa80150dca8e598bfc423e260aa9df9584d716f3b299fdc0fd79c2e1911",
-    "Harness/scripts/wf-update-check.mjs": "sha256-44d15f59cbb98c320552df9e164f19f8a643448299b81c6274666dcd51f4c752",
-    "Harness/subagents.md": "sha256-5468557fb9a4a0e0509518e1a5d92cb5324ff542ed83b526c6a1902745950a25",
+    "Harness/scripts/scan-clean.mjs": "sha256-76fb4212897ea3f366d33b7defee87611c01e9de75c745adfe828745c6fd0887",
+    "Harness/scripts/validate-harness.mjs": "sha256-53339f20c291666fe703cda73325b0b9bca0b4a67dc703d7876a4b1a4d8d6bd9",
+    "Harness/scripts/wf-auto-update-prompt.mjs": "sha256-14210304dbd8e648b8939fc4c5d3664f943052153e689264c16b05b7b81bd39e",
+    "Harness/scripts/wf-remove.mjs": "sha256-576bc92325bf63d4142eb6028d095f12abf9d845a1a178dfe247b813794476a9",
+    "Harness/scripts/wf-update-check.mjs": "sha256-41f7a3c9324d006dc745557031c31d4b9319eaf7fc78df5cfdec671a24c90838",
+    "Harness/subagents.md": "sha256-f2e81c21792b4d70c64c9bd22e9548d783d945dddb3504b4937e04ca1d04320d",
     "Harness/templates/ACCEPTANCE.template.md": "sha256-394a6c08b155b1d121f1d51da774f7988bdb891224c6d5f2ca2c131e8c95ffb3",
     "Harness/templates/API_CONTRACT.template.md": "sha256-e11ec9866576624982f35e77359e3f4ef3aea3e3f6b5895f6cc5419d29699fc5",
     "Harness/templates/PLAYWRIGHT_SPEC.template.ts": "sha256-bef5f3bbae833b31eeb8cab04fc5a5ff355e9eda4ba6909db70f83b403607115",

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

@@ -13,7 +13,7 @@ do not dispatch agents, and do not edit files.
 | `/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-review <focus>` | workflow skill | `/wf-review security and test coverage` | Peer CLI review through Claude/Codex/OpenCode, with reviewer subagent fallback. |
 | `/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` | direct command | `/wf-update` | Check/apply Harness scaffold updates with safe file classification and conflict handling. |

package/templates/common/.opencode/commands/wf-review.md

@@ -1,5 +1,5 @@
 ---
-description: Run cross-model peer review via the wf-review skill
+description: Run peer CLI or reviewer-subagent review via the wf-review skill
 ---
 
 # /wf-review
@@ -9,7 +9,7 @@ static help or script command.
 
 1. Load `CLAUDE.md`, `Harness/MEMORY.md` (index only per Memory Preflight), then `Harness/README.md`.
 2. Execute per the skill adapter `.claude/skills/wf-review/SKILL.md` (mirror: `.agents/skills/wf-review/SKILL.md`).
-3. Do not duplicate the workflow here. The skill adapter and the wf-review cross-model contract are authoritative.
+3. Do not duplicate the workflow here. The skill adapter and the wf-review peer-review contract are authoritative.
 
 If this runtime cannot invoke the skill directly, read
 `.claude/skills/wf-review/SKILL.md` and follow it in place.

package/templates/common/.opencode/plugins/harness-wf-status.mjs

@@ -1,6 +1,6 @@
 import { existsSync, mkdirSync, readFileSync, rmSync, writeFileSync } from 'node:fs';
 import { spawnSync } from 'node:child_process';
-import { dirname, resolve } from 'node:path';
+import { resolve } from 'node:path';
 
 const WF_COMMANDS = new Map([
   ['wf', 'WF'],
@@ -53,14 +53,14 @@ function clearMode(root) {
   }
 }
 
-function runUpdatePrompt(root, prompt) {
+function runUpdatePrompt(root, prompt = '', hookEventName = 'opencode.startup') {
   const script = resolve(root, 'Harness', 'scripts', 'wf-auto-update-prompt.mjs');
   if (!existsSync(script)) return null;
   const result = spawnSync(process.execPath, [script, '--format', 'json'], {
     cwd: root,
     input: JSON.stringify({
       cwd: root,
-      hook_event_name: 'chat.message',
+      hook_event_name: hookEventName,
       prompt,
     }),
     encoding: 'utf-8',
@@ -74,13 +74,6 @@ function runUpdatePrompt(root, prompt) {
   }
 }
 
-function textFromParts(parts) {
-  return (parts || [])
-    .filter(part => part?.type === 'text' && typeof part.text === 'string')
-    .map(part => part.text)
-    .join('\n');
-}
-
 async function showToast(client, directory, body) {
   try {
     await client.tui.showToast({
@@ -94,19 +87,17 @@ async function showToast(client, directory, body) {
 
 export const HarnessWfStatusPlugin = async ({ client, directory, worktree }) => {
   const root = worktree || directory || process.cwd();
+  const startupUpdate = runUpdatePrompt(root);
+  if (startupUpdate?.message) {
+    await showToast(client, root, {
+      title: 'Harness update available',
+      message: startupUpdate.message,
+      variant: 'warning',
+      duration: 12000,
+    });
+  }
 
   return {
-    'chat.message': async (_input, output) => {
-      const update = runUpdatePrompt(root, textFromParts(output.parts));
-      if (!update?.message) return;
-      await showToast(client, root, {
-        title: 'Harness update available',
-        message: update.message,
-        variant: 'warning',
-        duration: 12000,
-      });
-    },
-
     'command.execute.before': async (input) => {
       const mode = WF_COMMANDS.get(commandName(input.command));
       if (!mode) return;

package/templates/common/Harness/MEMORY.md

@@ -33,10 +33,10 @@ Stack-specific agents can be added after the product shape is known.
 - [wf](../.claude/skills/wf/SKILL.md) - Claude Code WF skill command; mirrored for Codex at `../.agents/skills/wf/SKILL.md`.
 - [subagent-orchestrator](../.claude/skills/subagent-orchestrator/SKILL.md) - controller-led subagent orchestration, parallel read-only passes, review gates, and recovery handoffs.
 - [wf-readme](../.claude/skills/wf-readme/SKILL.md) - README preservation, append-only development sections, structured tables, and approved architecture diagrams.
-- [wf-review](../.claude/skills/wf-review/SKILL.md) - cross-model peer review: invoke the other agent CLI (Codex/Claude) for independent review.
+- [wf-review](../.claude/skills/wf-review/SKILL.md) - peer review: prefer another agent CLI (Claude/Codex/OpenCode); otherwise use the installed reviewer role as an independent subagent context. Controller decides.
 - [wf-update](../.claude/skills/wf-update/SKILL.md) - GitHub-based incremental harness update, checksum comparison, and safe in-place updates.
 - [wf-learn](../.claude/skills/wf-learn/SKILL.md) - force memory learning cycle: context-master -> memory-master -> project + global memory.
-- [wf-max](../.claude/skills/wf-max/SKILL.md) - WF kernel + maximum safe fan-out: WF-Max-Useful by default (fan out only where independent), WF-Max-Strict only on explicit strict request; current runtime subagents first, cross-CLI overflow when available.
+- [wf-max](../.claude/skills/wf-max/SKILL.md) - WF kernel + maximum safe fan-out: WF-Max-Useful by default (fan out only where independent), WF-Max-Strict only on explicit strict request; current runtime subagents first, peer-CLI overflow when available.
 - [wf-auto](../.claude/skills/wf-auto/SKILL.md) - perpetual adaptive auto-optimization: evidence-selected probes, dynamic obligations, intent checkpoints, evidence ledger.
 - [wf-auto-spark](../.claude/skills/wf-auto-spark/SKILL.md) - perpetual inspiration mode: external spark search, long-term roadmap with staged milestones, <=50% deviation guard.
 - [tdd](../.claude/skills/tdd/SKILL.md) - acceptance-driven TDD: AC-linked RED tests, real UI clicks for browser-visible behavior, Playwright/CDP evidence, and configured coverage gate.

package/templates/common/Harness/README.md

@@ -104,7 +104,7 @@ Routing priority: **direct mode is the default** when no explicit WF token is pr
 | Need perpetual auto-optimization | /wf-auto, $wf-auto, /skills wf-auto (explicit user token only) | [WF-AUTO.md](WF-AUTO.md), [WF-AUTO-ANGLES.md](WF-AUTO-ANGLES.md), [subagents.md](subagents.md), [dispatch.md](dispatch.md) | perpetual loop, adaptive probe selection, dynamic risk obligations, spark search, intent checkpoint, evidence ledger; CEO never writes code |
 | Need perpetual inspiration mode | /wf-auto-spark, $wf-auto-spark, /skills wf-auto-spark (explicit user token only) | [WF-AUTO-SPARK.md](WF-AUTO-SPARK.md), [WF-AUTO.md](WF-AUTO.md), [subagents.md](subagents.md), [dispatch.md](dispatch.md) | roadmap-anchored: North Star + milestones; external spark search; <=50% deviation guard; never auto-stops |
 | Need WF-MAX mode (explicit only) | /wf-max, $wf-max, /skills wf-max (explicit user token only) | [WF-MAX.md](WF-MAX.md), [WF-KERNEL.md](WF-KERNEL.md), [subagents.md](subagents.md), [dispatch.md](dispatch.md) | /wf kernel + max safe fan-out (WF-Max-Useful default, WF-Max-Strict override) |
-| Need peer review | /wf-review, $wf-review, peer review, second opinion, cross-check, stuck | `.claude/skills/wf-review/SKILL.md`, `.agents/skills/wf-review/SKILL.md`, `Harness/README.md` | cross-model multi-dimension review with severity classification |
+| Need peer review | /wf-review, $wf-review, peer review, second opinion, cross-check, stuck | `.claude/skills/wf-review/SKILL.md`, `.agents/skills/wf-review/SKILL.md`, `Harness/README.md`, `.opencode/commands/wf-review.md` | peer CLI when available; otherwise installed `reviewer` role subagent; controller decides |
 | Adding harness to existing project | existing project, onboarding, migrate, bootstrap, preserve, conflict | [extension.md](extension.md), [PROGRESS.md](PROGRESS.md), root `README.md` and package/CI files | discovered project facts, preserved config, manual registration plan |
 | README optimization | README, docs, quickstart, install docs, architecture diagram, command table, documentation polish | root `README.md`, `.claude/skills/wf-readme/SKILL.md`, [PROGRESS.md](PROGRESS.md), [architecture.md](architecture.md) as needed | approved README mode, preserved sections, proposed diff plan |
 | Need implementation plan | plan, task, write set, verify, milestone, progress | [PROGRESS.md](PROGRESS.md), the current task `tasks/<id>/PROGRESS.md` and `tasks/<id>/PLAN.md`, [agent-workflow.md](agent-workflow.md), [ACCEPTANCE_PROTOCOL.md](ACCEPTANCE_PROTOCOL.md) | tasks, AC IDs, write set, verification commands |
@@ -124,7 +124,7 @@ Routing priority: **direct mode is the default** when no explicit WF token is pr
 - Use `/wf <task>` in Claude Code or `$wf` in Codex, or `/wf-max [task]` / `$wf-max` for maximum-parallelism mode. WF mode is explicit only. WF-Light for low-risk, WF-Standard for multi-file, WF-Full for high-risk/cross-layer. `/wf-max` defaults to useful-fanout (WF-Max-Useful); use explicit `--strict` or "strict wf-max" for unconditional fan-out (WF-Max-Strict).
 - Use `/wf-auto` for perpetual self-directed optimization. It selects probes from project evidence and stops only after dynamic risk obligations and two different empty confirmation passes are recorded.
 - **WF-MAX Role Contract**: Three-layer architecture: global mode (`wf-max`), agent role (`ceo|manager|worker|verifier|reviewer|reflector`), dispatch permission (`writeSet`, `forbidden`, `verification`). CEO never writes source code. Workers edit only dispatch.writeSet. Compliance is checked through dispatch packets, independent review, validation evidence, and task capsules. See `CLAUDE.md#1a`.
-- **WF-REVIEW Anti-Self-Review**: Must invoke the OTHER CLI (Codex -> Claude, or Claude -> Codex). Same-model simulation is forbidden.
+- **WF-REVIEW Independence**: Prefer a peer CLI (`claude`, `codex`, or `opencode`) that is not the current runtime. If none exists, dispatch the installed `reviewer` role as a separate subagent context. Same-runtime fallback is independent-context review, not cross-model review; the main agent owns final decisions.
 - WF-MAX has no runtime hook state. The durable state is the task capsule, dispatch table, review findings, and validation evidence. The only runtime hook exception in Harness is the optional `/wf-auto` bounded tick hook described in `WF-AUTO.md`.
 - Do not code before PRD-GATE, AC-GATE, CONTRACT-GATE, and TEST-GATE are satisfied or explicitly compressed into a documented fast lane.
 - PRD-derived Acceptance Criteria are the source of truth. Code, tests, reviews, validation, debug, and memory must trace to AC IDs.
@@ -176,7 +176,7 @@ Routing priority: **direct mode is the default** when no explicit WF token is pr
 | `/wf-max [task]` | `$wf-max [task]` | WF-Max-Useful default (fan-out only where independent), WF-Max-Strict override (unconditional fan-out) |
 | `/wf-auto` | `$wf-auto` | Perpetual adaptive auto-optimization: dynamic probes, risk obligations, evidence-based exhaustion |
 | `/wf-auto-spark` | `$wf-auto-spark` | Perpetual inspiration: spark search, roadmap-anchored, <=50% deviation guard, never auto-stops |
-| `/wf-review [focus]` | `$wf-review [focus]` | Cross-model peer review via Codex <-> Claude |
+| `/wf-review [focus]` | `$wf-review [focus]` | Peer CLI review via Claude/Codex/OpenCode, or installed reviewer subagent fallback |
 | `/wf-learn` | `$wf-learn` | Force learning cycle: context-master -> memory-master |
 | `/wf-browser [task]` | `$wf-browser [task]` | AI-driven browser automation for E2E testing |
 | `/wf-readme [task]` | `$wf-readme [task]` | README preservation, merge, and documentation improvement workflow |

package/templates/common/Harness/WF-AUTO-ANGLES.md

@@ -132,7 +132,7 @@ The A-GATE is evidence-based:
 5. the CEO records unresolved uncertainty, skipped probes, and why oracle or
    spark search was or was not needed.
 
-The cross-model oracle is triggered by unresolved high-risk uncertainty or a
+The peer-review oracle is triggered by unresolved high-risk uncertainty or a
 borderline exhaustion result. Spark search is triggered by a genuine value gap,
 not merely because a catalog was empty. This prevents both premature stopping
 and pointless full-tree scanning.

package/templates/common/Harness/WF-AUTO.md

@@ -205,7 +205,7 @@ TIER 2 — Did any selected probe find an actionable direction?
   └── NO → Run a confirmation pass with a different scan strategy.
 
 TIER 3 — Is uncertainty still high or coverage borderline?
-  ├── YES → Re-run only the uncertain probe, or invoke the cross-model oracle.
+  ├── YES → Re-run only the uncertain probe, or invoke the peer-review oracle.
   └── NO → Record an empty confirmation pass.
 
 TIER 4 — Two different confirmation strategies are empty?
@@ -215,9 +215,10 @@ TIER 4 — Two different confirmation strategies are empty?
 
 **Oracle Rules (modeled on /wf-review):**
 
-- [ ] CEO detects which CLI is running: `which codex` / `which claude`
-- [ ] CEO invokes the OTHER CLI only when unresolved high-risk uncertainty or borderline coverage justifies it
-- [ ] If neither CLI is available, record "oracle unavailable" in PROGRESS.md and continue with local confirmation
+- [ ] CEO detects available peer CLIs: `claude`, `codex`, and `opencode`
+- [ ] CEO invokes a peer CLI only when unresolved high-risk uncertainty or borderline coverage justifies it
+- [ ] If no peer CLI is available, dispatch the installed `reviewer` role as an independent subagent context
+- [ ] If neither peer CLI nor subagent surface is available, record "oracle unavailable" in PROGRESS.md and continue with local confirmation
 - [ ] Oracle is invoked at most once per adaptive exhaustion event
 - [ ] Oracle findings are treated as severity=high by default (external model perspective gets extra weight)
 
@@ -360,7 +361,7 @@ CEO presents:
 
 ### Spark: External Candidate Provider
 
-Spark is NOT a separate optimization engine. It is a **candidate provider** plugged into W0, alongside the adaptive probe scan and the cross-model oracle. W1 still owns prioritization across ALL sources.
+Spark is NOT a separate optimization engine. It is a **candidate provider** plugged into W0, alongside the adaptive probe scan and the peer-review oracle. W1 still owns prioritization across ALL sources.
 
 **When spark activates:**
 - W0 internal scan returns empty AND oracle also empty → `auto.spark` state
@@ -398,7 +399,7 @@ Spark is NOT a separate optimization engine. It is a **candidate provider** plug
 
 W1 prioritization now handles three source types:
 - `source=internal` — from adaptive probe scan
-- `source=oracle` — from cross-model review
+- `source=oracle` — from peer CLI or reviewer-subagent review
 - `source=spark-<name>` — from external inspiration search
 
 Tie-breaking: internal > oracle > spark (local context beats external inspiration).
@@ -490,14 +491,14 @@ Mini PRD-derived AC IDs in `/wf-auto`.
 |-----------|-----|---------|----------|
 | Scope | Task-bounded | Task-bounded | Unbounded |
 | Stop condition | Task complete | Task complete | Dynamic obligations covered + two different empty confirmation passes |
-| Direction | User-specified | User-specified | AI-inferred + cross-model oracle + external spark |
+| Direction | User-specified | User-specified | AI-inferred + peer-review oracle + external spark |
 | Organization | Flat (CEO + agents) | 3-tier (CEO→Mgr→Worker) | Flat (CEO + selected probes + oracle + spark searchers + build agents) |
 | Duration | One task | One task | Perpetual |
 | User interaction | At key gates | At key gates | Adaptive checkpoint (2→5→10 cycles), 2 questions only |
 | Cycle count | 1 | 1 (multi-wave) | ∞ (until exhaustion) |
 | Files/cycle | Per task | Per wave (many) | ≤3 per cycle |
 | Exploration | 3-5 agents once | 5-10 agents once | Dynamic probes + triggered spark sources per cycle |
-| Cross-model check | No (wf-review is separate) | No (wf-review is separate) | Yes — Cross-Model Oracle built into A-GATE Tier 1.5 |
+| Peer review check | No (wf-review is separate) | No (wf-review is separate) | Yes — peer-review oracle built into A-GATE Tier 1.5 |
 | External inspiration | No | No | Yes — Spark candidate provider when internal sources empty |
 | Evidence tracking | Per task | Per task | Evidence ledger per cycle with measured impact |
 

package/templates/common/Harness/WF-MAX.md

@@ -80,7 +80,7 @@ D-GATE is mandatory before implementation waves per [WF-KERNEL.md](WF-KERNEL.md)
 
 1. Current runtime subagents first.
 2. Close completed agents; fill idle slots immediately.
-3. Cross-CLI overflow: Codex → `claude -p`, Claude → `codex exec`.
+3. Cross-CLI overflow: use an available peer CLI with explicit dispatch packets: `claude -p`, `codex exec`, or `opencode run --agent <role> --dir .`.
 4. Bounded-pass fallback only when subagents and overflow are exhausted.
 5. Generated Codex config defaults to `agents.max_threads = 12` and `agents.max_depth = 1`. Ask the user before raising `agents.max_threads` above that default. Keep `max_depth = 1` unless recursive delegation is explicitly approved.
 6. Do not rely on Codex++, undocumented config, environment variables, forked/derived conversations, or third-party forks as stable capacity.

package/templates/common/Harness/dispatch.md

@@ -13,7 +13,7 @@ Use when work needs parallel reading, independent review, cross-layer analysis,
 - Important assumptions, decisions, blockers, evidence, and handoffs must be written to `Harness/tasks/<task-id>/PROGRESS.md` and `Harness/tasks/<task-id>/PLAN.md`, the current feature doc, `Harness/MEMORY.md`, or `Harness/memory/*` as appropriate.
 - Resumable state is governed by [WF-STATE.md](WF-STATE.md). On session start, the controller reads STATE.json before building a fresh dispatch table.
 - PRD-derived Acceptance Criteria are the source of truth. Dispatch packets must carry the relevant AC IDs and contracts.
-- Agent count: default (non-WF) <=3 active agents; `/wf` selects a tier dynamically per [WF-KERNEL.md](WF-KERNEL.md) (Light/Standard/Full); `/wf-max` inherits the selected tier and adds maximum safe fan-out (WF-Max-Useful default; WF-Max-Strict explicit only), removing the Harness default cap through the span formula. Real concurrency is still bounded by runtime thread budget, config, billing, and local resources. Use current runtime subagents first, close completed agents, then cross-CLI overflow. Generated Codex config defaults to `agents.max_threads = 12` and `agents.max_depth = 1`; ask the user before raising `agents.max_threads` above that default. See [WF.md](WF.md) and [WF-MAX.md](WF-MAX.md).
+- Agent count: default (non-WF) <=3 active agents; `/wf` selects a tier dynamically per [WF-KERNEL.md](WF-KERNEL.md) (Light/Standard/Full); `/wf-max` inherits the selected tier and adds maximum safe fan-out (WF-Max-Useful default; WF-Max-Strict explicit only), removing the Harness default cap through the span formula. Real concurrency is still bounded by runtime thread budget, config, billing, and local resources. Use current runtime subagents first, close completed agents, then peer-CLI overflow (`claude -p`, `codex exec`, or `opencode run --agent <role> --dir .`). Generated Codex config defaults to `agents.max_threads = 12` and `agents.max_depth = 1`; ask the user before raising `agents.max_threads` above that default. See [WF.md](WF.md) and [WF-MAX.md](WF-MAX.md).
 - Read-only agents may run in parallel.
 - Writing agents run serially unless write sets are disjoint.
 - Use a worktree when two agents may touch overlapping files or long-running branches.

package/templates/common/Harness/scripts/scan-clean.mjs

@@ -65,6 +65,7 @@ const MANAGED_SUBDIRS = new Set([
 
 /** Reject paths that escape ROOT (traversal, absolute, .., etc.). */
 function safePath(file) {
+  if (/^[A-Za-z]:/.test(file)) return null;
   let normalized = file.replace(/\\/g, '/').replace(/^\/+/, '');
   if (/\/\//.test(normalized)) return null;
   if (normalized.split('/').some(p => p === '..')) return null;

package/templates/common/Harness/scripts/validate-harness.mjs

@@ -97,6 +97,7 @@ const required = [
   '.opencode/commands/wf-help.md',
   '.opencode/commands/wf-update.md',
   ...opencodeWorkflowCommands.map(command => `.opencode/commands/${command}.md`),
+  '.opencode/plugins/harness-wf-status.mjs',
   '.claude/rules/ecc/common.md',
   ...commonAgents.map(agent => `.claude/agents/${agent}.md`),
   ...commonAgents.map(agent => `.opencode/agents/${agent}.md`),
@@ -725,6 +726,11 @@ requireText('.claude/skills/tdd/SKILL.md', 'No syntax-only acceptance', 'tdd ski
 requireText('.claude/skills/wf-remove/SKILL.md', 'User-facing removal is the slash/skill command', 'wf-remove slash command is user-facing');
 requireText('.claude/skills/wf-remove/SKILL.md', 'agent-internal execution steps', 'wf-remove script commands are agent-internal');
 requireText('.claude/skills/wf-remove/SKILL.md', 'verify residual discovery folders', 'wf-remove residual discovery verification');
+requireText('.claude/skills/wf-review/SKILL.md', 'opencode run --agent reviewer', 'wf-review OpenCode peer CLI path');
+requireText('.claude/skills/wf-review/SKILL.md', 'Role: reviewer', 'wf-review installed reviewer role fallback');
+requireText('.claude/skills/wf-review/SKILL.md', 'The main agent is the controller', 'wf-review controller final authority');
+requireText('.opencode/commands/wf-review.md', 'peer-review contract', 'OpenCode wf-review wrapper peer-review contract');
+requireText('Harness/subagents.md', 'For `/wf-review`, use the installed `reviewer` role', 'subagents wf-review role fallback');
 requireText('.claude/agents/tdd-guide.md', 'Browser Acceptance Rules', 'tdd-guide browser acceptance rules');
 requireText('.claude/agents/tdd-guide.md', 'real user actions', 'tdd-guide real user action requirement');
 requireText('.claude/agents/test-writer.md', 'Harness/ACCEPTANCE_PROTOCOL.md', 'test-writer loads acceptance protocol');
@@ -766,6 +772,12 @@ forbidText('.claude/settings.json', 'wf-mode-hook.mjs', 'Claude WF hook command
 forbidText('.codex/hooks.json', 'wf-mode-hook.mjs', 'Codex WF hook command registration');
 const codexHookConfig = read('.codex/hooks.json');
 const claudeSettings = read('.claude/settings.json');
+requireText('.codex/hooks.json', '"SessionStart"', 'Codex startup-only update hook');
+requireText('.claude/settings.json', '"SessionStart"', 'Claude startup-only update hook');
+forbidText('.codex/hooks.json', 'UserPromptSubmit', 'Codex turn-by-turn update hook');
+forbidText('.claude/settings.json', 'UserPromptSubmit', 'Claude turn-by-turn update hook');
+requireText('.opencode/plugins/harness-wf-status.mjs', 'opencode.startup', 'OpenCode startup-only update check');
+forbidText('.opencode/plugins/harness-wf-status.mjs', "'chat.message'", 'OpenCode turn-by-turn update hook');
 if (codexHookConfig && !codexHookConfig.includes('wf-auto')) {
   errors.push('.codex/hooks.json may only exist for a wf-auto hook configuration');
 }

package/templates/common/Harness/scripts/wf-auto-update-prompt.mjs

@@ -142,7 +142,7 @@ function buildMessage(update) {
     `Harness update available: ${from} -> ${to}.`,
     `Before unrelated work, ask the user whether to run /wf-update.`,
   ];
-  // Only include summary counts — never list individual conflict files in hook output
+  // Only include summary counts; never list individual conflict files in hook output.
   if (update.conflict > 0) {
     parts.push(`${update.conflict} conflict file(s) will need agent/user merge decisions.`);
   }
@@ -174,7 +174,7 @@ function emit(message, payload = {}) {
     if (context) {
       console.log(JSON.stringify({
         hookSpecificOutput: {
-          hookEventName: input.hook_event_name || 'UserPromptSubmit',
+          hookEventName: input.hook_event_name || 'SessionStart',
           additionalContext: context,
         },
       }));

package/templates/common/Harness/scripts/wf-remove.mjs

@@ -214,6 +214,7 @@ const CLEANUP_DIRS = [
 
 /** Reject paths that escape ROOT (traversal, absolute, .., etc.). Sync with wf-update-check. */
 function safePath(file) {
+  if (/^[A-Za-z]:/.test(file)) return null;
   let normalized = file.replace(/\\/g, '/').replace(/^\/+/, '');
   if (normalized.includes('//')) return null;  // double slash bypass
   if (normalized.split('/').some(p => p === '..')) return null;

package/templates/common/Harness/scripts/wf-update-check.mjs

@@ -1,6 +1,6 @@
 #!/usr/bin/env node
 /**
- * wf-update-check.mjs — Fast harness update comparison.
+ * wf-update-check.mjs - Fast harness update comparison.
  * Fetches remote checksums, compares locally, classifies all files instantly.
  * Only CONFLICT files need AI/user decision.
  *
@@ -23,9 +23,13 @@ import { fileURLToPath } from 'url';
 const __dirname = dirname(fileURLToPath(import.meta.url));
 const ROOT = process.env.WF_ROOT ? resolve(process.env.WF_ROOT) : resolve(__dirname, '..', '..');
 const VERSION_FILE = resolve(ROOT, 'Harness', '.harness-version');
-const DEFAULT_SOURCE_BASE = 'https://raw.githubusercontent.com/zingspark/create-harness-vibe-coding/main/templates/common/';
+const GITHUB_REPO = 'zingspark/create-harness-vibe-coding';
+const GITHUB_LATEST_STABLE = `https://api.github.com/repos/${GITHUB_REPO}/releases/latest`;
+const RAW_GITHUB = `https://raw.githubusercontent.com/${GITHUB_REPO}`;
+const TEMPLATE_SUBPATH = 'templates/common/';
+const DEFAULT_SOURCE_BASE = `${RAW_GITHUB}/main/${TEMPLATE_SUBPATH}`;
 
-// ── Tier classification ──────────────────────────────────────────
+// Tier classification
 
 /** Files we NEVER overwrite or delete. */
 const PRESERVE_PATTERNS = [
@@ -56,10 +60,15 @@ const OPTIONAL_REGISTRATION_FILES = new Set([
   'Harness/README.md',
 ]);
 
-// ── Helpers ────────────────────────────────────────────────────────
+const BOOTSTRAP_ONLY_FILES = new Set([
+  'Harness/SETUP.md',
+]);
+
+// Helpers
 
 /** Reject paths that escape ROOT (traversal, absolute, .., etc.). */
 function safePath(file) {
+  if (/^[A-Za-z]:/.test(file)) return null;
   let normalized = file.replace(/\\/g, '/').replace(/^\/+/, '');
   if (/\/\//.test(normalized)) return null;
   if (normalized.split('/').some(p => p === '..')) return null;
@@ -136,7 +145,7 @@ function sha256(content) {
 function sha256File(path) {
   if (!existsSync(path)) return null;
   let content = readFileSync(path, 'utf-8');
-  // Normalize CRLF → LF
+  // Normalize CRLF to LF.
   content = content.replace(/\r\n/g, '\n');
   return sha256(content);
 }
@@ -146,16 +155,18 @@ function classify(file, localHash, storedHash) {
   for (const p of PRESERVE_PATTERNS) {
     if (p.test(file)) return 'PRESERVE';
   }
-  // MERGE — dual-purpose, check if user modified
+  // MERGE: dual-purpose, check if user modified.
   for (const p of MERGE_PATTERNS) {
     if (p.test(file)) {
       if (localHash === storedHash) return 'SAFE'; // unmodified, safe
       return 'CONFLICT'; // user modified, needs decision
     }
   }
-  // Everything else is SAFE runtime file
-  if (localHash === storedHash || localHash === null) return 'SAFE';
-  return 'CONFLICT'; // modified runtime file — unexpected
+  // Everything else is SAFE runtime file: always overwrite.
+  // Harness system files (scripts, skills, agents, commands, WF docs) are
+  // not user data; the template is authoritative. Only PRESERVE and MERGE
+  // files should ever require conflict resolution.
+  return 'SAFE';
 }
 
 async function fetchRemote(url, timeoutMs = 30000) {
@@ -174,7 +185,49 @@ async function fetchRemote(url, timeoutMs = 30000) {
   }
 }
 
-// ── Main ───────────────────────────────────────────────────────────
+// Main
+
+function isPrerelease(v) {
+  if (!v || typeof v !== 'string') return false;
+  return /-[0-9A-Za-z.-]+/.test(v.replace(/^[^0-9]*/, ''));
+}
+
+async function resolveStableSourceBase() {
+  try {
+    const controller = new AbortController();
+    const timer = setTimeout(() => controller.abort(), 15000);
+    let res;
+    try {
+      res = await fetch(GITHUB_LATEST_STABLE, {
+        signal: controller.signal,
+        headers: { Accept: 'application/vnd.github+json', 'User-Agent': 'harness-wf-update-check' },
+      });
+    } finally {
+      clearTimeout(timer);
+    }
+    if (!res.ok) throw new Error(`HTTP ${res.status}`);
+    const data = JSON.parse(await res.text());
+    const tag = data && data.tag_name;
+    if (!tag || data.prerelease) return null;
+    const source = `${RAW_GITHUB}/${tag}/${TEMPLATE_SUBPATH}`;
+    const versionController = new AbortController();
+    const versionTimer = setTimeout(() => versionController.abort(), 15000);
+    try {
+      const versionRes = await fetch(source + '.harness-version', {
+        signal: versionController.signal,
+        headers: { 'User-Agent': 'harness-wf-update-check' },
+      });
+      if (!versionRes.ok) return null;
+      const raw = await versionRes.text();
+      if (isTemplate(raw)) return null;
+    } finally {
+      clearTimeout(versionTimer);
+    }
+    return source;
+  } catch {
+    return null;
+  }
+}
 
 async function main() {
   const args = process.argv.slice(2);
@@ -186,7 +239,16 @@ async function main() {
   const acceptMerged = readRepeatedFlagValues(args, '--accept-merged');
   const acceptTemplate = readRepeatedFlagValues(args, '--accept-template');
   const ignoreVersion = args.includes('--ignore-version') || args.includes('--force-check');
-  const sourceBase = normalizeSourceBase(readFlagValue(args, '--source-base') || process.env.WF_SOURCE_BASE || DEFAULT_SOURCE_BASE);
+  const explicitSource = readFlagValue(args, '--source-base') || process.env.WF_SOURCE_BASE;
+  let sourceBase = normalizeSourceBase(explicitSource || DEFAULT_SOURCE_BASE);
+  let stableTagResolved = false;
+  if (!explicitSource) {
+    const resolved = await resolveStableSourceBase();
+    if (resolved) {
+      sourceBase = normalizeSourceBase(resolved);
+      stableTagResolved = true;
+    }
+  }
 
   // 1. Read local state
   if (!existsSync(VERSION_FILE)) {
@@ -248,9 +310,9 @@ async function main() {
       if (jsonOut) {
         console.log(JSON.stringify({ status: 'template-remote', message: 'Remote .harness-version has not been generated yet.' }));
       } else {
-        console.log('⚠ Remote .harness-version is a template (contains {{placeholders}}).');
+        console.log('WARN: Remote .harness-version is a template (contains {{placeholders}}).');
         console.log('  The generate step has not been run on the remote repo. No update possible.');
-        console.log('  This is expected during development — the update mechanism works once the remote is live.');
+        console.log('  This is expected during development; the update mechanism works once the remote is live.');
       }
       process.exitCode = 1;
       return;
@@ -267,10 +329,10 @@ async function main() {
     return;
   }
 
-  // Compare versions — warn if remote is older (downgrade prevention)
+  // Compare versions and prevent downgrades from explicit custom sources.
   function parseSemver(v) {
     if (!v || typeof v !== 'string') return [0, 0, 0];
-    return v.replace(/^[^0-9]*/, '').split('-')[0].split('.').map(Number);
+    return v.replace(/^[^0-9]*/, '').split('.').slice(0, 3).map(n => Number(n) || 0);
   }
   function cmpSemver(a, b) {
     const va = parseSemver(a), vb = parseSemver(b);
@@ -280,27 +342,38 @@ async function main() {
 
   const localGen = localVersion.generator || '0.0.0';
   const remoteGen = remoteVersion.generator || '0.0.0';
+
+  if (!ignoreVersion && isPrerelease(remoteGen)) {
+    if (jsonOut) {
+      console.log(JSON.stringify({ status: 'up-to-date', version: localGen, remote: remoteGen, sourceBase }));
+    } else {
+      console.log(`Already up to date (v${localGen}). Remote ${remoteGen} is a prerelease and is ignored.`);
+    }
+    return;
+  }
+
   const versionCmp = cmpSemver(remoteGen, localGen);
 
   if (!ignoreVersion && versionCmp <= 0) {
+    const reportDowngrade = !stableTagResolved;
     if (jsonOut) {
       console.log(JSON.stringify({
-        status: versionCmp < 0 ? 'downgrade-refused' : 'up-to-date',
+        status: (versionCmp < 0 && reportDowngrade) ? 'downgrade-refused' : 'up-to-date',
         version: localGen,
         remote: remoteGen,
         sourceBase,
       }));
-    } else if (versionCmp < 0) {
-      console.log(`⚠ Remote (v${remoteGen}) is OLDER than local (v${localGen}). Downgrade refused.`);
+    } else if (versionCmp < 0 && reportDowngrade) {
+      console.log(`WARN: Remote (v${remoteGen}) is OLDER than local (v${localGen}). Downgrade refused.`);
     } else {
-      console.log(`✅ Already up to date (v${localGen})`);
+      console.log(`Already up to date (v${localGen})`);
     }
-    if (versionCmp < 0) process.exitCode = 1;
+    if (versionCmp < 0 && reportDowngrade) process.exitCode = 1;
     return;
   }
 
   if (ignoreVersion) {
-    if (!jsonOut) console.log('🔧 Version check bypassed (--ignore-version). Comparing files anyway.');
+    if (!jsonOut) console.log('Version check bypassed (--ignore-version). Comparing files anyway.');
   }
 
   const remoteChecksums = remoteVersion.checksums || {};
@@ -469,8 +542,13 @@ async function main() {
       continue;
     }
 
+    if (BOOTSTRAP_ONLY_FILES.has(canonical) && localHash === null) {
+      plan.skipped.push({ file, reason: 'bootstrap-only file already removed locally' });
+      continue;
+    }
+
     if (!storedHash) {
-      // New file from remote — if local file exists, it's a CONFLICT
+      // New file from remote: if local file exists, it is a CONFLICT.
       if (localHash) {
         if (localHash === remoteHash) {
           plan.adopted.push({ file, localHash, remoteHash, reason: 'new remote file already matches local file' });
@@ -483,10 +561,10 @@ async function main() {
         plan.conflict.push({ file, localHash, storedHash: 'none', remoteHash, reason: 'new remote file conflicts with existing local file' });
         continue;
       }
-      // New file — still respect PRESERVE classification
+      // New file: still respect PRESERVE classification.
       const tier = classify(canonical, null, null);
       if (tier === 'PRESERVE') {
-        plan.skipped.push({ file, reason: 'PRESERVE — new file would overwrite user data' });
+        plan.skipped.push({ file, reason: 'PRESERVE: new file would overwrite user data' });
       } else {
         plan.created.push({ file, remoteHash });
       }
@@ -517,7 +595,7 @@ async function main() {
     const tier = classify(canonical, localHash, storedHash);
 
     if (tier === 'PRESERVE') {
-      plan.skipped.push({ file, reason: 'PRESERVE — user data' });
+      plan.skipped.push({ file, reason: 'PRESERVE: user data' });
     } else if (tier === 'SAFE') {
       if (localHash === remoteHash) {
         plan.skipped.push({ file, reason: 'already current' });
@@ -564,14 +642,14 @@ async function main() {
     return;
   }
 
-  console.log(`\n🔄 Update: v${localGen} → v${remoteGen}`);
+  console.log(`\nUpdate: v${localGen} -> v${remoteGen}`);
   console.log(`   ${plan.updated.length} safe update, ${plan.created.length} new, ${plan.conflict.length} conflict, ${plan.skipped.length} skipped\n`);
 
   // Show conflicts (these need AI/user decision)
   if (plan.conflict.length > 0) {
-    console.log('⚠ CONFLICTS (need your decision):');
+    console.log('CONFLICTS (need your decision):');
     for (const c of plan.conflict) {
-      console.log(`   📄 ${c.file}  [${c.reason}]`);
+      console.log(`   ! ${c.file}  [${c.reason}]`);
     }
     if (plan.updated.length + plan.created.length > 0) {
       console.log('   Tip: run --apply-safe to apply SAFE/NEW files first, then merge conflicts.');
@@ -581,17 +659,17 @@ async function main() {
 
   // Show what will be auto-updated
   if (plan.updated.length + plan.created.length > 0) {
-    console.log('✅ AUTO (safe to apply):');
-    for (const u of plan.updated) console.log(`   ↑ ${u.file}`);
+    console.log('AUTO (safe to apply):');
+    for (const u of plan.updated) console.log(`   ^ ${u.file}`);
     for (const c of plan.created) console.log(`   + ${c.file}`);
     console.log('');
   }
 
   // 4. Apply if requested
   if (apply || applySafe) {
-    // Refuse to apply when conflicts exist — must resolve first
+    // Refuse to apply when conflicts exist; must resolve first.
     if (apply && !applySafe && plan.conflict.length > 0) {
-      console.log(`❌ Cannot apply: ${plan.conflict.length} conflicts must be resolved first.`);
+      console.log(`Cannot apply: ${plan.conflict.length} conflicts must be resolved first.`);
       console.log('   Run --apply-safe to apply SAFE/NEW files first, or resolve conflicts manually then re-run --apply.');
       process.exitCode = 1;
       return plan;
@@ -607,23 +685,23 @@ async function main() {
     for (const u of plan.updated) {
       try {
         const dest = safePath(u.file);
-        if (!dest) { console.error(`   ✗ Traversal rejected: ${u.file}`); failed++; continue; }
-        // Symlink rejection — don't follow symlinks
+        if (!dest) { console.error(`   x Traversal rejected: ${u.file}`); failed++; continue; }
+        // Symlink rejection: do not follow symlinks.
         if (lexists(dest)) {
-          try { if (lstatSync(dest).isSymbolicLink()) { console.error(`   ✗ Symlink rejected: ${u.file}`); failed++; continue; } } catch (_) {}
+          try { if (lstatSync(dest).isSymbolicLink()) { console.error(`   x Symlink rejected: ${u.file}`); failed++; continue; } } catch (_) {}
         }
         const content = await fetchRemote(sourceBase + remotePath(u.file));
         const normalized = content.replace(/\r\n/g, '\n');
         const fetchedHash = sha256(normalized);
         if (fetchedHash !== u.remoteHash) {
-          console.error(`   ✗ Hash mismatch: ${u.file}`);
+          console.error(`   x Hash mismatch: ${u.file}`);
           failed++; continue;
         }
         mkdirSync(dirname(dest), { recursive: true });
         writeFileSync(dest, normalized, 'utf-8');
         applied++;
       } catch (e) {
-        console.error(`   ✗ Failed: ${u.file} — ${e.message}`);
+        console.error(`   x Failed: ${u.file} - ${e.message}`);
         failed++;
       }
     }
@@ -631,25 +709,25 @@ async function main() {
     for (const c of plan.created) {
       try {
         const dest = safePath(c.file);
-        if (!dest) { console.error(`   ✗ Traversal rejected: ${c.file}`); failed++; continue; }
+        if (!dest) { console.error(`   x Traversal rejected: ${c.file}`); failed++; continue; }
         // TOCTOU: recheck file didn't appear since planning
         if (lexists(dest)) {
-          try { if (lstatSync(dest).isSymbolicLink()) { console.error(`   ✗ Symlink rejected: ${c.file}`); failed++; continue; } } catch (_) {}
-          console.error(`   ✗ File created since plan: ${c.file} — treating as CONFLICT`);
+          try { if (lstatSync(dest).isSymbolicLink()) { console.error(`   x Symlink rejected: ${c.file}`); failed++; continue; } } catch (_) {}
+          console.error(`   x File created since plan: ${c.file} - treating as CONFLICT`);
           failed++; continue;
         }
         const content = await fetchRemote(sourceBase + remotePath(c.file));
         const normalized = content.replace(/\r\n/g, '\n');
         const fetchedHash = sha256(normalized);
         if (fetchedHash !== c.remoteHash) {
-          console.error(`   ✗ Hash mismatch: ${c.file}`);
+          console.error(`   x Hash mismatch: ${c.file}`);
           failed++; continue;
         }
         mkdirSync(dirname(dest), { recursive: true });
         writeFileSync(dest, normalized, 'utf-8');
         applied++;
       } catch (e) {
-        console.error(`   ✗ Failed: ${c.file} — ${e.message}`);
+        console.error(`   x Failed: ${c.file} - ${e.message}`);
         failed++;
       }
     }
@@ -676,12 +754,12 @@ async function main() {
       }
       writeFileSync(VERSION_FILE, JSON.stringify(localVersion, null, 2) + '\n', 'utf-8');
       if (plan.conflict.length === 0) {
-        console.log(`✅ Applied ${applied} files. Version updated to ${remoteVersion.generator}.`);
+        console.log(`Applied ${applied} files. Version updated to ${remoteVersion.generator}.`);
       } else {
-        console.log(`✅ Applied ${applied} SAFE/NEW files. Version remains ${localGen}; ${plan.conflict.length} conflicts still need merge.`);
+        console.log(`Applied ${applied} SAFE/NEW files. Version remains ${localGen}; ${plan.conflict.length} conflicts still need merge.`);
       }
     } else {
-      console.log(`❌ ${failed} failures. NO files were version-tracked. Fix and re-run.`);
+      console.log(`${failed} failures. NO files were version-tracked. Fix and re-run.`);
       process.exitCode = 1;
     }
   }

package/templates/common/Harness/subagents.md

@@ -124,7 +124,7 @@ Choose the cheapest coordination level that is safe.
 Max parallelism removes the Harness default cap, not the runtime's physical or
 account cap. For WF-MAX, record the current runtime budget, use native
 subagents first, close completed agents before declaring the pool exhausted,
-then overflow to the other CLI (`claude -p` or `codex exec`) with explicit
+then overflow to a peer CLI (`claude -p`, `codex exec`, or `opencode run --agent <role> --dir .`) with explicit
 dispatch packets. Generated Harness Codex config defaults to
 `agents.max_threads = 12` and `agents.max_depth = 1`; if that becomes the
 bottleneck, ask the user before raising `agents.max_threads` and keep
@@ -192,6 +192,13 @@ matrix from running behavior and evidence, not from the implementer's summary.
 
 If either reviewer finds issues, the implementer or debugger fixes them and the same gate runs again. Do not move to final acceptance with open critical/high findings or without reflector PASS.
 
+For `/wf-review`, use the installed `reviewer` role before inventing any
+ad hoc review prompt. If no peer CLI is available, dispatch `reviewer` as an
+independent same-runtime subagent context; for broad WF-MAX review, dispatch
+`review-manager` when the runtime supports nested reviewer fan-out. Reviewer
+agents report suggestions only. The controller accepts, rejects, or escalates
+each finding and owns the final decision.
+
 ## Subagent Status Handling
 
 | Status | Controller Action |

package/templates/common/README.md

@@ -45,4 +45,4 @@ The agentic engineering harness lives in `Harness/`.
 Tool discovery files stay at the repository root:
 
 - Claude Code: `.claude/settings.json`, `.claude/agents/`, and `.claude/skills/`.
-- Codex: `.agents/skills/` for repo skills and `.codex/` for config placeholders. Runtime hooks are absent by default; only `/wf-auto` may opt into a bounded tick hook.
+- Codex: `.agents/skills/` for repo skills and `.codex/` for config placeholders. The bundled update reminder uses a startup-only hook; avoid turn-by-turn runtime hooks unless `/wf-auto` explicitly opts into a bounded tick hook.