@mstar-harness/opencode 2.0.4 → 2.0.6

package/CHANGELOG.md

@@ -6,6 +6,27 @@ The monorepo root [CHANGELOG.md](../../CHANGELOG.md) summarizes cross-surface re
 
 ## [Unreleased]
 
+## [2.0.6] - 2026-08-10
+
+### Harness
+
+- Added a **host-agnostic full-flow goal rule** in `mstar-host`: any host exposing a `/goal` command (Codex Goal Mode, omp, future code agents) must set the goal to running the **complete flow to its end** — whether advancing an iteration (start → per-plan cycles → close → PR delivery → merge-ready loop) or non-iteration work (specify → clarify → plan → tasks → implement → plan QC tri + QA gate → Done) — never a sub-stage goal.
+- Removed the Codex-specific `references/codex-plan-goal-mode-bridge.md`; goal text rules now live host-agnostically in `mstar-host` SKILL.md, and Codex Plan Mode reads `references/_shared/plan-mode-bridge-core.md` directly.
+
+- Version alignment with harness **2.0.6** (no OpenCode package API change).
+
+See root [CHANGELOG.md](../../CHANGELOG.md) **2.0.6**.
+
+## [2.0.5] - 2026-08-10
+
+### Harness
+
+- `/iteration-start`: accepts an optional `direction` hint (constrains §2 candidates, seeds §3 grill-me — start stays interactive) and a `pause` flag; auto-continues into Phase 2→5 (execute → close → PR → merge-ready) after Phase 1 lock + integration branch, by default. `/iteration-drive` remains standalone for re-entry/resume on an already-locked iteration. Updated `iteration-loop` vs-commands table, README/README_CN command tables + workflow diagrams, OpenCode package quick start; added routing eval `iteration-start-auto-continue-phase2`.
+
+- Version alignment with harness **2.0.5** (no OpenCode package API change).
+
+See root [CHANGELOG.md](../../CHANGELOG.md) **2.0.5**.
+
 ## [2.0.4] - 2026-08-09
 
 ### Bundled harness skills (`harness-skills/` at publish)

package/README.md

@@ -46,7 +46,7 @@ The plugin registers a non-blocking `tool.execute.before` lint for the `task` to
 
 1. Install the plugin (above).
 2. In OpenCode, start with the **Project Manager** agent (`project-manager`).
-3. For a full iteration: run **`/iteration-start`** then **`/iteration-drive`**, or one-shot **`/iteration-loop`** (autonomous Phase 1→5).
+3. For a full iteration: run **`/iteration-start`** (Phase 1 grill-me → auto-continues Phase 2→5; add `pause` to stop after Phase 1), or one-shot **`/iteration-loop`** (autonomous Phase 1→5). Use **`/iteration-drive`** to resume an interrupted iteration.
 
 Entry skill: **`mstar-harness-core`** (loaded before other `mstar-*` skills).
 

package/harness-commands/iteration-loop.md

@@ -11,9 +11,8 @@ Run a **full** Morning Star iteration with minimal human intervention. **Done =
 **vs other commands:**
 
 | Command | Scope |
-|---------|--------|
-| `iteration-start` | Phase 1 only; **grill-me** with user |
-| `iteration-drive` | Phase 2→5 on an already locked iteration |
+| `iteration-start` | Phase 1 (**grill-me** with user) → **auto-continue** Phase 2→5（`pause` 止于 Phase 1） |
+| `iteration-drive` | Phase 2→5 re-entry / resume on an already locked iteration |
 | **`iteration-loop`** | Phase 1→5 end-to-end; **autonomous** direction lock |
 
 Phase gate SSOT → **`mstar-iteration`** §1–§5. This command is a **consumer**; it does not redefine skill semantics.

package/harness-commands/iteration-start.md

@@ -1,12 +1,25 @@
 ---
 name: iteration-start
-description: Start a new harness iteration — research, grill-me, compass/plans, Review & Edit chain (long-lived {SPECS_DIR}/ + {ITERATION_DIR}/<id>/ package; compound promotes package at close only), PM lock, integration branch.
+description: "Start a new harness iteration — optional direction hint, research, grill-me, compass/plans, Review & Edit chain (long-lived {SPECS_DIR}/ + {ITERATION_DIR}/<id>/ package; compound promotes package at close only), PM lock, integration branch; then auto-continue Phase 2→5 (execute → close → PR → merge-ready) unless `pause` arg given."
 agent: project-manager
 ---
 
 # Start Iteration
 
-Start a new Morning Star harness iteration. **Not Done until the Review & Edit chain runs via dispatched roles and PM lock — not when compass files are first written.**
+Start a new Morning Star harness iteration. **Phase 1 is not complete until the Review & Edit chain runs via dispatched roles and PM lock — not when compass files are first written.** By default, after Phase 1 lock + integration branch, **auto-continue into Phase 2→5** (execute → close → PR → merge-ready); pass **`pause`** to stop after Phase 1 and resume later with `/iteration-drive`.
+
+## Args
+
+```text
+/iteration-start [direction] [pause]
+```
+
+| Arg | Meaning | Default |
+|-----|---------|---------|
+| `direction` | Iteration direction hint — constrains §2 candidates and seeds §3 grill-me; **not** a lock (start stays interactive) | Research → grill-me converges with user |
+| `pause` | Stop after Phase 1 (lock + integration branch); run `/iteration-drive` later to resume | **Auto-continue** into Phase 2→5 |
+
+**Parse**: if any token is exactly `pause` (case-insensitive), treat as the `pause` flag; the remaining tokens (joined) are the `direction` hint. `/iteration-start pause` = pause with empty direction.
 
 ## PM invariants（本命令全程有效 — 读完再动手）
 
@@ -20,10 +33,12 @@ Start a new Morning Star harness iteration. **Not Done until the Review & Edit c
 
 派发细则 → **`mstar-dispatch-gates`**（specialist review-and-edit dispatch）+ **`mstar-host`**（宿主 invoke 能力）。**不得**在 PM 线程加载其他 role reference 代劳。
 
-**完成定义**：compass `status: locked` + 三角色 invoke 已返回 + pre-commit checklist 全 `[x]` — 不是初稿落盘。
+**Phase 1 完成定义**：compass `status: locked` + 三角色 invoke 已返回 + pre-commit checklist 全 `[x]` — 不是初稿落盘。**Command Done**（§7 auto-continue）= Phase 5 §5.5 exit checklist 全 `[x]`（同 `iteration-drive`）；`pause` 时 = Phase 1 完成。
 
 Detailed workflow → **`mstar-iteration` § Phase 1**；per-plan Prepare gates → **`mstar-phase-gates`**（specify → clarify → plan）。
 
+**Phase 2–5 auto-continue（§7）invariants** → **`iteration-drive`**「PM invariants」表（不写产品代码 / 不 inline 大包 / 每 Assignment 1 invoke / Phase 3→4→5 顺序 / Phase 5 dispatch 改代码）。
+
 ## Path split（HARD — 路由）
 
 | 宿主上下文 | 走哪条 |
@@ -31,6 +46,8 @@ Detailed workflow → **`mstar-iteration` § Phase 1**；per-plan Prepare gates
 | **Cursor Plan mode**（CreatePlan / Plan 会话活跃） | §0 Boot → **§P** — **先**空白 CreatePlan，再 **feedback-driven** 自主改同一份 plan；grill-me **仅**在用户明确结束反馈后、仍有阻塞疑问时；**Build 前不执行** Review 链 / commit / integration 分支 |
 | **其它**（Agent、OpenCode、非 Plan） | §0 Boot → §1–§6（Research → Explore → grill-me → Write → Review → branch） |
 
+**Both paths converge at §6**（integration branch）。Default → §7 auto-continue Phase 2→5；`pause` → command ends at §6。
+
 ## 0. Boot
 
 1. `mstar-harness-core`
@@ -58,11 +75,9 @@ Command-unique 补充（bridge 未枚举）：
 
 Survey structured harness dirs（`{HARNESS_DIR}/status.json`、`{ITERATION_DIR}/`、`{KNOWLEDGE_DIR}/`、`{SPECS_DIR}/`）+ glob for planning artifacts（`**/roadmap*.md`、`**/deferred*.md`、`**/features*.md`、`**/backlog*.md`、`**/TODO*.md`、`**/*.plan.md`）；read matches with iteration-level / deferred-scope information；read `STRATEGY.md`（if exists）。Prioritize deferred / incomplete items from prior iterations。
 
-**Optional — codebase audit**: if a prior `/codebase-audit` run exists under `{PLAN_DIR}/audit-<date>/`, read its findings index as evidence-grounded direction candidates for §2（not mandatory；one source among many）。
-
 ## 2. Explore Directions
 
-Scope **2–4** candidates targeting **product completeness**（default to deferred items from previous iterations；allow substantive refactoring where it accelerates product maturity）。**非 Plan 路径**（Plan mode 已由 §P 处理）。
+Scope **2–4** candidates targeting **product completeness**（default to deferred items from previous iterations；allow substantive refactoring where it accelerates product maturity）。**If `direction` arg given** — narrow candidates to that hint (still scope 2–4 unless the hint is explicitly singular); record the hint in grill-me context。**非 Plan 路径**（Plan mode 已由 §P 处理）。
 
 ## 3. Lock Direction — bundled `grill-me`
 
@@ -72,7 +87,7 @@ Scope **2–4** candidates targeting **product completeness**（default to defer
 
 This command bundles a **non-`mstar-*`** skill at `skills/grill-me/SKILL.md`. **Only this command step**（及 §P.3.5 deferred grill）references it — **do not** load it from `mstar-harness-core` or other `mstar-*` skills.
 
-**Before this step:** Read `skills/grill-me/SKILL.md`. Run **grill-me** to stress-test candidate directions with the user: walk through trade-offs, converge on a **single iteration direction** with shared understanding, document locked direction + success criteria + non-goals。Confirm delivery branch policy（`iteration_base_branch`、`target_branch`）per **`mstar-iteration` §1.2** — **Do not default to `main` / `master` just because those names exist.**
+**Before this step:** Read `skills/grill-me/SKILL.md`. Run **grill-me** to stress-test candidate directions with the user: walk through trade-offs, converge on a **single iteration direction** with shared understanding, document locked direction + success criteria + non-goals。**If `direction` arg given** — seed grill-me with it as the recommended direction (still interactive: user may correct/refine; the hint does **not** skip grill-me)。Confirm delivery branch policy（`iteration_base_branch`、`target_branch`）per **`mstar-iteration` §1.2** — **Do not default to `main` / `master` just because those names exist.**
 
 ## 4. Write Compass & Plans
 
@@ -130,6 +145,34 @@ git checkout -b <spec_integration_branch> <iteration_base_branch>
 - Register `iteration_base_branch`, `spec_integration_branch`, and `target_branch` in compass frontmatter **and** `{HARNESS_DIR}/status.json` root `metadata`
 - Commit all documents to the integration branch and push to remote
 
-**Phase 2 note**：control worktree + `execution_lease` 门控在 Phase 2 入口（`iteration-drive` / `iteration-loop`）——见 **`mstar-iteration/references/phase-2-worktree-lease.md`**。
-
 **STOP** if `iteration_base_branch` or `target_branch` is missing. Ask the user or derive only from an already documented project/iteration policy; never silently substitute `main`.
+
+---
+
+## 7. Phase 2–5: Execute → close → PR → merge-ready（auto-continue）
+
+**`pause` arg → command ends here.** Phase 1 locked + integration branch pushed；run `/iteration-drive` later to resume。
+
+**Default（no `pause`）→ auto-continue** into Phase 2→5。
+
+### Phase 2 boot（load before delegating）
+
+1. `mstar-iteration` → **§ Phase 2–5**（§2 Autonomous Execute、§3 close、§4 PR、§5 merge-ready）
+2. **`mstar-sdd`** — before first implement dispatch（per-task loop SSOT）
+3. `mstar-review-qc` — before first QC dispatch
+4. `mstar-compound` — before Phase 3 §3.2
+5. `mstar-branch-worktree` + **`mstar-iteration/references/phase-2-worktree-lease.md`** — control worktree + lease（§2.0 #5 未 waive）
+
+### Delegate to `iteration-drive` Phase 2→5
+
+Execute **`iteration-drive`** Phase 2–5 exactly：Phase 2 → **`mstar-iteration` §2**（§2.0 五道闸 → §2.6 push 纪律；SDD per-task；QC tri N=3 + QA）、Phase 3 → **§3** + `references/phase-3-iteration-close.md`、Phase 4/5 → **§4–§5** + `references/phase-4-5-pr-delivery.md`、Phase 5 helper discovery → `mstar-iteration/references/phase5-helper-discovery.md`。
+
+**Continuous execution（HARD）**：自 Phase 2 进入至 Phase 5 §5.5 exit，PM **连续编排**（**`mstar-iteration` §2.6**），进度汇报后下一条必须是 dispatch 或下一 phase 步骤，不向用户例行 yes/no check-in。合法 STOP 仅限：branch metadata 缺失、真冲突 / secrets / 不可逆范围缺口、Phase 5 多轮仍无法 merge-ready、用户本轮显式打断。
+
+**Assignment preflight**：同 §5（每次 implement/QC/QA 派发前校验；`mstar-harness` bin 未安装时静默跳过）。
+
+**Done = Phase 5 §5.5 exit checklist 全 `[x]`**（同 `iteration-drive`）。
+
+**Then** report: iteration id, direction lock summary, plans completed, compound summary, PR link, merge-ready evidence（CI snapshot + review resolution + Greptile if applicable）。
+
+PR merge itself may remain manual unless user authorized auto-merge.

package/harness-skills/mstar-host/SKILL.md

@@ -29,10 +29,10 @@ Detect from **session tool shapes and available commands** — not from plugin m
 |--------|------|-----------|
 | **`subagent_type`** param on the Task tool (plus **CreatePlan**/**SwitchMode** when Plan mode is active) | `cursor` | `references/cursor.md`; Plan mode also `references/cursor-plan-mode-bridge.md` |
 | **`question`** tool, or **`task`** tool with **`subagent`** (singular) — no `tasks[]` batch | `opencode` | `references/opencode.md` |
-| **`task`** tool with **`agent`** / **`tasks[]`** batch, **`ask`**, **`hub`** | `omp` | `references/omp.md`; Plan mode also `references/omp-plan-mode-bridge.md` |
+| **`task`** tool with **`agent`** / **`tasks[]`** batch, **`ask`**, **`hub`** (omp also exposes `/goal`; goal rule is host-agnostic per below) | `omp` | `references/omp.md`; Plan mode also `references/omp-plan-mode-bridge.md` |
 | **`Agent`** / **`AskUserQuestion`** / **`EnterPlanMode`** + **`AgentSwarm`** (Kimi-only) | `kimi` | `references/kimi.md`; Plan mode also `references/kimi-plan-mode-bridge.md` |
 | **`Agent`** / **`AskUserQuestion`** / **`EnterPlanMode`** / **`TodoWrite`**, **no `AgentSwarm`** | `zcode` | `references/zcode.md`; Plan mode also `references/zcode-plan-mode-bridge.md` |
-| `/plan`, `/goal` slash commands; **Goal tools**; `functions.*` / `codex_app.*` tool namespaces; `tool_search`; Browser plugin tools | `codex` | `references/codex.md`; Plan/Goal mode also `references/codex-plan-goal-mode-bridge.md` |
+| `/plan`, `/goal` slash commands; **Goal tools**; `functions.*` / `codex_app.*` tool namespaces; `tool_search`; Browser plugin tools | `codex` | `references/codex.md`; Plan mode also `references/_shared/plan-mode-bridge-core.md` |
 | Still ambiguous | - | Read sections in **`cursor.md`**, **`opencode.md`**, **`codex.md`**, **`kimi.md`**, **`zcode.md`**, and **`omp.md`** that match tools you have; **`mstar-harness-core` wins** on conflict |
 
 Order matters: check `cursor` → `opencode` → `omp` → `kimi` → `zcode` → `codex`. `subagent_type` (Cursor) vs `subagent` (OpenCode) vs `agent`/`tasks[]` (omp) is the sharpest split among the Task-based hosts.
@@ -43,6 +43,15 @@ Order matters: check `cursor` → `opencode` → `omp` → `kimi` → `zcode`
 
 When PM dispatches **N >= 2** concurrent assignees (QC tri-review, dual-track implement, etc.) and the host exposes actual invoke / Task / subagent tools, read **`references/parallel-dispatch.md`** in the dispatch round (shared with `mstar-dispatch-gates`). Without a callable invoke tool when dispatch is required → **`Blocked`**; Assignment Markdown alone is not dispatch.
 
+## `/goal` directive (host-agnostic)
+
+**Applicability is by capability, not host identity**: any host that exposes a `/goal` command (currently Codex Goal Mode and omp; other code agents may add it later) attaches a persistent objective to the thread. Rule — **always set the goal to running the complete flow to the end**, never a sub-stage:
+
+- **Advancing an iteration**: set the goal to **complete the entire iteration flow** (`iteration-start → per-plan cycles → iteration-close → PR delivery → PR merge-ready loop`). Do not set a sub-stage goal (e.g. "finish Phase 1 only").
+- **Advancing non-iteration work** (single plan / hotfix / one-off task): set the goal to **complete the entire per-plan flow** (`specify → clarify → plan → tasks → implement → plan QC tri + QA gate → Done`). Do not set a sub-stage goal (e.g. "write the plan" or "implement one task").
+
+Goal text is a session-level objective only: `{HARNESS_DIR}` / `{PLAN_DIR}` / `status.json` remain SSOT, and goal completion is **not** harness Done. Mirror goal success criteria into the SSOT plan; when the goal changes, update goal text and the SSOT in the same round.
+
 ## Resolve loaded skill root
 
 Docs name assets as skill **`<name>`** → `scripts/…` / `references/…`. **Resolve the loaded skill directory first** — do **not** open `skills/<name>/…` from a consumer app cwd (that layout exists in the harness source / plugin package only).

package/harness-skills/mstar-host/references/_shared/plan-mode-bridge-core.md

@@ -2,7 +2,7 @@
 
 > **Load order**: Read **`mstar-harness-core`** first, then **`mstar-host`** and the host reference + this bridge. When plan management is required, also read **`mstar-plan-conventions`** and **`mstar-plan-artifacts`** before creating or claiming any durable plan state. Path symbols `{HARNESS_DIR}`, `{PLAN_DIR}`, `{SPECS_DIR}` are defined in `mstar-plan-conventions`. On conflict, **`mstar-harness-core`** wins.
 
-Each per-host bridge (`cursor-plan-mode-bridge.md`, `codex-plan-goal-mode-bridge.md`, `kimi-plan-mode-bridge.md`, `zcode-plan-mode-bridge.md`, `omp-plan-mode-bridge.md`) loads this core and adds its host-specific plan UX (plan tooling, approval gate, todo UI, command surfaces).
+Each per-host bridge (`cursor-plan-mode-bridge.md`, `kimi-plan-mode-bridge.md`, `zcode-plan-mode-bridge.md`, `omp-plan-mode-bridge.md`) loads this core and adds its host-specific plan UX (plan tooling, approval gate, todo UI, command surfaces). Codex Plan Mode reads this core directly via `references/codex.md` (no per-host codex plan bridge; the `/goal` rule is host-agnostic in `mstar-host` SKILL.md).
 
 ## Dual-write SSOT rule
 

package/harness-skills/mstar-host/references/codex.md

@@ -2,7 +2,7 @@
 
 Load when **`mstar-host`** detection resolves **codex** (Codex app/CLI session, `/plan` / `/goal` slash commands, Goal tools, or Codex tool namespaces such as `functions.*`, `codex_app.*`, `tool_search`, `image_gen`, or Browser plugin tools).
 
-Plan / Goal Mode: read **`codex-plan-goal-mode-bridge.md`** when Codex Plan Mode (`/plan`) or Goal Mode (`/goal`, goal tools, or goal progress controls) is active. Codex session plans, UI todos, and goal text are not durable harness SSOT.
+Plan Mode: read **`references/_shared/plan-mode-bridge-core.md`** when Codex Plan Mode (`/plan`) is active. Goal Mode (`/goal`, goal tools, or goal progress controls) follows the host-agnostic **`/goal`** rule in `mstar-host` SKILL.md — applicability is by the `/goal` command, not host identity. Codex session plans, UI todos, and goal text are not durable harness SSOT.
 
 Parallel PM dispatch: read **`parallel-dispatch.md`** only when Codex exposes an actual multi-agent / Task-style invocation tool. If no callable invoke tool exists, Assignment Markdown is coordination text only; do **not** claim subagent dispatch.
 
@@ -19,7 +19,7 @@ Parallel PM dispatch: read **`parallel-dispatch.md`** only when Codex exposes an
 
 1. Read `mstar-harness-core`.
 2. Read `mstar-host` and this Codex reference.
-3. If Plan Mode or Goal Mode is active, read `codex-plan-goal-mode-bridge.md`.
+3. If Plan Mode is active, read `references/_shared/plan-mode-bridge-core.md`; Goal Mode follows the `/goal` rule in `mstar-host` SKILL.md.
 4. Load `mstar-roles` and the active role reference.
 5. Load topic skills on demand per the role reference.
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mstar-harness/opencode",
-  "version": "2.0.4",
+  "version": "2.0.6",
   "description": "Morning Star harness OpenCode plugin — skills bootstrap + engine-backed runtime hooks (status lint, dispatch validation, Enforcement: hard gates).",
   "license": "MIT",
   "repository": {
@@ -36,6 +36,6 @@
     "access": "public"
   },
   "devDependencies": {
-    "@mstar-harness/engine": "2.0.4"
+    "@mstar-harness/engine": "2.0.6"
   }
 }

package/harness-skills/mstar-host/references/codex-plan-goal-mode-bridge.md

@@ -1,98 +0,0 @@
-# Codex Plan / Goal Mode x Harness Bridge
-
-> **Load order**: Read **`mstar-harness-core`** first, then **`mstar-host`** and **`references/codex.md`**, then **`references/_shared/plan-mode-bridge-core.md`** (shared contract) + this bridge. When plan management is required, also read **`mstar-plan-conventions`** and **`mstar-plan-artifacts`** before creating or claiming any durable plan state. On conflict, **`mstar-harness-core`** wins.
-
-**Shared contract** (dual-write SSOT rule + priority, bootstrap init, Build resume contract, bootstrap todos, implement done-gate, Phase 1 gate, shared anti-patterns) → **`references/_shared/plan-mode-bridge-core.md`**. This bridge covers Codex **Plan Mode** (`/plan`) and **Goal Mode** (`/goal`) specifics only.
-
-## Purpose
-
-Codex **Plan Mode** (`/plan`) and **Goal Mode** (`/goal`) are host collaboration surfaces:
-
-- **Plan Mode** helps shape a plan inside the active Codex conversation.
-- **Goal Mode** attaches a persistent objective and success criteria to the active thread.
-
-Morning Star durable state still lives under **`{HARNESS_DIR}`** (default `.mstar/`, legacy `.agents/`). This reference prevents Codex session plans, UI todos, goal text, or goal completion from replacing the harness SSOT.
-
-## Priority (hard)
-
-1–3 → core (user explicit → `AGENTS.md`/`CLAUDE.md` → **`{HARNESS_DIR}` / `{PLAN_DIR}` / `status.json`** harness SSOT).
-
-4. Codex Goal Mode objective / progress controls
-5. Codex Plan Mode output, `update_plan`, UI todos, chat summaries
-
-**NEVER** cite only a Codex goal, session plan, UI todo, or chat summary in Assignment **Plan Path**, **Context Loaded**, or Completion Report when `{PLAN_DIR}/<plan-id>-<name>.md` should exist.
-
-## When this applies
-
-- Codex Plan Mode is active (`/plan`, Plan collaboration mode, or host guidance says planning-only).
-- Codex Goal Mode is active (`/goal`, host goal controls, or goal tools such as `create_goal`, `get_goal`, `update_goal`).
-- Morning Star plugin or `/pm` is in use under Codex.
-
-## Codex Plan Mode
-
-Use Plan Mode to clarify, inspect, compare approaches, and draft the harness plan. Do **not** treat Plan Mode output as a durable artifact.
-
-Bootstrap before implementation or PM dispatch (discover `{HARNESS_DIR}` / `{PLAN_DIR}`, ensure `status.json`, register a `plans[]` row, write `{PLAN_DIR}/<plan-id>-<name>.md` with task checkboxes + roadmap; use the SSOT plan path in Assignment and Completion Report evidence) → core.
-
-Allowed in Plan Mode: exploration, clarify questions, spec/plan drafting, `.mstar/` initialization, SSOT plan/status edits, PM routing decisions.
-
-Not allowed by default in Plan Mode: product implementation, test implementation, QC execution, QA execution, deployment, or ops changes. Switch to normal execution or dispatch through an actual callable subagent/multi-agent tool first.
-
-## Codex Goal Mode
-
-Goal text is useful as the top-level objective and success criteria, but it is **not** a Morning Star plan, status ledger, PM Assignment, QC report, or QA Done authority.
-
-When starting or receiving a Goal Mode objective:
-
-1. If the goal is implementation-sized or long-running, create or update the harness SSOT (`status.json` + `{PLAN_DIR}` plan) before implementation.
-2. Mirror the goal's success criteria into the SSOT plan as acceptance / verification criteria.
-3. If the goal changes, update both Goal Mode text/progress and the SSOT plan/status in the same coordination round.
-4. If the goal conflicts with the SSOT, pause or report **Blocked** until PM/user resolves scope.
-
-### Goal completion gate
-
-Only mark a Codex goal complete when all applicable harness gates are satisfied:
-
-- Required plan checkboxes are complete in `{PLAN_DIR}`.
-- `status.json` reflects the current lifecycle state.
-- Required commits exist on the authorized branch.
-- Verification evidence is recorded.
-- QC/QA authority has passed when the plan requires InReview / Done gates.
-
-If the host asks to complete a goal but harness Done authority is missing, report **Blocked** and list the missing artifacts or gate decisions. Do not call a goal-completion tool as a substitute for PM/QC/QA evidence.
-
-## Resume / compaction
-
-Codex can resume threads and compact context. On resume, before editing product code:
-
-1. Reload `mstar-harness-core` -> `mstar-host` -> `references/codex.md` -> this bridge.
-2. If Goal Mode is active, read the current goal and compare it with `{HARNESS_DIR}/status.json` and the active SSOT plan.
-3. Treat `.mstar/` as durable truth over chat summaries or UI todos.
-4. If the active role or Assignment is missing, resume as PM for coordination and dispatch only.
-
-## `/pm` under Codex Plan / Goal Mode
-
-When `/pm` runs under Plan or Goal Mode:
-
-- `/pm` is still the force entry into Morning Star PM behavior.
-- Prepare phase (`specify -> clarify -> plan`) still applies unless the task qualifies for a documented hotfix path.
-- Goal Mode can hold the high-level objective, but PM must still write Assignment with `Execute as`, `Delegation`, branch policy, SSOT `Plan Path`, and evidence requirements.
-- Without an actual callable subagent/multi-agent tool, Assignment Markdown is coordination text only; execute serially in-session or report Blocked for rerouting.
-
-## Anti-patterns
-
-| Anti-pattern | Fix |
-|--------------|-----|
-| `/plan` output only, no `{HARNESS_DIR}` files | Write SSOT plan + `status.json` entry before implementation |
-| `update_plan` todo done, no commit/evidence | Commit or record required evidence before completion |
-| Goal objective treated as Done authority | Check harness plan/status/QC/QA gates first |
-| Goal changed but `.mstar/` still has old scope | Update Goal Mode and SSOT in the same round |
-| Resume starts coding from chat summary | Reload harness context and SSOT plan/status first |
-| Assignment Plan Path points at Codex transcript/goal | Use `{PLAN_DIR}/...` path |
-
-## Related skills
-
-- `mstar-plan-conventions` - discover `{HARNESS_DIR}`, `{PLAN_DIR}`, legacy layouts
-- `mstar-plan-artifacts` - `status.json`, plan checkboxes, reports, residuals
-- `mstar-phase-gates` - Prepare / Execute and Done authority
-- `mstar-dispatch-gates` - Assignment, Delegation, anti-recursion