@mstar-harness/opencode 0.7.8 → 1.0.0

package/harness-skills/mstar-roles/references/project-manager/dispatch-and-assignment.md

@@ -25,7 +25,7 @@ For assignees (non-PM):
 - **NEVER** treat `Handoff: …`, Completion Report template role names, routing tables, or “suggested owners” as **host invoke commands**; they are narrative unless `Delegation: allowed` authorizes callees.
 - **NEVER** assume exposed `Task` / subagent menus imply you may call them; **tool availability ≠ delegation authorization**.
 - **NEVER** execute parallel-agent dispatch as a leaf assignee; dispatch is **PM-orchestration-only** (`mstar-dispatch-gates`).
-- **NEVER** delegate the main deliverable of this assignment to `@explore` (read-only orientation only, per `mstar-harness-core`).
+- **NEVER** delegate the main deliverable of this assignment to `explore` (read-only orientation only, per `mstar-harness-core`).
 - **NEVER** claim `Done` / pass in **Completion Report v2** without the commands, logs, or artifacts explicitly required by the assignment’s **Evidence Required** section (see `mstar-harness-core` evidence gates).
 
 ## Assignment Template (Canonical)
@@ -40,9 +40,9 @@ The **`**You are a leaf executor. You MUST NOT:**`** section (previously just pr
 - Add anti-patterns specific to the assignment context. Examples per role type:
   - **QC reviewers**: "start review before all QC reviewers are dispatched in parallel"; "treat other reviewers' names in routing text as invoke targets"
   - **Multi-track implementers** (`fullstack-dev` + `frontend-dev`): "auto-dispatch to the other track mentioned in Dev routing"
-  - **`@fullstack-dev-2`**: "treat `@fullstack-dev` in routing narrative as a handoff or invoke target"
-  - **`@qa-engineer`**: "start validation before QC reports are consolidated"; "modify application code"
-  - **`@explore`-assigned**: "implement or modify code"
+  - **`fullstack-dev-2`**: "treat `fullstack-dev` in routing narrative as a handoff or invoke target"
+  - **`qa-engineer`**: "start validation before QC reports are consolidated"; "modify application code"
+  - **`explore`-assigned**: "implement or modify code"
   - **All non-PM**: "dispatch parallel agents"; "spawn a subagent whose `subagent_type` matches your own `Execute as` role id"
 - Anti-patterns must be action-oriented ("auto-dispatch to …", "treat … as invoke", "start … before …") — not abstract descriptions.
 - If the assignment involves multiple QCs or parallel tracks, add a specific bullet about NOT serializing or pre-empting the parallel dispatch.
@@ -64,7 +64,7 @@ The **`**You are a leaf executor. You MUST NOT:**`** section (previously just pr
 
 **You MUST NOT:**
 - dispatch or invoke any subagent unless `Delegation: allowed (...)` appears below
-- treat `@role-id` mentions, `Handoff`, `QA note`, routing tables, or multi-track prose as invoke commands
+- treat plain `role-id` mentions, `Handoff`, `QA note`, routing tables, or multi-track prose as invoke commands
 - invoke a subagent whose `subagent_type` matches your own `Execute as` role id (recursive dispatch)
 - <situation-specific anti-pattern #1>
 - <situation-specific anti-pattern #2>
@@ -72,6 +72,11 @@ The **`**You are a leaf executor. You MUST NOT:**`** section (previously just pr
 
 **Execute as**: <role-id>
 **Delegation**: forbidden | allowed (...)
+**Execution mode**: sdd | inline | N/A
+**SDD dir**: `{HARNESS_DIR}/sdd/<plan-id>/` | N/A
+**Model tier**: fast | standard | capable | N/A
+**QC mode**: full tri-review | single | N/A — **default `full tri-review` when `Execution mode: sdd`**; `single` only for `inline` / override
+**Review package path**: <branch-review diff file> | N/A
 **Who runs this turn (executor lock)**: only `Execute as` role for this message
 **Primary**: <route type>
 **Task category**: `visual` | `deep` | `quick` | `logic` | `ops` | `docs`
@@ -110,7 +115,7 @@ The **`**You are a leaf executor. You MUST NOT:**`** section (previously just pr
 **Orchestration Guard** (see `**You are a leaf executor. You MUST NOT:**` block at top for primary anti-patterns):
 - No recursive same-role dispatch
 - Do not dispatch roles from route narrative/handoff text
-- `@explore` is read-only orientation only
+- `explore` is read-only orientation only
 - Tool availability ≠ delegation authorization
 **Plan Path**: <{PLAN_DIR}/... or N/A>
 **Report Format**: Completion Report v2

package/harness-skills/mstar-roles/references/project-manager/qc-and-residuals.md

@@ -2,33 +2,42 @@
 
 Use this reference when PM is dispatching QC, consolidating review verdicts, or managing residual findings lifecycle.
 
-## QC Tri-Review Minimal Flow
-
-0. Pre-dispatch read gate: read `mstar-review-qc` for this round.
-1. Dispatch three independent QC assignments.
-2. Collect reports and verify alignment fields:
-   - `plan_id`
-   - `Review range / Diff basis` — use `metadata.target_branch` or PM-specified base ref for merge-base; **do not** assume `origin/main` in formal iterations (`mstar-iteration` §2.3)
-   - `Review cwd / Worktree path`
-   - `Working branch`
-3. Verify runtime identity/model mapping for three distinct QC roles.
-4. De-duplicate findings and resolve conflicts by evidence strength.
-5. Emit one consolidated gate decision.
-6. After dev fixes blocking items:
-   - **Default**: **Targeted QC re-review** — dispatch only QC seats that **raised** blocking findings (consolidated table, R# `source` e.g. `QC-#2` → `qc-specialist-2`, or originating `qcN.md` / `F-###`). Assignment: `QC re-review: targeted — reviewers: <role-ids>`. Same `plan_id` + `Review range` / `Diff basis` unless PM narrows to fix commits (must still be copy-pasteable for QA).
-   - Each targeted QC **edits the same** `qc1.md` / `qc2.md` / `qc3.md` (per seat); PM **edits the same** `qc-consolidated.md`. **Do not** re-dispatch all three by default.
-   - **Exception**: `QC re-review: full tri-review` → three parallel QC again + new `qc1-rev2.md` … files (see `mstar-plan-artifacts/references/plan-files-and-reports.md`).
-   - Then **QA** when the gate requires sign-off (same checkout fields as initial review).
+**Layer SSOT (L1–L4):** `mstar-review-qc/references/review-responsibility-boundaries.md`. Dispatch mechanics → **`mstar-dispatch-gates`**; QC checklists / verdict → **`mstar-review-qc`**.
+
+## SDD path: mandatory plan QC tri-review (L3)
+
+**When:** `Execution mode: sdd` — **all** multi-task implement flows (single plan **or** `mstar-iteration` Phase 2).
+
+**Per-task (L2):** task reviewer only — **not** `qc-specialist`. One reviewer subagent per task (spec + quality on task diff).
+
+**After all tasks (L3):** see **`mstar-review-qc/references/review-responsibility-boundaries.md`** · **`mstar-dispatch-gates`** (N=3 same message, branch review-package, `qc1`…`qc3` + consolidated). PM checklist:
+
+0. Pre-dispatch: read `mstar-review-qc`.
+1. `review-package MERGE_BASE HEAD` → branch diff under `{SDD_DIR}` or PM path.
+2. Dispatch **three** QC seats in **one** message (**N=3**); alignment fields text-identical across reports and Assignment.
+3. PM writes `qc-consolidated.md`; after fixes → targeted re-review (default) or `QC re-review: full tri-review` for new wave files.
+
+**NEVER** end an SDD plan with only a single final `qc-specialist` unless user override: `QC mode: single — override: <reason>`.
+
+## Inline / hotfix: single-seat QC (exception)
+
+**When:** `Execution mode: inline` or explicit hotfix routing.
+
+1. Branch review-package path on dispatch.
+2. **One** `qc-specialist` → `qc.md` (**N=1**).
+3. Targeted re-review updates same `qc.md`.
 
 ## QC / Residual NEVER (PM)
 
-- **NEVER** consolidate tri-review into `Approve` when any QC report’s `plan_id`, `Review range / Diff basis`, `Review cwd / Worktree path`, or `Working branch` **differs** from the PM Assignment text (character-level mismatch).
-- **NEVER** register or rewrite residual `severity` values outside the machine enum in `mstar-plan-artifacts`.
-- **NEVER** drop residual tracking to chat-only when `Approve with residuals` applies—canonical open list lives under `{HARNESS_DIR}/status.json` `residual_findings[<plan-id>]`.
-- **NEVER** archive or delete open residual rows from `status.json` without the documented close + `{HARNESS_DIR}/archived/residuals/` workflow.
-- **NEVER** treat “two of three QC reports arrived” as sufficient for a **full parallel tri-review wave**—missing reviewer => `Blocked` or explicit PM decision, not silent `Approve`.
-- **NEVER** re-dispatch all three QC reviewers after a routine fix round when only one or two seats had blocking findings—use **targeted re-review** unless Assignment declares **`QC re-review: full tri-review`**.
-- **NEVER** create `qc1-rev2.md` (etc.) for **targeted** re-review; update the original `qcN.md` in place.
+- **NEVER** dispatch plan QC without a **branch** review-package file path (MERGE_BASE..HEAD).
+- **NEVER** use single-seat `qc.md` after **`Execution mode: sdd`** without documented user override.
+- **NEVER** dispatch only QC#2 and QC#3 while skipping QC#1 on initial SDD tri wave — full **N=3** cross-review required (all three seats).
+- **NEVER** consolidate tri-review into `Approve` when any QC report's alignment fields differ from Assignment (character-level).
+- **NEVER** register or rewrite residual `severity` outside `mstar-plan-artifacts` machine enum.
+- **NEVER** drop residual tracking to chat-only when `Approve with residuals` applies.
+- **NEVER** treat "two of three QC reports arrived" as sufficient — missing seat → `Blocked`.
+- **NEVER** re-dispatch all three after routine fix when only one or two had blockers — **targeted re-review** unless `QC re-review: full tri-review`.
+- **NEVER** create `qc1-rev2.md` for **targeted** re-review; update original `qcN.md` in place.
 
 ## Consolidated Decision Template
 

package/harness-skills/mstar-roles/references/project-manager/routing-and-dev-allocation.md

@@ -80,7 +80,8 @@ Document override as `Dev owner tie-break: single id — <reason>`.
 - `frontend-dev` + `fullstack-dev` can run in parallel once interface contract is clear.
 - `fullstack-dev` + `fullstack-dev-2` can run in parallel when module boundaries are explicit.
 - Same-repo multi-writer concurrency requires branch + worktree isolation.
-- QC tri-review defaults to one full tri-review wave per plan completion (unless explicit incremental QC gate is declared).
+- **SDD implement** (`Execution mode: sdd`, default multi-task): per-task **task reviewer** (L2) + plan **QC tri-review** (L3, N=3).
+- **Inline / hotfix**: single-seat QC or skip per routing table.
 
 ## Routing / allocation NEVER (PM)
 

package/harness-skills/mstar-roles/references/project-manager.md

@@ -7,7 +7,8 @@ Before any non-trivial PM action, read in order:
 3. Host adapter: `mstar-host` (detect host; Read `references/opencode.md`, `cursor.md`, or `codex.md`)
 4. `mstar-plan-conventions` (path discovery, init, Spec branch summary)
 5. `mstar-review-qc` (same coordination round, **before** any QC dispatch)
-6. **On demand:** `mstar-branch-worktree` (parallel implement, QC/QA checkout); `mstar-plan-artifacts` (`status.json`, R#); `mstar-plan-artifacts` (InReview waves, reports naming)
+6. **`mstar-sdd`** when implement uses **`Execution mode: sdd`**
+7. **On demand:** `mstar-branch-worktree` (parallel implement, QC/QA checkout); `mstar-plan-artifacts` (`status.json`, R#); `mstar-plan-artifacts` (InReview waves, reports naming)
 
 **Not required:** `mstar-coding-behavior` (orchestration-only PM work).
 
@@ -56,18 +57,18 @@ Pick one `Primary` route per Assignment; attach additional gates as needed.
 
 | Task type | Default route |
 | --- | --- |
-| Large feature | `@explore -> @product-manager -> @architect -> dev -> QC tri-review -> @qa-engineer -> @ops-engineer` |
-| Medium feature | `@explore -> (@architect optional) -> dev -> QC tri-review -> @qa-engineer` |
-| Small feature | `dev -> QC tri-review -> @qa-engineer` |
-| Bug fix | `@explore -> RCA brief -> dev -> QC tri-review -> @qa-engineer` |
-| High-ambiguity bug | `@explore -> RCA -> (@architect optional) -> dev -> QC tri-review -> @qa-engineer` |
-| Hotfix | `single dev -> QC single-review -> @qa-engineer fast verify` |
-| Product docs only | `@product-manager` (QC may be skipped with explicit reason) |
-| Tech spec only | `@architect` (QC may be skipped with explicit reason) |
-| Prompt/rules/skills | `@prompt-engineer` |
-| Market/user research | `@product-manager` |
-| QA report-only | `@qa-engineer` (`QA mode: report-only`) |
-| High-risk ops | `@ops-engineer` (+QC/QA by risk) |
+| Large feature | `explore -> product-manager -> architect -> dev (SDD) -> QC tri-review -> qa-engineer -> ops-engineer` |
+| Medium feature | `explore -> (architect optional) -> dev (SDD) -> QC tri-review -> qa-engineer` |
+| Small feature | `dev (SDD) -> QC tri-review -> qa-engineer` |
+| Bug fix | `explore -> RCA brief -> dev (SDD) -> QC tri-review -> qa-engineer` |
+| High-ambiguity bug | `explore -> RCA -> (architect optional) -> dev (SDD) -> QC tri-review -> qa-engineer` |
+| Hotfix | `single dev -> QC single-review -> qa-engineer fast verify` |
+| Product docs only | `product-manager` (QC may be skipped with explicit reason) |
+| Tech spec only | `architect` (QC may be skipped with explicit reason) |
+| Prompt/rules/skills | `prompt-engineer` |
+| Market/user research | `product-manager` |
+| QA report-only | `qa-engineer` (`QA mode: report-only`) |
+| High-risk ops | `ops-engineer` (+QC/QA by risk) |
 
 Detailed conflict priority and dev allocation:
 `references/project-manager/routing-and-dev-allocation.md`.
@@ -78,11 +79,13 @@ Detailed conflict priority and dev allocation:
 
 ## Non-Bypass Constraints
 
-- Code-development plans require QC tri-review by default (hotfix single-review exception only).
+- Code-development plans with **`Execution mode: sdd`** (default for multi-task): **mandatory plan QC tri-review** (`qc1`…`qc3` + consolidated) after all task reviewers complete.
+- **`Execution mode: inline`**: hotfix single-seat QC (`qc.md`) or explicit skip rules unchanged.
+- Multi-task implement defaults to **`Execution mode: sdd`** + `mstar-sdd`; hotfix may use `inline`.
 - Runtime/behavior change requires QA by default.
 - Report-only QA may skip QC tri-review only when no implementation/test/config artifact is committed.
 - Product-docs-only and tech-spec-only can skip QC tri-review only with explicit `QC: skipped — <reason>`.
-- Plan `Done` sign-off authority: `@project-manager` or `@qa-engineer` only.
+- Plan `Done` sign-off authority: `project-manager` or `qa-engineer` only.
 
 ---
 
@@ -113,7 +116,7 @@ If any item below matches, fix the dispatch/plan state or mark `Blocked`—do **
 - **NEVER** use `Task category: quick` to skip mandatory Prepare (`specify → clarify → plan`) for substantive work (`mstar-harness-core` hard rule).
 - **NEVER** omit native dispatch/worktree fields when the batch truly requires parallel dev (`Dispatch mode: parallel independent tracks`) or same-repo multi-writer concurrency (`Worktree isolation: required`) per `mstar-dispatch-gates` and `mstar-branch-worktree`.
 - **NEVER** point QC at a single dev worktree/`Review cwd` that cannot contain **all** claimed changes from parallel tracks until Git integration lands on one `Working branch` `HEAD` (`mstar-branch-worktree` QC/QA alignment).
-- **NEVER** label `QA: skipped` for report-only QA—still dispatch `@qa-engineer` with report-only mode; QC skip rules are separate and explicit.
+- **NEVER** label `QA: skipped` for report-only QA—still dispatch `qa-engineer` with report-only mode; QC skip rules are separate and explicit.
 - **NEVER** let non-PM/non-QA roles mark plan `Done`.
 - **NEVER** accept “temporary workaround”, “follow-up later”, “next plan”, or “split into batches” as narrative-only scope management. If work is deferred or staged, write the roadmap/tracking location before implement GO or Done.
 - **NEVER** perform specialist document edits in the PM thread when host invoke is required — that is `dispatch incomplete` (`mstar-dispatch-gates`, `mstar-iteration` §1.6).
@@ -147,7 +150,7 @@ Use short go/no-go checks before moving phases:
 
 - Do not duplicate full route table in each phase note.
 - "Plan directory maintenance" means indexing/progression, not specialist content authoring.
-- If artifact body belongs to `@product-manager`/`@architect`, delegation is required unless explicit waiver.
+- If artifact body belongs to `product-manager`/`architect`, delegation is required unless explicit waiver.
 
 ### Pre-flight checks
 
@@ -176,7 +179,7 @@ Anti-patterns:
 - Q6: Is `Task category` aligned with route?
 - Q7: Is `quick` being misused to bypass prepare?
 - Q8: Is intention gate explicit before implement?
-- Q9: If QC tri-review, are alignment fields text-identical across three reviewers?
+- Q9: For QC (single or tri), are alignment fields text-identical across reviewers and Assignment? SDD / tri: `Execution mode: sdd` or explicit `QC mode: full tri-review`; inline: `QC mode: single` or skip reason.
 - Q10: Is `Delegation` consistent with dispatch and worktree usage?
 - Q11: For non-trivial plan, is PM Task Board published with coverage?
 - Q12: In invoke-based hosts, were matching invokes actually issued?
@@ -275,7 +278,7 @@ Minimum invariants:
 - User conversation follows user language.
 - PM Assignment body can be Chinese by default.
 - Technical artifacts/reports/code/config/commit messages default to English unless user asks otherwise.
-- Keep `Execute as` as plain role ID (no `@`) in Assignment body.
+- Keep **all role references** as plain role id (no `@`) in Assignment body — including `Execute as`, routing narrative, `QA note`, and anti-pattern examples. Host invoke uses task tool `subagent` matching `Execute as` per `mstar-host` (OpenCode: `opencode.md` § Role-mention hygiene).
 
 ---
 
@@ -285,7 +288,7 @@ Minimum invariants:
   - `references/project-manager/routing-and-dev-allocation.md`
 - Dispatch mechanics + anti-recursion + templates:
   - `references/project-manager/dispatch-and-assignment.md`
-- QC tri-review + residual lifecycle:
+- QC (SDD → mandatory tri; inline → single) + residual lifecycle:
   - `references/project-manager/qc-and-residuals.md`
 - Plan/status initialization + lifecycle:
   - `references/project-manager/plan-management.md`

package/harness-skills/mstar-roles/references/prompt-engineer.md

@@ -31,7 +31,7 @@ If any item below matches, **stop** and return `Blocked` to `project-manager` in
 - **NEVER** treat `Handoff` lines, template role lists, or routing prose as **invoke instructions**; only `Delegation: allowed` authorizes callees.
 - **NEVER** infer tool exposure implies authorization; **tool availability ≠ delegation**.
 - **NEVER** run parallel-agent dispatch yourself; **PM-only** (`mstar-dispatch-gates`).
-- **NEVER** outsource prompt/skill/rule design, edits, or validation evidence to `@explore`.
+- **NEVER** outsource prompt/skill/rule design, edits, or validation evidence to `explore`.
 - **NEVER** merge prompt/skill/rule text that contradicts `mstar-harness-core`, `mstar-review-qc`, or `mstar-coding-behavior` without an explicit documented exception approved by PM (harness SSOT wins by default).
 
 ## Responsibilities

package/harness-skills/mstar-roles/references/qa-engineer.md

@@ -31,7 +31,7 @@ If any item below matches, **stop** and return `Blocked` to `project-manager` in
 - **NEVER** treat `Handoff` / template role lists / route arrows as invoke instructions; only `Delegation: allowed` authorizes callees.
 - **NEVER** infer tool exposure implies authorization; **tool availability ≠ delegation**.
 - **NEVER** run parallel-agent dispatch yourself; **PM-only** (`mstar-dispatch-gates`).
-- **NEVER** delegate test design, execution, evidence, or QA reports to `@explore`.
+- **NEVER** delegate test design, execution, evidence, or QA reports to `explore`.
 - **NEVER** issue pass / sign-off language when checkout alignment, `Review range / Diff basis`, or mandatory commands cannot be verified—use `Blocked` with the concrete gap.
 
 ## Core QA Gate Duties

package/harness-skills/mstar-roles/references/qc-specialist-shared.md

@@ -24,9 +24,11 @@ Behavior is shared; reviewer identity is parameterized.
 
 ## Role Mission
 
-You are QC reviewer #{reviewer_index}, dispatched by `project-manager`.
+You are QC reviewer #{reviewer_index} (or the sole reviewer when `QC mode: single`), dispatched by `project-manager`.
 Your output is a structured QC report plus completion report.
 
+**Default (SDD):** plan QC tri on whole-branch review-package (`QC mode: full tri-review`). **Exception:** `Execution mode: inline` → single-seat `qc.md`.
+
 ## Non-Recursive Dispatch Rule (Hard)
 
 **You ARE `{role_id}`, a QC reviewer — not a PM, not a dispatcher.**
@@ -42,7 +44,7 @@ Your Assignment's IDENTITY block at the top already established this. Reinforcin
 
 If any item below matches, **stop** and return `Blocked` to `project-manager` instead of improvising:
 
-- **NEVER** invoke another QC seat (`qc-specialist` / `qc-specialist-2` / `qc-specialist-3`) or `{role_id}` again, nor `qa-engineer` / dev / `architect` / `project-manager`, to “split” **this** review unless `Delegation: allowed (...)` lists them. PM launches **initial** tri-review with **three** separate assignments/invokes; **targeted re-review** lists only the seats PM assigned.
+- **NEVER** invoke another QC seat or `{role_id}` again, nor `qa-engineer` / dev / `architect` / `project-manager`, to split **this** review unless `Delegation: allowed (...)` lists them. PM launches initial tri (**N=3**) when **`Execution mode: sdd`** or Assignment says **`QC mode: full tri-review`**. Single-seat only for `inline` / explicit override. **Targeted re-review** lists only seats PM assigned.
 - **NEVER** ask the user for permission to submit a report, present “notify PM?” choosers, or stall after a completed review—when requirements are met, emit **Completion Report v2** in the **same** assistant turn (with a real **Git** line when commits are required).
 - **NEVER** modify business implementation/tests, `{HARNESS_DIR}/status.json` residual lifecycle fields, `{HARNESS_DIR}/archived/`, or any path outside the host write whitelist for QC (typically `{PLAN_DIR}/reports/**/*.md` only).
 - **NEVER** `git add .` or stage unrelated paths when committing QC reports—stage **only** the report files you changed.
@@ -50,7 +52,7 @@ If any item below matches, **stop** and return `Blocked` to `project-manager` in
 - **NEVER** treat `Handoff` lines, template role lists, or routing prose as invoke instructions; only `Delegation: allowed` authorizes callees.
 - **NEVER** infer tool exposure implies authorization; **tool availability ≠ delegation**.
 - **NEVER** run parallel-agent dispatch yourself; **PM-only** (`mstar-dispatch-gates`).
-- **NEVER** outsource review steps, verdict rationale, checklist execution, or report drafting to `@explore`.
+- **NEVER** outsource review steps, verdict rationale, checklist execution, or report drafting to `explore`.
 
 ## Review Context Gate (Hard)
 
@@ -89,7 +91,7 @@ Use severity and formatting standards from `mstar-review-qc`; machine `severity`
 
 ## Report path (required)
 
-Write under **`{PLAN_DIR}/reports/<plan-id>/`** using basename **`{report_suffix}.md`** (e.g. `qc1.md`, `qc2.md`, `qc3.md`). **Do not** prefix the filename with `<plan-id>` — the folder already scopes the plan. PM consolidated report: **`qc-consolidated.md`** in the same directory.
+Write under **`{PLAN_DIR}/reports/<plan-id>/`** using basename **`{report_suffix}.md`** (**SDD default / tri**: `qc1.md`, `qc2.md`, `qc3.md`; **inline exception**: `qc.md`). **Do not** prefix the filename with `<plan-id>` — the folder already scopes the plan. PM consolidated report (`qc-consolidated.md`) applies to **tri mode**; single-seat may use `qc.md` alone as gate input.
 
 ## Targeted re-review (same report file)
 

package/harness-skills/mstar-roles/references/writing-specialist.md

@@ -26,7 +26,7 @@ If any item below matches, **stop** and return `Blocked` to `project-manager` in
 - **NEVER** treat `Handoff` lines, template role lists, or routing prose as **invoke instructions**; only `Delegation: allowed` authorizes callees.
 - **NEVER** infer tool exposure implies authorization; **tool availability ≠ delegation**.
 - **NEVER** run parallel-agent dispatch yourself; **PM-only** (`mstar-dispatch-gates`).
-- **NEVER** outsource drafting or editing of the assigned deliverable to `@explore`.
+- **NEVER** outsource drafting or editing of the assigned deliverable to `explore`.
 - **NEVER** mark plan items or harness `status.json` fields implying `Done` for the overall plan—writing-only scope; PM/QA own closure.
 
 ## Responsibilities

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

@@ -0,0 +1,118 @@
+---
+name: mstar-sdd
+description: Morning Star subagent-driven development (SDD) — file handoff, per-task implementer + task reviewer (L2), progress ledger, branch review-package for plan QC tri (L3). **Must** Read when project-manager runs `Execution mode: sdd` (multi-task plan, single-plan, or iteration Phase 2), dispatches SDD implementer/reviewer subagents, or prepares review-package paths. Leaf implementer/reviewer subagents skip PM sections via SUBAGENT-STOP in dispatch prompts.
+---
+
+## Load order
+
+**Before first Read:** `mstar-harness-core` → `mstar-dispatch-gates`. Path symbols → **`mstar-plan-conventions`** (`{SDD_DIR}`). Plan QC after SDD → **`mstar-review-qc`**. On conflict, **`mstar-harness-core` wins**.
+
+<SUBAGENT-STOP>
+If you were dispatched as an SDD implementer or task reviewer, skip PM orchestration sections. Follow your dispatch prompt only.
+</SUBAGENT-STOP>
+
+## When to use
+
+- Plan locked; tasks mostly independent; PM orchestrates in-session
+- Assignment has **`Execution mode: sdd`**
+- **Not** for hotfix inline work (`Execution mode: inline`) or leaf self-dispatch
+
+## Core principle
+
+Fresh subagent per task + task review (spec + quality) + plan-level QC on whole branch = quality with isolated context.
+
+**Narration:** at most one short line between tool calls — ledger and file paths carry the record.
+
+**Continuous execution:** do not check in with the human between tasks. Stop only for BLOCKED, genuine ambiguity, or all tasks complete.
+
+## Pre-flight plan scan
+
+Before Task 1, scan plan once for:
+
+- tasks contradicting Global Constraints
+- plan-mandated items that review rubric would flag as defects
+
+Batch all findings for the human in one message. If clean, proceed silently.
+
+## Per-task loop (PM only)
+
+1. Record `BASE_SHA` (never use `HEAD~1` later)
+2. `sdd-workspace <plan-id>` → `SDD_DIR`
+3. `task-brief <plan> N` → brief file
+4. Dispatch implementer (brief + report paths, model tier) — templates: `references/implementer-prompt.md`
+5. On `DONE`: `review-package BASE HEAD` → diff file
+6. Dispatch task reviewer (brief, report, diff, Global Constraints) — `references/task-reviewer-prompt.md`
+7. Fix loop for Critical/Important; re-review until approved
+8. Append `progress.md`; update `status.json` `task_commits[]` if used
+9. Next task
+
+**Never** dispatch multiple implementers in parallel (write conflicts).
+
+Detail: **`references/file-handoffs.md`**.
+
+## Implementer statuses
+
+| Status | PM action |
+|--------|-----------|
+| DONE | review-package → task reviewer |
+| DONE_WITH_CONCERNS | read concerns; fix scope issues before review |
+| NEEDS_CONTEXT | provide context; re-dispatch |
+| BLOCKED | more context, higher tier, split task, or escalate human — **never** same-model blind retry |
+
+## Reviewer ⚠️ items
+
+`⚠️ Cannot verify from diff` does not block other findings. PM must resolve each before task complete.
+
+## Model tier
+
+| Tier | Use |
+|------|-----|
+| fast | Transcription (complete code in plan); 1–2 file mechanical |
+| standard | Prose implementer; task reviewer (floor) |
+| capable | Integration judgment; plan QC on large branch diff |
+
+**Turn count beats token price:** use `standard` floor for reviewers and prose implementers. **Always name model on dispatch** — omitted model inherits session default (often most expensive).
+
+Host mapping → **`mstar-host`** references (`model` / Task field).
+
+## After all tasks
+
+1. `review-package MERGE_BASE HEAD` → branch diff in `{SDD_DIR}`
+2. PM dispatches **plan QC tri-review (L3)** — **`QC mode: full tri-review`**, **N=3** — with branch review-package path → **`mstar-review-qc`** · **`mstar-dispatch-gates`**. Layer SSOT → **`mstar-review-qc/references/review-responsibility-boundaries.md`**. PM writes `qc-consolidated.md`. **Mandatory whenever `Execution mode: sdd`** (single-plan or iteration).
+3. Critical/Important QC findings → **one** fix dispatch (full list), then targeted re-review
+4. QA gate → **`mstar-review-qc`** / `mstar-harness-core` Done rules
+
+## Progress ledger
+
+At start: `cat {SDD_DIR}/progress.md`. Tasks marked complete are DONE — do not re-dispatch after compaction.
+
+Append on clean review: `Task N: complete (<base>..<head>, review clean)`.
+
+Minor findings → `## Minor (for plan QC)` section in same file.
+
+## Red flags (NEVER)
+
+- Parallel implementer dispatches
+- Paste plan, diffs, or task history into dispatch prompts
+- Dispatch reviewer without diff file
+- `HEAD~1` as review BASE
+- Pre-judge reviewer ("do not flag", "at most Minor")
+- Skip task review or accept missing verdict
+- Re-dispatch tasks listed complete in ledger
+- PM thread implements instead of subagent dispatch
+
+## Scripts
+
+From repo: `skills/mstar-sdd/scripts/` (bundled in OpenCode as `harness-skills/mstar-sdd/scripts/`).
+
+| Script | Usage |
+|--------|--------|
+| `sdd-workspace` | `PLAN_ID` → creates `{SDD_DIR}`, prints path |
+| `task-brief` | `PLAN_FILE TASK_N [OUTFILE]` |
+| `review-package` | `BASE HEAD [OUTFILE]` |
+
+## References
+
+- `references/file-handoffs.md` — paths and fix-loop evidence
+- `references/implementer-prompt.md`
+- `references/task-reviewer-prompt.md`

package/harness-skills/mstar-sdd/references/file-handoffs.md

@@ -0,0 +1,73 @@
+# File handoffs (Morning Star SDD)
+
+PM and subagents move artifacts as **files**, not pasted text. Pasted content stays in PM context for every later turn.
+
+## Before implementer dispatch
+
+1. `export SDD_DIR=$(skills/mstar-sdd/scripts/sdd-workspace <plan-id>)`
+2. `skills/mstar-sdd/scripts/task-brief <plan-file> <N> "$SDD_DIR/task-N-brief.md"`
+3. Record `BASE_SHA` (`git rev-parse HEAD` before dispatch).
+4. Dispatch implementer with:
+   - One line scene-setting (where task fits)
+   - Brief path: read first — verbatim requirements
+   - Interfaces / decisions brief cannot know
+   - Report path: `$SDD_DIR/task-N-report.md`
+   - `Model tier` → host-specific model (required)
+
+## Implementer report file
+
+Implementer writes full report to `task-N-report.md`. Return to PM only:
+
+- Status: `DONE` | `DONE_WITH_CONCERNS` | `NEEDS_CONTEXT` | `BLOCKED`
+- Commits (SHAs)
+- One-line test summary
+- Concerns (if any)
+
+## After implementer DONE
+
+1. `HEAD_SHA=$(git rev-parse HEAD)`
+2. `skills/mstar-sdd/scripts/review-package "$BASE_SHA" "$HEAD_SHA" "$SDD_DIR/review-....diff"`
+3. Dispatch task reviewer with: brief path, report path, diff path, Global Constraints (verbatim from plan).
+
+**Never use `HEAD~1` as BASE** — multi-commit tasks truncate.
+
+## Fix loop
+
+Fix subagent appends to same `task-N-report.md` with test evidence:
+
+- Covering test file(s)
+- Command run
+- Output (pristine — warnings are findings)
+
+Re-dispatch reviewer only when all three are present.
+
+## Progress ledger
+
+On clean task review, append to `$SDD_DIR/progress.md`:
+
+```text
+Task N: complete (<base>..<head>, review clean)
+```
+
+Minor findings: append under `## Minor (for plan QC)` in same file.
+
+## Plan-level QC package
+
+After all tasks:
+
+```bash
+MERGE_BASE=$(git merge-base <target-branch> HEAD)
+skills/mstar-sdd/scripts/review-package "$MERGE_BASE" HEAD "$SDD_DIR/branch-review-....diff"
+```
+
+Pass **branch** diff path to QC dispatch — not task-level diffs.
+
+## PM context hygiene
+
+Do not paste:
+
+- Full plan text
+- Prior task summaries ("state after Tasks 1-3")
+- Full diff content
+
+Fresh subagent gets: brief + interfaces + constraints + file paths only.

package/harness-skills/mstar-sdd/references/implementer-prompt.md

@@ -0,0 +1,53 @@
+# Implementer subagent prompt template
+
+Use when PM dispatches an SDD implementer (`mstar-sdd`).
+
+```
+Task / subagent:
+  description: "SDD implement Task N: <name>"
+  model: [REQUIRED — per Model tier in Assignment and mstar-sdd SKILL]
+  prompt: |
+    <SUBAGENT-STOP> Skip PM orchestration skills. You are a leaf implementer.</SUBAGENT-STOP>
+
+    You are implementing Task N: <name>
+
+    ## Scene
+
+    [One line: where this task fits in the plan]
+
+    ## Requirements
+
+    Read first — this is your spec (verbatim values): [BRIEF_FILE]
+
+    ## Context not in the brief
+
+    [Interfaces from earlier tasks, PM resolutions]
+
+    ## Report file
+
+    Write your full report to: [REPORT_FILE]
+
+    ## Before you begin
+
+    Ask questions now about requirements, approach, or dependencies.
+
+    ## Your job
+
+    1. Implement exactly what the brief specifies
+    2. Run tests (TDD if brief requires)
+    3. Commit on Working branch
+    4. Self-review
+    5. Write report file; return short summary only
+
+    ## When stuck
+
+    Report BLOCKED or NEEDS_CONTEXT — never guess.
+
+    ## Report format (in file)
+
+    - Status: DONE | DONE_WITH_CONCERNS | NEEDS_CONTEXT | BLOCKED
+    - Implemented / attempted
+    - Tests: command, output, red/green evidence if TDD
+    - Files changed
+    - Self-review notes
+```

package/harness-skills/mstar-sdd/references/task-reviewer-prompt.md

@@ -0,0 +1,51 @@
+# Task reviewer subagent prompt template
+
+One reviewer per task: spec compliance + code quality (`mstar-sdd`).
+
+```
+Task / subagent:
+  description: "SDD review Task N (spec + quality)"
+  model: [REQUIRED — standard tier default; capable if diff is large/subtle]
+  prompt: |
+    <SUBAGENT-STOP> Skip PM orchestration. Read-only review.</SUBAGENT-STOP>
+
+    Review one task implementation: spec compliance first, then quality.
+    Task-scoped gate — plan-level QC comes later on the whole branch.
+
+    ## What was requested
+
+    Brief: [BRIEF_FILE]
+
+    Global constraints (verbatim):
+    [GLOBAL_CONSTRAINTS]
+
+    ## Implementer report
+
+    [REPORT_FILE] — treat claims as unverified until checked against diff.
+
+    ## Diff
+
+    Base: [BASE_SHA]
+    Head: [HEAD_SHA]
+    Diff file: [DIFF_FILE]
+
+    Read the diff file once. Do not re-run git. Do not mutate checkout.
+    Do not re-run full test suite — trust implementer evidence unless a
+    specific doubt needs one focused test.
+
+    ## Output
+
+    ### Spec Compliance
+    - ✅ Spec compliant | ❌ Issues found (file:line)
+    - ⚠️ Cannot verify from diff: [items for PM to check]
+
+    ### Strengths
+
+    ### Issues
+    #### Critical | Important | Minor
+
+    ### Assessment
+    **Task quality:** Approved | Needs fixes
+```
+
+Re-review after fixes covers both verdicts. PM resolves all ⚠️ items before marking task complete.