@mstar-harness/opencode 1.8.8 → 2.0.0

package/harness-skills/mstar-plan-conventions/references/harness-bootstrap-and-agents-layering.md

@@ -14,7 +14,7 @@
 
 1. 创建 `{HARNESS_DIR}`（推荐 `.mstar/`）与 `{PLAN_DIR}`（推荐 `.mstar/plans/`）。
 2. 初始化 `status.json`：从 **`mstar-plan-artifacts/templates/status.empty.json`** 复制；residual canonical 见 **`mstar-plan-artifacts` SKILL.md**；字段与生命周期见 **`mstar-plan-artifacts/references/status-and-residuals.md`**。
-3. 初始化可选 `notes.json`（**`mstar-plan-artifacts/templates/notes.empty.json`**）；`sdd/` 空目录占位（per-plan 子目录由 skill **`mstar-sdd`** → `scripts/sdd-workspace` 创建）。
+3. 初始化可选 `notes.json`（**`mstar-plan-artifacts/templates/notes.empty.json`**）；`sdd/` 空目录占位（per-plan 子目录由 **`mstar-sdd`** → `mstar sdd workspace <plan-id>` 创建）。
 4. 项目根 `.gitignore` 追加 Morning Star **进程产物**忽略集（canonical snippet → `mstar-plan-conventions` SKILL.md「Git 跟踪策略」；legacy `.agents/` 有等价表）。
 5. **Profile B**（统一 Done 压缩）时另建 `{HARNESS_DIR}/archived/plans/` 与 `archived/plans-done.json`（自 **`mstar-plan-artifacts/templates/plans-done.empty.json`** 复制；schema 仅 `{ "plans": [] }`，见 **`mstar-plan-artifacts/references/done-compaction.md`**）。
 6. 可选：创建 `{ITERATION_DIR}`（`iterations/` + `README.md`）与 `{KNOWLEDGE_DIR}`（`knowledge/` + `README.md`）；`{HARNESS_DIR}/specs/`（解析后的 `{SPECS_DIR}` 默认落点）；内容边界见 `mstar-plan-conventions` SKILL.md 与 `references/knowledge-and-designs.md`。

package/harness-skills/mstar-review-qc/SKILL.md

@@ -24,6 +24,8 @@ description: "Morning Star QC orchestration — **SDD mandatory plan QC tri-revi
 - **After `Request Changes` (default)**：**Targeted re-review** — PM dispatches only seats that **raised** blocking findings; each updates **the same** `{SDD_DIR}/review/qcN.md` (`## Revalidation`, update verdict). **Do not** spawn `qcN-rev2.md` for targeted re-review. Naming → **`mstar-plan-artifacts/references/plan-files-and-reports.md`** § QC 三审触发时机.
 - **Full tri re-review (exception)**：Assignment **`QC re-review: full tri-review`** → new basenames (`qc1-rev2.md` …); PM marks **active wave** in consolidated decision.
 
+> **Engine check (when available):** run `mstar review seats <assignment-file> [--mode sdd|inline|targeted] [--reviewers <role1,role2,...>]` (or `import { executionModeToN, assertTriIdentity } from "@mstar-harness/engine"` in a host hook) to map `Execution mode` to its QC seat count N above and assert tri identity. On `fail` -> do not proceed; fix and re-run. Skill text below remains authoritative when the runtime is absent.
+
 ## 三审身份与模型独立性门禁（PM 强制）
 
 在 PM 发出 **initial** QC 三审后、进入汇总前：

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

@@ -74,6 +74,8 @@ Role `references/*.md` files include explicit **`NEVER`** sections (anti-recursi
 
 PM consolidated (tri mode): `{SDD_DIR}/review/qc-consolidated.md` (same folder; no `<plan-id>` basename prefix) + durable main-plan summary. Naming SSOT: `mstar-plan-artifacts/references/plan-files-and-reports.md`.
 
+> **Engine check (when available):** import `validateRoleMapping` / `lintLoadOrder` from `@mstar-harness/engine` in a host hook to validate the mapping and parameter tables above against the on-disk `references/*.md` layout (shared families included) and lint the load-order declarations (no CLI form yet). On `fail` -> do not proceed; fix and re-run. Skill text below remains authoritative when the runtime is absent.
+
 ## Maintenance Rules
 
 - Edit behavior in `references/*.md`.

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

@@ -137,7 +137,7 @@ When `metadata.control_worktree_path` is set and worktree mode is **not** waived
 | **`Worktree path`** | Absolute **feature** checkout (`execution_lease.worktree_path`) — product/source edits only |
 | **`Control harness root`** | Absolute `<control_worktree_path>/{HARNESS_DIR}` |
 | **`Plan Path`** | Absolute under control harness (not relative from feature cwd) |
-| **`SDD dir`** | Absolute under control harness; run skill **`mstar-sdd`** → `scripts/sdd-workspace` with `MSTAR_CONTROL_ROOT=<control_worktree_path>` when cwd is the feature tree |
+| **`SDD dir`** | Absolute under control harness; run `mstar sdd workspace <plan-id>` with `MSTAR_CONTROL_ROOT=<control_worktree_path>` when cwd is the feature tree |
 
 Do **not** waive worktree because default-gitignored `plans/` are missing under the feature checkout — see `mstar-branch-worktree` 「Harness path SSOT under default gitignore」.
 ## Completion Report Template

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

@@ -23,6 +23,8 @@ If you were dispatched as an SDD implementer or task reviewer, skip PM orchestra
 
 **Optional:** **`SDD implementer session: sticky`** — same implementer subagent across sequential tasks on one plan/branch; **task reviewers stay fresh per task**. SSOT → **`references/sticky-implementer-session.md`**.
 
+> **Engine check (when available):** import `implementerSessionStickyRules` from `@mstar-harness/engine` in a host hook to validate the sticky resume decision above (no CLI form yet). On `fail` -> do not proceed; fix and re-run. Skill text below remains authoritative when the runtime is absent.
+
 **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.
@@ -39,12 +41,12 @@ 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. skill **`mstar-sdd`** → `scripts/sdd-workspace <plan-id>` → `SDD_DIR`（iteration L1 从 feature cwd 调用时：`MSTAR_CONTROL_ROOT=<control_worktree_path>` 或 `scripts/sdd-workspace <plan-id> <control_worktree_path>`；缺 status.json 的 linked worktree 会 fail closed）
-3. `scripts/task-brief <plan> N` → brief file
+2. `mstar sdd workspace <plan-id>` → `SDD_DIR`（iteration L1 从 feature cwd 调用时：`MSTAR_CONTROL_ROOT=<control_worktree_path>` 或 `mstar sdd workspace <plan-id> <control_worktree_path>`；缺 status.json 的 linked worktree 会 fail closed）
+3. `mstar sdd task-brief <plan> N` → brief file
 4. Dispatch implementer:
-   - **`SDD implementer session: fresh`** (default) — new subagent; templates: `references/implementer-prompt.md`
-   - **`SDD implementer session: sticky`** — first task: same as fresh + write `{SDD_DIR}/implementer-session.json` with `host_agent_id`; later tasks: host **resume** + `references/implementer-continuation-prompt.md` (see **`references/sticky-implementer-session.md`**)
-5. On `DONE`: `scripts/review-package BASE HEAD` → diff file
+    - **`SDD implementer session: fresh`** (default) — new subagent; templates: `references/implementer-prompt.md`
+    - **`SDD implementer session: sticky`** — first task: same as fresh + write `{SDD_DIR}/implementer-session.json` with `host_agent_id`; later tasks: host **resume** + `references/implementer-continuation-prompt.md` (see **`references/sticky-implementer-session.md`**)
+5. On `DONE`: `mstar sdd review-package BASE HEAD` → diff file
 6. Dispatch **fresh** task reviewer — role **`generalPurpose`** (L2; **not** `qc-specialist*`; host role field → `mstar-host` C5) — brief, report, diff, Global Constraints — `references/task-reviewer-prompt.md` — **never** sticky resume for reviewers
 7. Fix loop for Critical/Important; re-review until approved
 8. Append `progress.md`; update `status.json` `task_commits[]` and `implementer-session.json` `last_task` if sticky
@@ -54,6 +56,8 @@ Batch all findings for the human in one message. If clean, proceed silently.
 
 Detail: **`references/file-handoffs.md`**.
 
+> **Engine check (when available):** run `mstar sdd workspace <plan-id>` / `mstar sdd task-brief <plan-file> <task-number>` / `mstar sdd review-package <base> <head>` (or `import { assertBaseSha, sddWorkspace, taskBrief, reviewPackage } from "@mstar-harness/engine"` in a host hook) to drive the loop steps above. On `fail` -> do not proceed; fix and re-run. Skill text below remains authoritative when the runtime is absent.
+
 ## Implementer statuses
 
 | Status | PM action |
@@ -81,7 +85,7 @@ Host mapping → **`mstar-host`** references (`model` / Task field).
 
 ## After all tasks
 
-1. `scripts/review-package MERGE_BASE HEAD` → branch diff in `{SDD_DIR}/review/`
+1. `mstar sdd review-package MERGE_BASE HEAD` → branch diff in `{SDD_DIR}/review/`
 2. PM dispatches **plan QC tri-review (L3)** — **`QC mode: full tri-review`**, **N=3** — with branch review-package path and report paths under `{SDD_DIR}/review/` → **`mstar-review-qc`** · **`mstar-dispatch-gates`**. Layer SSOT → **`mstar-review-qc/references/review-responsibility-boundaries.md`**. PM writes `{SDD_DIR}/review/qc-consolidated.md` and durable main-plan gate summary. **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-harness-core`** Done rules; PM **`mstar-roles/references/project-manager/qa-trigger-matrix.md`**
@@ -94,6 +98,8 @@ Append on clean review: `Task N: complete (<base>..<head>, review clean)`.
 
 Minor findings → `## Minor (for plan QC)` section in same file.
 
+> **Engine check (when available):** import `readProgressLedger` from `@mstar-harness/engine` in a host hook to read the ledger above (no CLI form yet). On `fail` -> do not proceed; fix and re-run. Skill text below remains authoritative when the runtime is absent.
+
 ## Red flags (NEVER)
 
 - Parallel implementer dispatches
@@ -107,17 +113,15 @@ Minor findings → `## Minor (for plan QC)` section in same file.
 - Sticky **resume** for task reviewers
 - Resume implementer without `host_agent_id` in `implementer-session.json`
 
-## Scripts
-
-Scripts live under this skill: **`mstar-sdd`** → `scripts/<name>`.
+## CLI
 
-Resolve the loaded **`mstar-sdd`** skill directory first, then run the script by skill-relative path. **Do not** treat `skills/mstar-sdd/scripts/...` as a consumer-project cwd path — that layout exists only in the harness source tree (and OpenCode's bundled `harness-skills/mstar-sdd/scripts/`).
+The SDD helpers are engine-backed commands under **`mstar sdd`**（引擎 CLI；原 bash 脚本已移除，行为语义不变）。Run the `mstar` binary from any checkout; env vars `MSTAR_CONTROL_ROOT` / `MSTAR_HARNESS_DIR` / `SDD_DIR` are honored exactly as before.
 
-| Script | Usage |
+| Command | Usage |
 |--------|--------|
-| `scripts/sdd-workspace` | `PLAN_ID [CONTROL_ROOT]` → creates `{SDD_DIR}` under control harness when set (`MSTAR_CONTROL_ROOT` or 2nd arg); fail closed on linked worktree without `status.json` |
-| `scripts/task-brief` | `PLAN_FILE TASK_N [OUTFILE]` |
-| `scripts/review-package` | `BASE HEAD [OUTFILE]` |
+| `mstar sdd workspace` | `PLAN_ID [CONTROL_ROOT]` → creates `{SDD_DIR}` under control harness when set (`MSTAR_CONTROL_ROOT` or 2nd arg); fail closed on linked worktree without `status.json` |
+| `mstar sdd task-brief` | `PLAN_FILE TASK_N [OUTFILE]` |
+| `mstar sdd review-package` | `BASE HEAD [OUTFILE]` |
 
 ## References
 

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

@@ -4,14 +4,14 @@ PM and subagents move artifacts as **files**, not pasted text. Pasted content st
 
 ## Before implementer dispatch
 
-Resolve scripts from skill **`mstar-sdd`** → `scripts/…` (loaded skill directory). Do **not** run `skills/mstar-sdd/scripts/…` from a consumer project cwd.
+Run the SDD helpers through the engine CLI **`mstar sdd …`** (engine-backed; the former bash scripts are removed — semantics unchanged).
 
-1. `export SDD_DIR=$(<mstar-sdd>/scripts/sdd-workspace <plan-id>)`
-   - Iteration L1 (implementer cwd = feature worktree):  
-     `export MSTAR_CONTROL_ROOT=<control_worktree_path>`  
-     or `sdd-workspace <plan-id> <control_worktree_path>`  
+1. `export SDD_DIR=$(mstar sdd workspace <plan-id>)`
+   - Iteration L1 (implementer cwd = feature worktree):
+     `export MSTAR_CONTROL_ROOT=<control_worktree_path>`
+     or `mstar sdd workspace <plan-id> <control_worktree_path>`
      so `{SDD_DIR}` lands on the control harness (default-gitignored plans/status/sdd). Do not create a second SDD tree under the feature checkout.
-2. `<mstar-sdd>/scripts/task-brief <plan-file> <N> "$SDD_DIR/task-N-brief.md"`
+2. `mstar sdd task-brief <plan-file> <N> "$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)
@@ -33,7 +33,7 @@ Implementer writes full report to `task-N-report.md`. Return to PM only:
 ## After implementer DONE
 
 1. `HEAD_SHA=$(git rev-parse HEAD)`
-2. `<mstar-sdd>/scripts/review-package "$BASE_SHA" "$HEAD_SHA" "$SDD_DIR/review-....diff"`
+2. `mstar sdd 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.
@@ -65,7 +65,7 @@ After all tasks:
 ```bash
 MERGE_BASE=$(git merge-base <target-branch> HEAD)
 mkdir -p "$SDD_DIR/review"
-<mstar-sdd>/scripts/review-package "$MERGE_BASE" HEAD "$SDD_DIR/review/branch-review-....diff"
+mstar sdd review-package "$MERGE_BASE" HEAD "$SDD_DIR/review/branch-review-....diff"
 ```
 
 Pass **branch** diff path and bundle report paths (`$SDD_DIR/review/qc1.md` …) to QC dispatch — not task-level diffs. Raw QC/QA files stay in the gitignored review bundle; PM records durable summary and open residuals in **local** plan/`status.json` (session SSOT) and promotes cross-clone decisions into tracked knowledge/specs/`AGENTS.md` per `mstar-plan-conventions` git policy.

package/harness-skills/mstar-sdd/references/sticky-implementer-session.md

@@ -52,12 +52,12 @@ After each completed task review, PM sets `last_task` to N. **Do not** resume if
 
 Same as default SDD for artifacts and L2 review; only implementer dispatch differs:
 
-1. `task-brief` → `{SDD_DIR}/task-N-brief.md`
+1. `mstar sdd task-brief` → `{SDD_DIR}/task-N-brief.md`
 2. Record `BASE_SHA`
 3. **Implementer dispatch**
    - **First task** (`fresh` or sticky start): normal Task/subagent invoke → save `host_agent_id` to ledger
    - **Next tasks** (`sticky`): host **resume** with same `host_agent_id` + continuation prompt (`implementer-prompt.md` § Continuation)
-4. On `DONE` → `review-package` → **fresh** task reviewer (never resume reviewer)
+4. On `DONE` → `mstar sdd review-package` → **fresh** task reviewer (never resume reviewer)
 5. Append `progress.md`; update ledger `last_task`
 6. Next task
 

package/harness-skills/mstar-skill-authoring/SKILL.md

@@ -70,6 +70,8 @@ description: Use when...
 Bad：`Explains how to write plans with steps, tests, commits, and review gates.`  
 Better：`Use when a non-trivial task has a spec or requirements and needs a written implementation plan before code changes.`
 
+> **Engine check (when available):** run `mstar skill lint <skill-dir>` (or `import { lintFrontmatter, lintFiveQuestion } from "@mstar-harness/engine"` in a host hook) to lint the frontmatter contract and the five-question body contract above. On `fail` -> do not proceed; fix and re-run. Skill text below remains authoritative when the runtime is absent.
+
 ## 默认 Body 结构
 
 ```markdown
@@ -97,6 +99,8 @@ Agents 按 **skill 名** 发现 skill；文档若给出完整仓内相对路径
 
 在本 harness：解析方式见 **`mstar-host`** § Resolve loaded skill root（omp `skill://`、各宿主插件挂载等）。其它环境按当地 skill 安装约定解析。
 
+> **Engine check (when available):** import `resolveAssetPath` from `@mstar-harness/engine` in a host hook to resolve a skill-relative asset per the convention above (no CLI form yet). On `fail` -> do not proceed; fix and re-run. Skill text below remains authoritative when the runtime is absent.
+
 ## Progressive Disclosure
 
 1. Frontmatter：仅触发  

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

@@ -58,6 +58,8 @@ A good strategy document is opinionated and concise. It should fit in one screen
 <Major past decisions with context — why, not just what>
 ```
 
+> **Engine check (when available):** run `mstar lint <STRATEGY.md>` (or `import { lintStrategySections } from "@mstar-harness/engine"` in a host hook) to check the six required sections above (Vision, What we build, What we don't build, Guiding Principles, Technology Direction, Decision Log). On `fail` -> do not proceed; fix and re-run. Skill text below remains authoritative when the runtime is absent.
+
 ### Optional sections
 
 - **Current Focus** — what the team is working on now

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@mstar-harness/opencode",
-  "version": "1.8.8",
-  "description": "Morning Star harness OpenCode plugin (skills bootstrap and agent loading).",
+  "version": "2.0.0",
+  "description": "Morning Star harness OpenCode plugin — skills bootstrap + engine-backed runtime hooks (status lint, dispatch validation, Enforcement: hard gates).",
   "license": "MIT",
   "repository": {
     "type": "git",
@@ -23,6 +23,7 @@
   "scripts": {
     "bundle-assets": "bun run scripts/bundle-harness-assets.ts",
     "build": "bun run bundle-assets && rm -rf dist && bun build src/mstar.ts --target node --outfile dist/mstar.js",
+    "test": "bun test",
     "prepublishOnly": "bun run build"
   },
   "engines": {
@@ -33,5 +34,8 @@
   },
   "publishConfig": {
     "access": "public"
+  },
+  "devDependencies": {
+    "@mstar-harness/engine": "2.0.0"
   }
 }

package/harness-skills/mstar-plan-artifacts/scripts/tech-debt-rollup.sh

@@ -1,115 +0,0 @@
-#!/usr/bin/env bash
-# Read-only rollup of open residual_findings into tech_debt_summary aggregates.
-# Does not write status.json — PM applies output manually.
-set -euo pipefail
-
-STATUS_FILE="${1:-.mstar/status.json}"
-
-if [[ ! -f "$STATUS_FILE" ]]; then
-  echo "error: status file not found: $STATUS_FILE" >&2
-  exit 1
-fi
-
-if ! command -v jq >/dev/null 2>&1; then
-  echo "error: jq is required" >&2
-  exit 1
-fi
-
-# Merge canonical + legacy maps (canonical keys win). Legacy "warning" -> low.
-# Skip entries with lifecycle != open (default open when omitted).
-read -r -d '' JQ_FILTER <<'JQEOF' || true
-def norm_sev:
-  if . == "warning" then "low"
-  elif . == null or . == "" then "medium"
-  else .
-  end;
-
-def is_open:
-  (.lifecycle // "open") == "open";
-
-(.residual_findings // {}) as $canon
-| (.metadata.residual_findings // {}) as $legacy
-| ($canon + $legacy) as $merged
-| [
-    $merged
-    | to_entries[]
-    | .key as $plan
-    | .value[]
-    | select(is_open)
-    | . + { _plan_id: $plan }
-  ] as $items
-| {
-    total_open: ($items | length),
-    by_severity: (
-      ["critical", "high", "medium", "low", "nit"]
-      | map(. as $s
-        | { ($s): ([$items[] | select((.severity | norm_sev) == $s)] | length) })
-      | add
-    ),
-    by_target: (
-      $items
-      | map(.target // "unspecified")
-      | group_by(.)
-      | map({ key: .[0], value: length })
-      | from_entries
-    ),
-    by_plan: (
-      $items
-      | group_by(._plan_id)
-      | map({ key: .[0]._plan_id, value: length })
-      | from_entries
-    )
-  }
-JQEOF
-
-COMPUTED=$(jq -c "$JQ_FILTER" "$STATUS_FILE")
-STORED=$(jq -c '.metadata.tech_debt_summary // null' "$STATUS_FILE")
-
-echo "=== tech_debt_summary (computed from open residual_findings) ==="
-echo "$COMPUTED" | jq '.'
-
-echo ""
-echo "=== stored metadata.tech_debt_summary ==="
-if [[ "$STORED" == "null" ]]; then
-  echo "(none)"
-else
-  echo "$STORED" | jq '.'
-fi
-
-echo ""
-echo "=== consistency check ==="
-
-compare_field() {
-  local field="$1"
-  local computed stored
-  computed=$(echo "$COMPUTED" | jq -c ".$field")
-  if [[ "$STORED" == "null" ]]; then
-    echo "DRIFT: no stored tech_debt_summary (computed $field = $computed)"
-    return 1
-  fi
-  stored=$(echo "$STORED" | jq -c ".$field // null")
-  if [[ "$computed" == "$stored" ]]; then
-    echo "PASS: $field"
-    return 0
-  fi
-  echo "DRIFT: $field"
-  echo "  computed: $computed"
-  echo "  stored:   $stored"
-  return 1
-}
-
-FAIL=0
-compare_field total_open || FAIL=1
-compare_field by_severity || FAIL=1
-compare_field by_target || FAIL=1
-compare_field by_plan || FAIL=1
-
-if [[ "$FAIL" -eq 0 ]]; then
-  echo ""
-  echo "OVERALL: PASS"
-  exit 0
-fi
-
-echo ""
-echo "OVERALL: DRIFT — refresh metadata.tech_debt_summary in status.json"
-exit 1

package/harness-skills/mstar-sdd/scripts/review-package

@@ -1,43 +0,0 @@
-#!/usr/bin/env bash
-# Write commit list, stat summary, and diff to a file for reviewer Read.
-# Usage: review-package BASE HEAD [OUTFILE]
-# Never use HEAD~1 as BASE for multi-commit tasks.
-set -euo pipefail
-
-if [ $# -lt 2 ] || [ $# -gt 3 ]; then
-  echo "usage: review-package BASE HEAD [OUTFILE]" >&2
-  exit 2
-fi
-
-base=$1
-head=$2
-
-git rev-parse --verify --quiet "$base" >/dev/null || { echo "bad BASE: $base" >&2; exit 2; }
-git rev-parse --verify --quiet "$head" >/dev/null || { echo "bad HEAD: $head" >&2; exit 2; }
-
-if [ $# -eq 3 ]; then
-  out=$3
-else
-  if [ -z "${SDD_DIR:-}" ]; then
-    echo "review-package: set SDD_DIR or pass OUTFILE" >&2
-    exit 2
-  fi
-  mkdir -p "$SDD_DIR"
-  out="$SDD_DIR/review-$(git rev-parse --short "$base")..$(git rev-parse --short "$head").diff"
-fi
-
-{
-  echo "# Review package: ${base}..${head}"
-  echo
-  echo "## Commits"
-  git log --oneline "${base}..${head}"
-  echo
-  echo "## Files changed"
-  git diff --stat "${base}..${head}"
-  echo
-  echo "## Diff"
-  git diff -U10 "${base}..${head}"
-} > "$out"
-
-commits=$(git rev-list --count "${base}..${head}" 2>/dev/null || echo 0)
-echo "wrote ${out}: ${commits} commit(s), $(wc -c < "$out" | tr -d ' ') bytes"

package/harness-skills/mstar-sdd/scripts/sdd-workspace

@@ -1,90 +0,0 @@
-#!/usr/bin/env bash
-# Resolve and ensure {SDD_DIR} for Morning Star SDD artifacts.
-# Usage: sdd-workspace PLAN_ID [CONTROL_ROOT]
-#   CONTROL_ROOT — optional absolute repo root of the control worktree
-#   (or set MSTAR_CONTROL_ROOT). Required when cwd is a linked feature
-#   worktree that lacks harness status.json (default gitignore).
-# Prints absolute path to {HARNESS_DIR}/sdd/<plan-id>/ (or legacy .agents/sdd/).
-set -euo pipefail
-
-if [ $# -lt 1 ] || [ $# -gt 2 ]; then
-  echo "usage: sdd-workspace PLAN_ID [CONTROL_ROOT]" >&2
-  echo "  Set MSTAR_CONTROL_ROOT=<control_worktree_path> when running from a feature worktree." >&2
-  exit 2
-fi
-
-plan_id=$1
-control_root="${2:-${MSTAR_CONTROL_ROOT:-}}"
-
-abs_dir() {
-  (cd "$1" && pwd -P)
-}
-
-if [ -n "$control_root" ]; then
-  if [ ! -d "$control_root" ]; then
-    echo "sdd-workspace: CONTROL_ROOT / MSTAR_CONTROL_ROOT is not a directory: $control_root" >&2
-    exit 1
-  fi
-  root=$(abs_dir "$control_root")
-else
-  root=$(git rev-parse --show-toplevel 2>/dev/null || pwd)
-  root=$(abs_dir "$root")
-fi
-
-resolve_harness_with_status() {
-  local r=$1
-  if [ -f "$r/.mstar/status.json" ]; then
-    printf '%s\n' "$r/.mstar"
-    return 0
-  fi
-  if [ -f "$r/.agents/status.json" ]; then
-    printf '%s\n' "$r/.agents"
-    return 0
-  fi
-  return 1
-}
-
-# Linked worktree from `git worktree add`: --git-dir ≠ --git-common-dir
-is_linked_worktree() {
-  local r=$1
-  local git_dir common
-  git_dir=$(git -C "$r" rev-parse --git-dir 2>/dev/null) || return 1
-  common=$(git -C "$r" rev-parse --git-common-dir 2>/dev/null) || return 1
-  case "$git_dir" in
-    /*) ;;
-    *) git_dir="$r/$git_dir" ;;
-  esac
-  case "$common" in
-    /*) ;;
-    *) common="$r/$common" ;;
-  esac
-  # Path contains /worktrees/ → definitely linked
-  case "$git_dir" in
-    */.git/worktrees/*|*/worktrees/*) return 0 ;;
-  esac
-  local gd_parent cm_abs
-  gd_parent=$(abs_dir "$(dirname "$git_dir")")
-  cm_abs=$(abs_dir "$common")
-  [ "$gd_parent/$(basename "$git_dir")" != "$cm_abs" ] && [ "$git_dir" != "$cm_abs" ]
-}
-
-if harness=$(resolve_harness_with_status "$root"); then
-  :
-elif [ -z "$control_root" ] && is_linked_worktree "$root"; then
-  echo "sdd-workspace: linked worktree at $root has no {HARNESS_DIR}/status.json (default gitignore)." >&2
-  echo "  Refusing to create a second SDD tree under the feature checkout." >&2
-  echo "  Re-run with MSTAR_CONTROL_ROOT=<control_worktree_path> or: sdd-workspace $plan_id <control_worktree_path>" >&2
-  echo "  See mstar-branch-worktree «Harness path SSOT under default gitignore»." >&2
-  exit 1
-elif [ -d "$root/.mstar" ]; then
-  harness="$root/.mstar"
-elif [ -d "$root/.agents" ]; then
-  harness="$root/.agents"
-else
-  harness="$root/.mstar"
-fi
-
-dir="$harness/sdd/$plan_id"
-mkdir -p "$dir"
-printf '*\n' > "$dir/.gitignore"
-cd "$dir" && pwd

package/harness-skills/mstar-sdd/scripts/task-brief

@@ -1,40 +0,0 @@
-#!/usr/bin/env bash
-# Extract one task's full text from a plan into a file for the implementer.
-# Usage: task-brief PLAN_FILE TASK_NUMBER [OUTFILE]
-# Default OUTFILE: {SDD_DIR}/task-N-brief.md (SDD_DIR from env or second arg via sdd-workspace)
-set -euo pipefail
-
-if [ $# -lt 2 ] || [ $# -gt 3 ]; then
-  echo "usage: task-brief PLAN_FILE TASK_NUMBER [OUTFILE]" >&2
-  exit 2
-fi
-
-plan=$1
-n=$2
-[ -f "$plan" ] || { echo "no such plan file: $plan" >&2; exit 2; }
-
-if [ $# -eq 3 ]; then
-  out=$3
-else
-  if [ -z "${SDD_DIR:-}" ]; then
-    echo "task-brief: set SDD_DIR or pass OUTFILE (run sdd-workspace PLAN_ID first)" >&2
-    exit 2
-  fi
-  mkdir -p "$SDD_DIR"
-  out="$SDD_DIR/task-${n}-brief.md"
-fi
-
-awk -v n="$n" '
-  /^```/ { infence = !infence }
-  !infence && /^#+[ \t]+Task[ \t]+[0-9]+/ {
-    intask = ($0 ~ ("^#+[ \t]+Task[ \t]+" n "([^0-9]|$)"))
-  }
-  intask { print }
-' "$plan" > "$out"
-
-if [ ! -s "$out" ]; then
-  echo "task ${n} not found in ${plan} (no heading matching Task ${n})" >&2
-  exit 3
-fi
-
-echo "wrote ${out}: $(wc -l < "$out" | tr -d ' ') lines"