@leing2021/super-pi 0.32.0 → 0.33.0

package/README.md

@@ -190,7 +190,7 @@ Commit everything to git — these files are the project's traceable memory.
 | Tools | 12 CE + 10 Pi built-in |
 | Rules | 78 |
 | TypeScript lines | ~4,100 |
-| Tests | 219 (882 assertions) |
+| Tests | 219 (888 assertions) |
 
 Rules in `rules/` cover 12 common topics + language-specific sets (TypeScript, Rust, Go, Python, Java, Kotlin, C++, C#, Dart, Swift, Perl, PHP). Project-level overrides take priority; projects can also add new languages via a project-level `rules/language-detection.md` marker map (append + same-marker wins).
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@leing2021/super-pi",
-  "version": "0.32.0",
+  "version": "0.33.0",
   "private": false,
   "type": "module",
   "description": "Pi-native Compound Engineering package for iterative development workflows",

package/skills/02-plan/SKILL.md

@@ -22,7 +22,7 @@ See [shared pipeline instructions](../references/pipeline-config.md) for model r
    - Extract keywords → `grep -rl "tags:.*keyword" docs/solutions/ ~/.pi/agent/docs/solutions/`
    - Read **frontmatter** only (first 15 lines) of matches → score by severity + tag relevance
    - Fully read top 3 candidates
-5. Write plan to `docs/plans/`
+5. Write plan to `docs/plans/` with the `> Status: draft` header (closed vocabulary: draft → ready → executing → done → deprecated); flip to `ready` when the plan is finalized
 6. If plan exists, use **`plan_diff`** to compare and patch incrementally
 7. End by recommending `03-work`
 

package/skills/02-plan/references/plan-template.md

@@ -1,5 +1,11 @@
 # Plan
 
+> Status: draft
+
+<!-- Status 词表（封闭集，全小写）：draft → ready → executing → done → deprecated
+     02-plan 创建=draft；定稿=ready；03-work 执行中=executing；
+     04-review 通过+归档=done（移入 docs/plans/archive/）；人裁决作废=deprecated -->
+
 ## Problem summary
 
 Summarize the problem and the relevant requirements.
@@ -15,7 +21,7 @@ Define what is in and out of scope.
 ## Architecture decisions
 
 List any decisions that meet the ADR threshold (see `references/adr-template.md`).
-Link to `docs/adr/XXXX-slug.md` if created. If none qualify, state "No ADR-worthy decisions."
+Link to `docs/adr/XXXX-slug.md` if created. If none qualify, keep this heading and state "No ADR-worthy decisions."
 
 ## Implementation units
 

package/skills/03-work/SKILL.md

@@ -16,7 +16,7 @@ See [shared pipeline instructions](../references/pipeline-config.md) for model r
 3. **Distinguish input:** plan path vs bare prompt
 4. Derive tasks from plan **implementation units**
 5. **Execution mode:** **inline mode** — all plan units execute inline in the current session. No built-in subagent tools.
-6. Use **`session_checkpoint`** to track progress and enable resume
+6. Use **`session_checkpoint`** to track progress and enable resume; before executing a plan, flip its Status header to `executing`
 7. Use **`task_splitter`** to analyze dependencies before execution
 8. If in **worktree** (via `07-worktree`), execute inside it
 9. End by recommending `04-review`

package/skills/04-review/SKILL.md

@@ -51,6 +51,7 @@ Code review is **technical evaluation**, not social performance:
 3. **Evaluate** — is it sound for THIS codebase?
 4. **Act** — fix confirmed issues, push back on incorrect ones
 5. **Test** — verify each fix individually, no regressions
+6. **Close** — when findings are resolved and tests green, flip the reviewed plan's Status header to `done` and move it to `docs/plans/archive/` (skip if no plan artifact)
 
 ## Workflow