Prefer Claude's Plan Mode over built-in planning when available (#2)

* Initial plan

* Prefer Claude's Plan Mode for planning, fall back to built-in process

Updated the planning workflow to prefer Claude's native Plan Mode
(available in Claude Code) when creating implementation plans. When
Plan Mode is not available (Cursor, Codex, OpenCode, etc.), falls
back to the plugin's built-in planning process.

Key changes:
- using-superpowers: Flow graph routes to writing-plans skill
  (with Plan Mode preference) instead of blocking Plan Mode
- writing-plans: New Plan Mode Detection section with instructions
  for using Claude's Plan Mode and saving output as a plan document
- brainstorming: Updated handoff to mention Plan Mode preference

The plan output format remains unchanged regardless of planning
method, ensuring downstream skills (alignment-check, executing-plans,
subagent-driven-development) continue to work correctly.

Co-authored-by: intel352 <77607+intel352@users.noreply.github.com>

* Fix: use consistent possessive form "Claude's Plan Mode" in flow graph

Co-authored-by: intel352 <77607+intel352@users.noreply.github.com>

* Address review feedback: fix flow graph dead-end and bullet capitalization

Co-authored-by: intel352 <77607+intel352@users.noreply.github.com>

---------

Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: intel352 <77607+intel352@users.noreply.github.com>

Author: Copilot

skills/brainstorming/SKILL.md

@@ -87,6 +87,7 @@ digraph brainstorming {
 **Autonomous handoff:**
 - This is the user's **last interaction point** — everything after runs autonomously
 - Invoke the writing-plans skill with autonomous context: the design is approved, no further user input needed
+- The writing-plans skill will prefer Claude's Plan Mode if available (Claude Code), falling back to its built-in planning process in other environments
 - The pipeline from here: writing-plans → alignment-check → team execution → PR creation → PR monitoring
 - Do NOT invoke any other skill. writing-plans is the next step. It handles the rest of the autonomous pipeline.
 

skills/using-superpowers/SKILL.md

@@ -29,6 +29,7 @@ digraph skill_flow {
     "About to EnterPlanMode?" [shape=doublecircle];
     "Already brainstormed?" [shape=diamond];
     "Invoke brainstorming skill" [shape=box];
+    "Invoke writing-plans skill\n(prefers Claude's Plan Mode)" [shape=box];
     "Might any skill apply?" [shape=diamond];
     "Invoke Skill tool" [shape=box];
     "Announce: 'Using [skill] to [purpose]'" [shape=box];
@@ -39,8 +40,9 @@ digraph skill_flow {
 
     "About to EnterPlanMode?" -> "Already brainstormed?";
     "Already brainstormed?" -> "Invoke brainstorming skill" [label="no"];
-    "Already brainstormed?" -> "Might any skill apply?" [label="yes"];
+    "Already brainstormed?" -> "Invoke writing-plans skill\n(prefers Claude's Plan Mode)" [label="yes"];
     "Invoke brainstorming skill" -> "Might any skill apply?";
+    "Invoke writing-plans skill\n(prefers Claude's Plan Mode)" -> "Might any skill apply?";
 
     "User message received" -> "Might any skill apply?";
     "Might any skill apply?" -> "Invoke Skill tool" [label="yes, even 1%"];

skills/writing-plans/SKILL.md

@@ -17,6 +17,24 @@ Assume they are a skilled developer, but know almost nothing about our toolset o
 
 **Save plans to:** `docs/plans/YYYY-MM-DD-<feature-name>.md`
 
+## Plan Mode Detection
+
+**Prefer Claude's Plan Mode when available.** If you are running in Claude Code and can enter Plan Mode (e.g. via `Shift+Tab` or the `/plan` command), use it to draft the implementation plan. If Claude's Plan Mode is not available (Cursor, Codex, OpenCode, or other environments), use the Built-In Planning Process below.
+
+### Using Claude's Plan Mode (Claude Code)
+
+1. **Enter Plan Mode** — explore the codebase, analyze the design, and draft the implementation plan using Claude's native Plan Mode
+2. **Follow the plan format below** — structure your Plan Mode output using the same Plan Document Header and Task Structure defined in this skill
+3. **Exit Plan Mode** — once the plan is fully drafted
+4. **Save the plan** — write the plan to `docs/plans/YYYY-MM-DD-<feature-name>.md` using the exact format from Plan Document Header and Task Structure sections below
+5. **Continue the pipeline** — proceed to Execution Handoff as normal
+
+The plan document you save MUST follow the same format described in Plan Document Header and Task Structure below, regardless of whether it was drafted in Plan Mode or with the built-in process. This ensures downstream skills (alignment-check, executing-plans, subagent-driven-development) work correctly.
+
+### Built-In Planning Process (Non-Claude Code)
+
+When Claude's Plan Mode is not available, use the full planning process described in the sections below to write the plan directly.
+
 ## Autonomous Mode
 
 When invoked from brainstorming with autonomous context (design already approved):