Add end-to-end brainstorm handoff test

8-turn brainstorming flow that tests whether Claude invokes writing-plans
(correct) or EnterPlanMode (bug) after design approval. Includes
--without-fix mode for failure reproduction attempts.

.gitattributes

@@ -1,6 +1,5 @@
 # Ensure shell scripts always have LF line endings
 *.sh text eol=lf
-hooks/session-start text eol=lf
 
 # Ensure the polyglot wrapper keeps LF (it's parsed by both cmd and bash)
 *.cmd text eol=lf

docs/README.codex.md

@@ -32,12 +32,6 @@ Fetch and follow instructions from https://raw.githubusercontent.com/obra/superp
 
 3. Restart Codex.
 
-4. **For subagent skills** (optional): Skills like `dispatching-parallel-agents` and `subagent-driven-development` require Codex's collab feature. Add to your Codex config:
-   ```toml
-   [features]
-   collab = true
-   ```
-
 ### Windows
 
 Use a junction instead of a symlink (works without Developer Mode):

hooks/hooks.json

@@ -6,7 +6,7 @@
         "hooks": [
           {
             "type": "command",
-            "command": "${CLAUDE_PLUGIN_ROOT}/hooks/run-hook.cmd session-start",
+            "command": "${CLAUDE_PLUGIN_ROOT}/hooks/session-start.sh",
             "async": true
           }
         ]

hooks/run-hook.cmd

@@ -1,46 +1,43 @@
 : << 'CMDBLOCK'
 @echo off
-REM Cross-platform polyglot wrapper for hook scripts.
+REM ============================================================================
-REM On Windows: cmd.exe runs the batch portion, which finds and calls bash.
+REM DEPRECATED: This polyglot wrapper is no longer used as of Claude Code 2.1.x
-REM On Unix: the shell interprets this as a script (: is a no-op in bash).
+REM ============================================================================
 REM
-REM Hook scripts use extensionless filenames (e.g. "session-start" not
+REM Claude Code 2.1.x changed the Windows execution model for hooks:
-REM "session-start.sh") so Claude Code's Windows auto-detection -- which
-REM prepends "bash" to any command containing .sh -- doesn't interfere.
 REM
+REM   Before (2.0.x): Hooks ran with shell:true, using the system default shell.
+REM                   This wrapper provided cross-platform compatibility by
+REM                   being both a valid .cmd file (Windows) and bash script.
+REM
+REM   After (2.1.x):  Claude Code now auto-detects .sh files in hook commands
+REM                   and prepends "bash " on Windows. This broke the wrapper
+REM                   because the command:
+REM                     "run-hook.cmd" session-start.sh
+REM                   became:
+REM                     bash "run-hook.cmd" session-start.sh
+REM                   ...and bash cannot execute a .cmd file.
+REM
+REM The fix: hooks.json now calls session-start.sh directly. Claude Code 2.1.x
+REM handles the bash invocation automatically on Windows.
+REM
+REM This file is kept for reference and potential backward compatibility.
+REM ============================================================================
+REM
+REM Original purpose: Polyglot wrapper to run .sh scripts cross-platform
 REM Usage: run-hook.cmd <script-name> [args...]
+REM The script should be in the same directory as this wrapper
 
 if "%~1"=="" (
     echo run-hook.cmd: missing script name >&2
     exit /b 1
 )
-
+"C:\Program Files\Git\bin\bash.exe" -l "%~dp0%~1" %2 %3 %4 %5 %6 %7 %8 %9
-set "HOOK_DIR=%~dp0"
+exit /b
-
-REM Try Git for Windows bash in standard locations
-if exist "C:\Program Files\Git\bin\bash.exe" (
-    "C:\Program Files\Git\bin\bash.exe" "%HOOK_DIR%%~1" %2 %3 %4 %5 %6 %7 %8 %9
-    exit /b %ERRORLEVEL%
-)
-if exist "C:\Program Files (x86)\Git\bin\bash.exe" (
-    "C:\Program Files (x86)\Git\bin\bash.exe" "%HOOK_DIR%%~1" %2 %3 %4 %5 %6 %7 %8 %9
-    exit /b %ERRORLEVEL%
-)
-
-REM Try bash on PATH (e.g. user-installed Git Bash, MSYS2, Cygwin)
-where bash >nul 2>nul
-if %ERRORLEVEL% equ 0 (
-    bash "%HOOK_DIR%%~1" %2 %3 %4 %5 %6 %7 %8 %9
-    exit /b %ERRORLEVEL%
-)
-
-REM No bash found - exit silently rather than error
-REM (plugin still works, just without SessionStart context injection)
-exit /b 0
 CMDBLOCK
 
-# Unix: run the named script directly
+# Unix shell runs from here
-SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]:-$0}")" && pwd)"
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
 SCRIPT_NAME="$1"
 shift
-exec bash "${SCRIPT_DIR}/${SCRIPT_NAME}" "$@"
+"${SCRIPT_DIR}/${SCRIPT_NAME}" "$@"

skills/brainstorming/SKILL.md

@@ -58,11 +58,9 @@ After writing the spec document:
 3. If loop exceeds 5 iterations, surface to human for guidance
 
 **Implementation (if continuing):**
-- Ask: "Ready to set up for implementation?"
+When the user approves the design and wants to build:
-- Use superpowers:using-git-worktrees to create isolated workspace
+1. **Invoke `superpowers:writing-plans` using the Skill tool.** Not EnterPlanMode. Not plan mode. Not direct implementation. The Skill tool.
-- **REQUIRED:** Use superpowers:writing-plans to create detailed implementation plan
+2. After the plan is written, use superpowers:using-git-worktrees to create an isolated workspace for implementation.
-  - Do NOT use platform planning features (e.g., EnterPlanMode, plan mode)
-  - Do NOT start implementing directly - the writing-plans skill comes first
 
 ## Key Principles
 

skills/using-superpowers/SKILL.md

@@ -3,10 +3,6 @@ name: using-superpowers
 description: Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
 ---
 
-<SUBAGENT-STOP>
-If you were dispatched as a subagent to execute a specific task, skip this skill.
-</SUBAGENT-STOP>
-
 <EXTREMELY-IMPORTANT>
 If you think there is even a 1% chance a skill might apply to what you are doing, you ABSOLUTELY MUST invoke the skill.
 
@@ -31,10 +27,6 @@ If CLAUDE.md says "don't use TDD" and a skill says "always use TDD," follow CLAU
 
 **In other environments:** Check your platform's documentation for how skills are loaded.
 
-## Platform Adaptation
-
-Skills use Claude Code tool names. Non-CC platforms: see `references/codex-tools.md` for tool equivalents.
-
 # Using Skills
 
 ## The Rule
@@ -81,6 +73,7 @@ These thoughts mean STOP—you're rationalizing:
 | "I'll just do this one thing first" | Check BEFORE doing anything. |
 | "This feels productive" | Undisciplined action wastes time. Skills prevent this. |
 | "I know what that means" | Knowing the concept ≠ using the skill. Invoke it. |
+| "I should use EnterPlanMode / plan mode" | If a loaded skill specifies the next step, follow the skill. EnterPlanMode is a platform default — skills override defaults. |
 
 ## Skill Priority
 

skills/using-superpowers/references/codex-tools.md

@@ -1,25 +0,0 @@
-# Codex Tool Mapping
-
-Skills use Claude Code tool names. When you encounter these in a skill, use your platform equivalent:
-
-| Skill references | Codex equivalent |
-|-----------------|------------------|
-| `Task` tool (dispatch subagent) | `spawn_agent` |
-| Multiple `Task` calls (parallel) | Multiple `spawn_agent` calls |
-| Task returns result | `wait` |
-| Task completes automatically | `close_agent` to free slot |
-| `TodoWrite` (task tracking) | `update_plan` |
-| `Skill` tool (invoke a skill) | Skills load natively — just follow the instructions |
-| `Read`, `Write`, `Edit` (files) | Use your native file tools |
-| `Bash` (run commands) | Use your native shell tools |
-
-## Subagent dispatch requires collab
-
-Add to your Codex config (`~/.codex/config.toml`):
-
-```toml
-[features]
-collab = true
-```
-
-This enables `spawn_agent`, `wait`, and `close_agent` for skills like `dispatching-parallel-agents` and `subagent-driven-development`.

skills/writing-plans/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: writing-plans
-description: Use when you have a spec or requirements for a multi-step task, before touching code
+description: Use when you have a spec or requirements for a multi-step task, before touching code. After brainstorming, ALWAYS use this — not EnterPlanMode or plan mode.
 ---
 
 # Writing Plans
@@ -13,7 +13,7 @@ Assume they are a skilled developer, but know almost nothing about our toolset o
 
 **Announce at start:** "I'm using the writing-plans skill to create the implementation plan."
 
-**Context:** This should be run in a dedicated worktree (created by brainstorming skill).
+**Context:** This runs in the main workspace after brainstorming, while context is fresh. The worktree is created afterward for implementation.
 
 **Save plans to:** `docs/superpowers/plans/YYYY-MM-DD-<feature-name>.md`
 - (User preferences for plan location override this default)

tests/claude-code/run-skill-tests.sh

@@ -58,6 +58,7 @@ while [[ $# -gt 0 ]]; do
             echo ""
             echo "Tests:"
             echo "  test-subagent-driven-development.sh  Test skill loading and requirements"
+            echo "  test-brainstorm-handoff.sh           Test brainstorm→writing-plans handoff"
             echo ""
             echo "Integration Tests (use --integration):"
             echo "  test-subagent-driven-development-integration.sh  Full workflow execution"
@@ -74,6 +75,7 @@ done
 # List of skill tests to run (fast unit tests)
 tests=(
     "test-subagent-driven-development.sh"
+    "test-brainstorm-handoff.sh"
 )
 
 # Integration tests (slow, full execution)

tests/claude-code/test-brainstorm-handoff-e2e.sh

@@ -0,0 +1,330 @@
+#!/usr/bin/env bash
+# Test: Brainstorm-to-plan handoff (end-to-end)
+#
+# Full brainstorming flow that builds enough context distance to reproduce
+# the EnterPlanMode failure. Simulates a real brainstorming session with
+# multiple turns of Q&A before the "build it" moment.
+#
+# This test takes 5-10 minutes to run.
+#
+# PASS: Skill tool invoked with "writing-plans" AND EnterPlanMode NOT invoked
+# FAIL: EnterPlanMode invoked OR writing-plans not invoked
+#
+# Usage:
+#   ./test-brainstorm-handoff-e2e.sh                  # With fix (expects PASS)
+#   ./test-brainstorm-handoff-e2e.sh --without-fix    # Strip fix, reproduce failure
+#   ./test-brainstorm-handoff-e2e.sh --verbose        # Show full output
+#
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+PLUGIN_DIR="$(cd "$SCRIPT_DIR/../.." && pwd)"
+
+# Parse flags
+VERBOSE=false
+WITHOUT_FIX=false
+while [[ $# -gt 0 ]]; do
+    case $1 in
+        --verbose|-v) VERBOSE=true; shift ;;
+        --without-fix) WITHOUT_FIX=true; shift ;;
+        *) echo "Unknown flag: $1"; exit 1 ;;
+    esac
+done
+
+TIMESTAMP=$(date +%s)
+OUTPUT_DIR="/tmp/superpowers-tests/${TIMESTAMP}/brainstorm-handoff-e2e"
+mkdir -p "$OUTPUT_DIR"
+
+echo "=== Brainstorm-to-Plan Handoff E2E Test ==="
+echo "Mode: $([ "$WITHOUT_FIX" = true ] && echo "WITHOUT FIX (expect failure)" || echo "WITH FIX (expect pass)")"
+echo "Output: $OUTPUT_DIR"
+echo "This test takes 5-10 minutes."
+echo ""
+
+# --- Project Setup ---
+
+PROJECT_DIR="$OUTPUT_DIR/project"
+mkdir -p "$PROJECT_DIR/src" "$PROJECT_DIR/test"
+
+cat > "$PROJECT_DIR/package.json" << 'PROJ_EOF'
+{
+  "name": "my-express-app",
+  "version": "1.0.0",
+  "type": "module",
+  "scripts": {
+    "start": "node src/index.js",
+    "test": "vitest run"
+  },
+  "dependencies": {
+    "express": "^4.18.0",
+    "better-sqlite3": "^9.0.0"
+  },
+  "devDependencies": {
+    "vitest": "^1.0.0",
+    "supertest": "^6.0.0"
+  }
+}
+PROJ_EOF
+
+cat > "$PROJECT_DIR/src/index.js" << 'PROJ_EOF'
+import express from 'express';
+const app = express();
+app.use(express.json());
+
+app.get('/health', (req, res) => res.json({ status: 'ok' }));
+
+const PORT = process.env.PORT || 3000;
+if (process.env.NODE_ENV !== 'test') {
+  app.listen(PORT, () => console.log(`Listening on ${PORT}`));
+}
+
+export default app;
+PROJ_EOF
+
+cd "$PROJECT_DIR"
+git init -q
+git add -A
+git commit -q -m "Initial commit"
+
+# --- Plugin Setup ---
+
+EFFECTIVE_PLUGIN_DIR="$PLUGIN_DIR"
+
+if [ "$WITHOUT_FIX" = true ]; then
+    echo "Creating plugin copy without the handoff fix..."
+    EFFECTIVE_PLUGIN_DIR="$OUTPUT_DIR/plugin-without-fix"
+    cp -R "$PLUGIN_DIR" "$EFFECTIVE_PLUGIN_DIR"
+
+    python3 << PYEOF
+import pathlib
+
+# Strip fix from brainstorming SKILL.md
+p = pathlib.Path('$EFFECTIVE_PLUGIN_DIR/skills/brainstorming/SKILL.md')
+content = p.read_text()
+content = content.replace(
+    '**Implementation (if continuing):**\nWhen the user approves the design and wants to build:\n1. **Invoke \`superpowers:writing-plans\` using the Skill tool.** Not EnterPlanMode. Not plan mode. Not direct implementation. The Skill tool.\n2. After the plan is written, use superpowers:using-git-worktrees to create an isolated workspace for implementation.',
+    '**Implementation (if continuing):**\n- Ask: "Ready to set up for implementation?"\n- Use superpowers:using-git-worktrees to create isolated workspace\n- **REQUIRED:** Use superpowers:writing-plans to create detailed implementation plan'
+)
+p.write_text(content)
+
+# Strip fix from using-superpowers
+p = pathlib.Path('$EFFECTIVE_PLUGIN_DIR/skills/using-superpowers/SKILL.md')
+lines = p.read_text().splitlines(keepends=True)
+lines = [l for l in lines if 'I should use EnterPlanMode' not in l]
+p.write_text(''.join(lines))
+
+# Strip fix from writing-plans
+p = pathlib.Path('$EFFECTIVE_PLUGIN_DIR/skills/writing-plans/SKILL.md')
+content = p.read_text()
+content = content.replace(
+    'description: Use when you have a spec or requirements for a multi-step task, before touching code. After brainstorming, ALWAYS use this — not EnterPlanMode or plan mode.',
+    'description: Use when you have a spec or requirements for a multi-step task, before touching code'
+)
+content = content.replace(
+    '**Context:** This runs in the main workspace after brainstorming, while context is fresh. The worktree is created afterward for implementation.',
+    '**Context:** This should be run in a dedicated worktree (created by brainstorming skill).'
+)
+p.write_text(content)
+PYEOF
+    echo "Plugin copy created."
+    echo ""
+fi
+
+# --- Helper ---
+
+run_turn() {
+    local turn_num="$1"
+    local prompt="$2"
+    local max_turns="$3"
+    local label="$4"
+    local continue_flag="${5:-}"
+
+    local log_file="$OUTPUT_DIR/turn${turn_num}.json"
+    echo ">>> Turn $turn_num: $label"
+
+    local cmd="timeout 300 claude -p \"$prompt\""
+    cmd="$cmd --plugin-dir \"$EFFECTIVE_PLUGIN_DIR\""
+    cmd="$cmd --dangerously-skip-permissions"
+    cmd="$cmd --max-turns $max_turns"
+    cmd="$cmd --output-format stream-json"
+    if [ -n "$continue_flag" ]; then
+        cmd="$cmd --continue"
+    fi
+
+    eval "$cmd" > "$log_file" 2>&1 || true
+
+    echo "    Done."
+    if [ "$VERBOSE" = true ]; then
+        echo "    ---"
+        grep '"type":"assistant"' "$log_file" 2>/dev/null | tail -1 | \
+            jq -r '.message.content[0].text // empty' 2>/dev/null | \
+            head -c 600 || true
+        echo ""
+        echo "    ---"
+    fi
+
+    echo "$log_file"
+}
+
+# --- Run Full Brainstorming Flow ---
+
+cd "$PROJECT_DIR"
+
+# Turn 1: Start brainstorming - this loads the skill and begins Q&A
+T1=$(run_turn 1 \
+    "I want to add URL shortening to this Express app. Help me think through the design." \
+    5 "Starting brainstorming")
+
+# Turn 2: Answer first question (whatever it is) generically
+T2=$(run_turn 2 \
+    "Good question. Here is what I want: POST /api/shorten that takes a URL and returns a short code. GET /:code that redirects. GET /api/stats/:code for click tracking. Random 6-char alphanumeric codes. SQLite storage using better-sqlite3 which is already in package.json. No auth needed." \
+    5 "Answering first question" --continue)
+
+# Turn 3: Agree with recommendations
+T3=$(run_turn 3 \
+    "Yes, that sounds right. Go with your recommendation." \
+    5 "Agreeing with recommendation" --continue)
+
+# Turn 4: Continue agreeing
+T4=$(run_turn 4 \
+    "Looks good. I agree with that approach." \
+    5 "Continuing to agree" --continue)
+
+# Turn 5: Push toward completion
+T5=$(run_turn 5 \
+    "Perfect. I am happy with all of that. Please wrap up the design and write the spec." \
+    8 "Requesting spec write-up" --continue)
+
+# Turn 6: Approve the spec
+T6=$(run_turn 6 \
+    "The spec looks great. I approve it." \
+    5 "Approving spec" --continue)
+
+# Turn 7: THE CRITICAL MOMENT - "build it"
+T7=$(run_turn 7 \
+    "Yes, build it." \
+    5 "Critical handoff: build it" --continue)
+
+# Turn 8: Safety net in case turn 7 asked a follow-up
+T8=$(run_turn 8 \
+    "Yes. Go ahead and build it now." \
+    5 "Safety net: build it" --continue)
+
+echo ""
+
+# --- Assertions ---
+
+echo "=== Results ==="
+echo ""
+
+# Combine all logs
+ALL_LOGS="$OUTPUT_DIR/all-turns.json"
+cat "$OUTPUT_DIR"/turn*.json > "$ALL_LOGS" 2>/dev/null
+
+# Check handoff turns (6-8, where approval + "build it" happens)
+HANDOFF_LOGS="$OUTPUT_DIR/handoff-turns.json"
+cat "$OUTPUT_DIR/turn6.json" "$OUTPUT_DIR/turn7.json" "$OUTPUT_DIR/turn8.json" > "$HANDOFF_LOGS" 2>/dev/null
+
+# Detection: writing-plans skill invoked in handoff turns?
+HAS_WRITING_PLANS=false
+if grep -q '"name":"Skill"' "$HANDOFF_LOGS" 2>/dev/null && grep -q 'writing-plans' "$HANDOFF_LOGS" 2>/dev/null; then
+    HAS_WRITING_PLANS=true
+fi
+
+# Detection: EnterPlanMode invoked in handoff turns?
+HAS_ENTER_PLAN_MODE=false
+if grep -q '"name":"EnterPlanMode"' "$HANDOFF_LOGS" 2>/dev/null; then
+    HAS_ENTER_PLAN_MODE=true
+fi
+
+# Also check across ALL turns (might happen earlier)
+HAS_ENTER_PLAN_MODE_ANYWHERE=false
+if grep -q '"name":"EnterPlanMode"' "$ALL_LOGS" 2>/dev/null; then
+    HAS_ENTER_PLAN_MODE_ANYWHERE=true
+fi
+
+# Report
+echo "Skills invoked (all turns):"
+grep -o '"skill":"[^"]*"' "$ALL_LOGS" 2>/dev/null | sort -u || echo "  (none)"
+echo ""
+
+echo "Skills invoked (handoff turns 6-8):"
+grep -o '"skill":"[^"]*"' "$HANDOFF_LOGS" 2>/dev/null | sort -u || echo "  (none)"
+echo ""
+
+echo "Tools invoked in handoff turns (6-8):"
+grep -o '"name":"[A-Z][^"]*"' "$HANDOFF_LOGS" 2>/dev/null | sort | uniq -c | sort -rn | head -10 || echo "  (none)"
+echo ""
+
+if [ "$HAS_ENTER_PLAN_MODE_ANYWHERE" = true ]; then
+    echo "WARNING: EnterPlanMode was invoked somewhere in the conversation."
+    echo "Turns containing EnterPlanMode:"
+    for f in "$OUTPUT_DIR"/turn*.json; do
+        if grep -q '"name":"EnterPlanMode"' "$f" 2>/dev/null; then
+            echo "  $(basename "$f")"
+        fi
+    done
+    echo ""
+fi
+
+# Determine result
+PASSED=false
+if [ "$WITHOUT_FIX" = true ]; then
+    echo "--- Without-Fix Mode (reproducing failure) ---"
+    if [ "$HAS_ENTER_PLAN_MODE" = true ] || [ "$HAS_ENTER_PLAN_MODE_ANYWHERE" = true ]; then
+        echo "REPRODUCED: Claude used EnterPlanMode (the bug we're fixing)"
+        PASSED=true
+    elif [ "$HAS_WRITING_PLANS" = true ]; then
+        echo "NOT REPRODUCED: Claude used writing-plans even without the fix"
+        echo "(The old guidance was sufficient in this run)"
+        PASSED=false
+    else
+        echo "INCONCLUSIVE: Claude used neither writing-plans nor EnterPlanMode"
+        echo "The brainstorming flow may not have reached the handoff point."
+        PASSED=false
+    fi
+else
+    echo "--- With-Fix Mode (verifying fix) ---"
+    if [ "$HAS_WRITING_PLANS" = true ] && [ "$HAS_ENTER_PLAN_MODE_ANYWHERE" = false ]; then
+        echo "PASS: Claude used writing-plans skill (correct handoff)"
+        PASSED=true
+    elif [ "$HAS_ENTER_PLAN_MODE_ANYWHERE" = true ]; then
+        echo "FAIL: Claude used EnterPlanMode instead of writing-plans"
+        PASSED=false
+    elif [ "$HAS_WRITING_PLANS" = true ] && [ "$HAS_ENTER_PLAN_MODE_ANYWHERE" = true ]; then
+        echo "FAIL: Claude used BOTH writing-plans AND EnterPlanMode"
+        PASSED=false
+    else
+        echo "INCONCLUSIVE: Claude used neither writing-plans nor EnterPlanMode"
+        echo "The brainstorming flow may not have reached the handoff."
+        echo "Check logs to see where the conversation stopped."
+        PASSED=false
+    fi
+fi
+
+echo ""
+
+# Show what happened in each turn
+echo "Turn-by-turn summary:"
+for i in 1 2 3 4 5 6 7 8; do
+    local_log="$OUTPUT_DIR/turn${i}.json"
+    if [ -f "$local_log" ]; then
+        local_skills=$(grep -o '"skill":"[^"]*"' "$local_log" 2>/dev/null | tr '\n' ' ' || true)
+        local_tools=$(grep -o '"name":"EnterPlanMode\|"name":"Skill"' "$local_log" 2>/dev/null | tr '\n' ' ' || true)
+        local_size=$(wc -c < "$local_log" | tr -d ' ')
+        printf "  Turn %d: %s bytes" "$i" "$local_size"
+        [ -n "$local_skills" ] && printf " | skills: %s" "$local_skills"
+        [ -n "$local_tools" ] && printf " | tools: %s" "$local_tools"
+        echo ""
+    fi
+done
+
+echo ""
+echo "Logs: $OUTPUT_DIR"
+echo ""
+
+if [ "$PASSED" = true ]; then
+    exit 0
+else
+    exit 1
+fi

tests/claude-code/test-brainstorm-handoff.sh

@@ -0,0 +1,317 @@
+#!/usr/bin/env bash
+# Test: Brainstorm-to-plan handoff
+#
+# Verifies that after brainstorming, Claude invokes the writing-plans skill
+# instead of using EnterPlanMode.
+#
+# The failure mode this catches:
+#   User says "build it" after brainstorming -> Claude calls EnterPlanMode
+#   (because the system prompt's planning guidance overpowers the brainstorming
+#   skill's instructions, which were loaded many turns ago)
+#
+# PASS: Skill tool invoked with "writing-plans" AND EnterPlanMode NOT invoked
+# FAIL: EnterPlanMode invoked OR writing-plans not invoked
+#
+# Usage:
+#   ./test-brainstorm-handoff.sh                  # Normal test (expects PASS)
+#   ./test-brainstorm-handoff.sh --without-fix    # Strip fix, reproduce failure
+#   ./test-brainstorm-handoff.sh --verbose        # Show full output
+#
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+PLUGIN_DIR="$(cd "$SCRIPT_DIR/../.." && pwd)"
+
+# Parse flags
+VERBOSE=false
+WITHOUT_FIX=false
+while [[ $# -gt 0 ]]; do
+    case $1 in
+        --verbose|-v) VERBOSE=true; shift ;;
+        --without-fix) WITHOUT_FIX=true; shift ;;
+        *) echo "Unknown flag: $1"; exit 1 ;;
+    esac
+done
+
+TIMESTAMP=$(date +%s)
+OUTPUT_DIR="/tmp/superpowers-tests/${TIMESTAMP}/brainstorm-handoff"
+mkdir -p "$OUTPUT_DIR"
+
+echo "=== Brainstorm-to-Plan Handoff Test ==="
+echo "Mode: $([ "$WITHOUT_FIX" = true ] && echo "WITHOUT FIX (expect failure)" || echo "WITH FIX (expect pass)")"
+echo "Output: $OUTPUT_DIR"
+echo ""
+
+# --- Project Setup ---
+
+PROJECT_DIR="$OUTPUT_DIR/project"
+mkdir -p "$PROJECT_DIR/src"
+mkdir -p "$PROJECT_DIR/docs/superpowers/specs"
+
+cat > "$PROJECT_DIR/package.json" << 'PROJ_EOF'
+{
+  "name": "my-express-app",
+  "version": "1.0.0",
+  "type": "module",
+  "dependencies": {
+    "express": "^4.18.0",
+    "better-sqlite3": "^9.0.0"
+  }
+}
+PROJ_EOF
+
+cat > "$PROJECT_DIR/src/index.js" << 'PROJ_EOF'
+import express from 'express';
+const app = express();
+app.use(express.json());
+
+app.get('/health', (req, res) => res.json({ status: 'ok' }));
+
+const PORT = process.env.PORT || 3000;
+app.listen(PORT, () => console.log(`Listening on ${PORT}`));
+PROJ_EOF
+
+# Pre-create a spec document (simulating completed brainstorming)
+cat > "$PROJECT_DIR/docs/superpowers/specs/2025-01-15-url-shortener-design.md" << 'SPEC_EOF'
+# URL Shortener Design Spec
+
+## Overview
+Add URL shortening capability to the existing Express.js API.
+
+## Features
+- POST /api/shorten accepts { url } and returns { shortCode, shortUrl }
+- GET /:code redirects to the original URL (302)
+- GET /api/stats/:code returns { clicks, createdAt, originalUrl }
+
+## Technical Design
+
+### Database
+Single SQLite table via better-sqlite3:
+```sql
+CREATE TABLE urls (
+  id INTEGER PRIMARY KEY AUTOINCREMENT,
+  short_code TEXT UNIQUE NOT NULL,
+  original_url TEXT NOT NULL,
+  clicks INTEGER DEFAULT 0,
+  created_at TEXT DEFAULT (datetime('now'))
+);
+CREATE INDEX idx_short_code ON urls(short_code);
+```
+
+### File Structure
+- `src/index.js` — modified to mount new routes
+- `src/db.js` — database initialization and query functions
+- `src/shorten.js` — route handlers for all three endpoints
+- `src/code-generator.js` — random 6-char alphanumeric code generation
+
+### Code Generation
+Random 6-character alphanumeric codes using crypto.randomBytes.
+Check for collisions and retry (astronomically unlikely with 36^6 space).
+
+### Validation
+- URL must be present and start with http:// or https://
+- Return 400 with { error: "..." } for invalid input
+
+### Error Handling
+- 404 with { error: "Not found" } for unknown short codes
+- 500 with { error: "Internal server error" } for database failures
+
+## Decisions
+- 302 redirects (not 301) so browsers don't cache and we always track clicks
+- Database path configurable via DATABASE_PATH env var, defaults to ./data/urls.db
+- No auth, no custom codes, no expiry — keeping it simple
+SPEC_EOF
+
+# Initialize git so brainstorming can inspect project state
+cd "$PROJECT_DIR"
+git init -q
+git add -A
+git commit -q -m "Initial commit with URL shortener spec"
+
+# --- Plugin Setup ---
+
+EFFECTIVE_PLUGIN_DIR="$PLUGIN_DIR"
+
+if [ "$WITHOUT_FIX" = true ]; then
+    echo "Creating plugin copy without the handoff fix..."
+    EFFECTIVE_PLUGIN_DIR="$OUTPUT_DIR/plugin-without-fix"
+    cp -R "$PLUGIN_DIR" "$EFFECTIVE_PLUGIN_DIR"
+
+    # Strip fix from brainstorming SKILL.md: revert to old implementation section
+    python3 << PYEOF
+import pathlib
+p = pathlib.Path('$EFFECTIVE_PLUGIN_DIR/skills/brainstorming/SKILL.md')
+content = p.read_text()
+content = content.replace(
+    '**Implementation (if continuing):**\nWhen the user approves the design and wants to build:\n1. **Invoke \`superpowers:writing-plans\` using the Skill tool.** Not EnterPlanMode. Not plan mode. Not direct implementation. The Skill tool.\n2. After the plan is written, use superpowers:using-git-worktrees to create an isolated workspace for implementation.',
+    '**Implementation (if continuing):**\n- Ask: "Ready to set up for implementation?"\n- Use superpowers:using-git-worktrees to create isolated workspace\n- **REQUIRED:** Use superpowers:writing-plans to create detailed implementation plan'
+)
+p.write_text(content)
+PYEOF
+
+    # Strip fix from using-superpowers: remove EnterPlanMode red flag
+    python3 << PYEOF
+import pathlib
+p = pathlib.Path('$EFFECTIVE_PLUGIN_DIR/skills/using-superpowers/SKILL.md')
+lines = p.read_text().splitlines(keepends=True)
+lines = [l for l in lines if 'I should use EnterPlanMode' not in l]
+p.write_text(''.join(lines))
+PYEOF
+
+    # Strip fix from writing-plans: revert description and context
+    python3 << PYEOF
+import pathlib
+p = pathlib.Path('$EFFECTIVE_PLUGIN_DIR/skills/writing-plans/SKILL.md')
+content = p.read_text()
+content = content.replace(
+    'description: Use when you have a spec or requirements for a multi-step task, before touching code. After brainstorming, ALWAYS use this — not EnterPlanMode or plan mode.',
+    'description: Use when you have a spec or requirements for a multi-step task, before touching code'
+)
+content = content.replace(
+    '**Context:** This runs in the main workspace after brainstorming, while context is fresh. The worktree is created afterward for implementation.',
+    '**Context:** This should be run in a dedicated worktree (created by brainstorming skill).'
+)
+p.write_text(content)
+PYEOF
+    echo "Plugin copy created at $EFFECTIVE_PLUGIN_DIR"
+    echo ""
+fi
+
+# --- Run Conversation ---
+
+cd "$PROJECT_DIR"
+
+# Turn 1: Load brainstorming and establish that we finished the design
+# The key is that brainstorming gets loaded into context, and we're at the handoff point
+echo ">>> Turn 1: Loading brainstorming skill and establishing context..."
+TURN1_LOG="$OUTPUT_DIR/turn1.json"
+
+TURN1_PROMPT='I want to add URL shortening to this Express app. I already have the full design worked out and written to docs/superpowers/specs/2025-01-15-url-shortener-design.md. Please read the spec.'
+
+timeout 300 claude -p "$TURN1_PROMPT" \
+    --plugin-dir "$EFFECTIVE_PLUGIN_DIR" \
+    --dangerously-skip-permissions \
+    --max-turns 5 \
+    --output-format stream-json \
+    > "$TURN1_LOG" 2>&1 || true
+
+echo "Turn 1 complete."
+if [ "$VERBOSE" = true ]; then
+    echo "---"
+    grep '"type":"assistant"' "$TURN1_LOG" | tail -1 | jq -r '.message.content[0].text // empty' 2>/dev/null | head -c 800 || true
+    echo ""
+    echo "---"
+fi
+echo ""
+
+# Turn 2: Approve and ask to build - this is the critical handoff moment
+echo ">>> Turn 2: 'The spec is done. Build it.' (critical handoff)..."
+TURN2_LOG="$OUTPUT_DIR/turn2.json"
+
+TURN2_PROMPT='The spec is complete and I am happy with the design. Build it.'
+
+timeout 300 claude -p "$TURN2_PROMPT" \
+    --continue \
+    --plugin-dir "$EFFECTIVE_PLUGIN_DIR" \
+    --dangerously-skip-permissions \
+    --max-turns 5 \
+    --output-format stream-json \
+    > "$TURN2_LOG" 2>&1 || true
+
+echo "Turn 2 complete."
+if [ "$VERBOSE" = true ]; then
+    echo "---"
+    grep '"type":"assistant"' "$TURN2_LOG" | tail -1 | jq -r '.message.content[0].text // empty' 2>/dev/null | head -c 800 || true
+    echo ""
+    echo "---"
+fi
+echo ""
+
+# --- Assertions ---
+
+echo "=== Results ==="
+echo ""
+
+# Combine all turn logs for analysis
+ALL_LOGS="$OUTPUT_DIR/all-turns.json"
+cat "$TURN1_LOG" "$TURN2_LOG" > "$ALL_LOGS"
+
+# Detection: writing-plans skill invoked?
+HAS_WRITING_PLANS=false
+if grep -q '"name":"Skill"' "$ALL_LOGS" 2>/dev/null && grep -q 'writing-plans' "$ALL_LOGS" 2>/dev/null; then
+    HAS_WRITING_PLANS=true
+fi
+
+# Detection: EnterPlanMode invoked?
+HAS_ENTER_PLAN_MODE=false
+if grep -q '"name":"EnterPlanMode"' "$ALL_LOGS" 2>/dev/null; then
+    HAS_ENTER_PLAN_MODE=true
+fi
+
+# Report what skills were invoked
+echo "Skills invoked:"
+grep -o '"skill":"[^"]*"' "$ALL_LOGS" 2>/dev/null | sort -u || echo "  (none)"
+echo ""
+
+echo "Notable tools invoked:"
+grep -o '"name":"[A-Z][^"]*"' "$ALL_LOGS" 2>/dev/null | sort | uniq -c | sort -rn | head -10 || echo "  (none)"
+echo ""
+
+# Determine result
+PASSED=false
+if [ "$WITHOUT_FIX" = true ]; then
+    # In without-fix mode, we EXPECT the failure (EnterPlanMode)
+    echo "--- Without-Fix Mode (reproducing failure) ---"
+    if [ "$HAS_ENTER_PLAN_MODE" = true ]; then
+        echo "REPRODUCED: Claude used EnterPlanMode (the bug we're fixing)"
+        PASSED=true
+    elif [ "$HAS_WRITING_PLANS" = true ]; then
+        echo "NOT REPRODUCED: Claude used writing-plans even without the fix"
+        echo "(The model may have followed the old guidance anyway)"
+        PASSED=false
+    else
+        echo "INCONCLUSIVE: Claude used neither writing-plans nor EnterPlanMode"
+        echo "The brainstorming flow may not have reached the handoff point."
+        PASSED=false
+    fi
+else
+    # Normal mode: expect writing-plans, not EnterPlanMode
+    echo "--- With-Fix Mode (verifying fix) ---"
+    if [ "$HAS_WRITING_PLANS" = true ] && [ "$HAS_ENTER_PLAN_MODE" = false ]; then
+        echo "PASS: Claude used writing-plans skill (correct handoff)"
+        PASSED=true
+    elif [ "$HAS_ENTER_PLAN_MODE" = true ]; then
+        echo "FAIL: Claude used EnterPlanMode instead of writing-plans"
+        PASSED=false
+    elif [ "$HAS_WRITING_PLANS" = true ] && [ "$HAS_ENTER_PLAN_MODE" = true ]; then
+        echo "FAIL: Claude used BOTH writing-plans AND EnterPlanMode"
+        PASSED=false
+    else
+        echo "INCONCLUSIVE: Claude used neither writing-plans nor EnterPlanMode"
+        echo "The brainstorming flow may not have reached the handoff point."
+        echo "Check logs - brainstorming may still be asking questions."
+        PASSED=false
+    fi
+fi
+
+echo ""
+
+# Show the critical turn 2 response
+echo "Turn 2 response (first 500 chars):"
+grep '"type":"assistant"' "$TURN2_LOG" 2>/dev/null | tail -1 | \
+    jq -r '.message.content[0].text // .message.content' 2>/dev/null | \
+    head -c 500 || echo "  (could not extract)"
+echo ""
+
+echo ""
+echo "Logs:"
+echo "  Turn 1: $TURN1_LOG"
+echo "  Turn 2: $TURN2_LOG"
+echo "  Combined: $ALL_LOGS"
+echo ""
+
+if [ "$PASSED" = true ]; then
+    exit 0
+else
+    exit 1
+fi