claude-fsd 1.3.8 → 1.3.9

package/bin/claudefsd-analyze-brief

@@ -37,7 +37,7 @@ Read all of these documents if they exist:
 - docs/WEBTESTS.md -- the project web tests
 - README.md -- the project README
 
-Your job, as a megathinking business analyst, is to analyze the project brief and generate clarifying questions.
+Your job, as a megathinker business analyst, is to analyze the project brief and generate clarifying questions.
 
 1. Read through the BRIEF.md and any existing documents to understand the project.
 2. Generate 10-15 relevant questions to clarify ambiguous aspects of the brief.
@@ -64,6 +64,7 @@ if command -v codex >/dev/null 2>&1; then
     echo "Running codex o3 (results won't display)..."
     codex -m o3 --full-auto -q "$prompt1" > $LOGFILE-ba2
 else
+    echo "Warning: codex not found, skipping enhanced analysis"
     echo "Codex not available, skipping o3 analysis" > $LOGFILE-ba2
 fi
 

package/bin/claudefsd-check-dependencies

@@ -25,7 +25,6 @@ check_dependencies() {
     # Check for codex (optional but recommended)
     if [ "$check_codex" = true ] && ! command_exists codex; then
         warnings+=("codex is not installed. Some review features will be unavailable.")
-        warnings+=("Install it from: https://github.com/Codex-ai/codex")
     fi
     
     # Check for OPENAI_API_KEY (optional for codex)

package/bin/claudefsd-create-plan

@@ -53,11 +53,18 @@ The CLAUDE-NOTES.md should contain:
 The PLAN.md should contain:
 - Ordered list of development tasks with [ ] checkboxes
 - Each task should be specific and actionable
-- Include infrastructure setup (git, linting, testing) as early tasks
+- Include proportional infrastructure setup (basic linting + pre-commit hooks)
 - Group related tasks into logical phases
 
-Ensure the plan includes basic SDLC infrastructure like git repo setup, pre-commit hooks, and linting.
-Use feature branches for development work. Follow YAGNI principle - don't over-engineer.
+INFRASTRUCTURE PROPORTIONALITY RULES:
+- Basic linter + pre-commit hooks: Always include for any project
+- Tests: Should be ≤50% the size of functional code (not 3x larger!)
+- For simple shell scripts (~200-500 lines): Basic integration tests only
+- For complex systems (>1000 lines): More comprehensive testing
+- NO enterprise patterns for simple solutions (file locking, complex CI, monolithic architectures)
+- Follow existing claude-fsd pattern: separate focused scripts, not monoliths
+- FAIL LOUD - simple error handling, exit on failure
+- Choose infrastructure complexity appropriate to solution size
 "
 
 # run BA's
@@ -69,6 +76,7 @@ if command -v codex >/dev/null 2>&1; then
     echo "Running codex o3 (results won't display)..."
     codex -m o3 --full-auto -q "$prompt2" > $LOGFILE-ba4
 else
+    echo "Warning: codex not found, skipping enhanced planning"
     echo "Codex not available, skipping o3 analysis" > $LOGFILE-ba4
 fi
 

package/bin/claudefsd-dev

@@ -118,7 +118,7 @@ Please follow these steps to complete the task:
      * Impact on the overall system
      * Defensive programming techniques to employ
      * Potential edge cases and how to handle them
-     * A testing strategy for the component
+     * A minimal, focused testing strategy (avoid extensive test infrastructure)
 
 2. Execute the necessary changes or Bash commands to complete the task. Use parallel agents for dev work when appropriate to increase efficiency.
 
@@ -216,6 +216,7 @@ If you have any questions of the user for the future, you can add them to QUESTI
 If you have any ideas for the future, you can add them to IDEAS.md.
 " > $LOGFILE-reviewer) &
     else
+        echo "Warning: codex not found, skipping background code review"
         echo "Codex not available, skipping static code review" > $LOGFILE-reviewer
     fi
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "claude-fsd",
-  "version": "1.3.8",
+  "version": "1.3.9",
   "description": "Claude Full Self Drive tools for autonomous AI-powered development",
   "bin": {
     "claude-fsd": "bin/claude-fsd",