📚 Update docs to goal-focused approach and remove yarn

optimal-development-workflow.md:
- Remove prescriptive bash code from worktree setup, PR creation,
  and bot feedback loop sections
- Convert to goal-focused descriptions matching autotask.md style
- Clarify what happens without showing how (goals over process)

README.md:
- Remove yarn references (standardize on npm)
- Update requirements to be more accurate
- Remove "Git with worktrees support" (obvious)

Addresses bot feedback: "Clarify bot feedback pseudo-code is
illustrative" by removing it entirely and using goal-focused
descriptions instead.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

Author: Nick Sullivan

README.md

@@ -326,9 +326,9 @@ Shows what changed, lets you choose what to update, preserves project-specific c
 - Claude Code with plugin support
 
 **For autonomous workflows**:
-- Git with worktrees support
 - GitHub CLI (`gh`) installed and authenticated
-- Project dependency managers (npm/yarn/pip/etc.)
+- Node.js/npm (for JavaScript/TypeScript projects)
+- Project-specific dependency managers (pip, bundle, cargo, etc.)
 
 **For Cursor**:
 - Cursor IDE with rules support

context/optimal-development-workflow.md

@@ -42,14 +42,7 @@ Analyzes task complexity:
 
 ### Phase 2: Worktree Setup
 
-Create isolated development environment:
-
-```bash
-mkdir -p .gitworktrees
-git worktree add -b feature/task-name .gitworktrees/task-name main
-cd .gitworktrees/task-name
-/setup-environment  # Install deps, copy env files, setup git hooks
-```
+Create isolated development environment in `.gitworktrees/` with sanitized branch name. Run `/setup-environment` to install dependencies, copy environment files, and set up git hooks (husky or pre-commit).
 
 ### Phase 3: Autonomous Execution
 
@@ -99,74 +92,17 @@ Automatically follows all `.cursor/rules/*.mdc` standards.
 
 ### Phase 5: Create PR
 
-```bash
-# Commit with proper message format
-git add .
-git commit -m "feat: Add OAuth2 authentication
-
-- Implement OAuth2 flow with token refresh
-- Add email/password fallback
-- Session management middleware
-- Test coverage: 97%
-
-🤖 Generated with Claude Code
-"
+Create commits following `.cursor/rules/git-commit-message.mdc` standards (emoji prefix, imperative verb, clear description, co-author line). Push to feature branch and create pull request with comprehensive description covering changes, rationale, trade-offs, and testing approach.
 
-# Push to origin
-git push -u origin feature/task-name
+### Phase 6: Bot Feedback Loop
 
-# Create PR
-gh pr create \
-  --title "Add OAuth2 authentication" \
-  --body "Summary of changes..."
-```
+**This is the key innovation** - autonomously handle bot feedback without waiting for human intervention.
 
-### Phase 6: Bot Feedback Loop
+After creating the PR, wait 3 minutes for AI code review bots to complete initial analysis. Check for bot comments using GitHub API. Evaluate each piece of feedback critically - you have context bots lack (project standards, implementation rationale, trade-offs, requirements).
 
-**This is the key innovation** - don't wait for you, autonomously handle bot feedback:
+Fix what's valuable (security issues, real bugs, good suggestions). Reject what's not (use WONTFIX with brief explanation for context-missing or incorrect feedback). You are the ultimate decider.
 
-```bash
-echo "⏳ Waiting for bot reviews..."
-PR_NUMBER=$(gh pr view --json number -q .number)
-
-# Initial wait for bots to run
-sleep 120
-
-# Loop until all bot feedback addressed
-while true; do
-  echo "📝 Checking for bot comments..."
-
-  # Get unresolved bot comments
-  COMMENTS=$(gh api \
-    repos/{owner}/{repo}/pulls/$PR_NUMBER/comments \
-    --jq '.[] | select(.user.type == "Bot") | select(.resolved != true)')
-
-  if [ -z "$COMMENTS" ]; then
-    echo "✅ All bot feedback addressed!"
-    break
-  fi
-
-  echo "🤖 Analyzing bot feedback..."
-
-  # Categorize each comment intelligently:
-  # - CRITICAL: Security, bugs, breaking changes → Fix immediately
-  # - VALID: Legitimate improvements → Apply fix
-  # - CONTEXT-MISSING: Bot lacks project context → Mark WONTFIX with explanation
-  # - FALSE-POSITIVE: Bot is wrong → Mark WONTFIX with reasoning
-
-  # If fixes made, push and re-wait
-  if git diff --quiet; then
-    break  # No changes needed
-  else
-    git add .
-    git commit -m "Address bot feedback"
-    git push
-
-    echo "⏳ Waiting for bots to re-review..."
-    sleep 90
-  fi
-done
-```
+After pushing fixes, wait 90 seconds for bots to re-review. Iterate up to 5 times if needed until critical issues are resolved.
 
 ### Phase 7: Done - Handoff to You