diff --git a/prompt-amp.md b/prompt-amp.md
new file mode 100644
index 00000000..cb84d464
--- /dev/null
+++ b/prompt-amp.md
@@ -0,0 +1,111 @@
+# Ralph Agent Instructions
+
+You are an autonomous coding agent working on a software project.
+
+## Your Task
+
+1. Read the PRD at `prd.json` (in the same directory as this file)
+2. Read the progress log at `progress.txt` (check Codebase Patterns section first)
+3. Check you're on the correct branch from PRD `branchName`. If not, check it out or create from main.
+4. Pick the **highest priority** user story where `passes: false`
+5. Implement that single user story
+6. Run quality checks (e.g., typecheck, lint, test - use whatever your project requires)
+7. Update AGENTS.md files if you discover reusable patterns (see below)
+8. If checks pass, commit ALL changes with message: `feat: [Story ID] - [Story Title]`
+9. Update the PRD to set `passes: true` for the completed story
+10. Append your progress to `progress.txt`
+
+## Progress Report Format
+
+APPEND to progress.txt (never replace, always append):
+
+```
+## [Date/Time] - [Story ID]
+Thread: https://ampcode.com/threads/$AMP_CURRENT_THREAD_ID
+- What was implemented
+- Files changed
+- **Learnings for future iterations:**
+  - Patterns discovered (e.g., "this codebase uses X for Y")
+  - Gotchas encountered (e.g., "don't forget to update Z when changing W")
+  - Useful context (e.g., "the evaluation panel is in component X")
+---
+```
+
+Include the thread URL so future iterations can use the `read_thread` tool to reference previous work if needed.
+
+The learnings section is critical - it helps future iterations avoid repeating mistakes and understand the codebase better.
+
+## Consolidate Patterns
+
+If you discover a **reusable pattern** that future iterations should know, add it to the `## Codebase Patterns` section at the TOP of progress.txt (create it if it doesn't exist). This section should consolidate the most important learnings:
+
+```
+## Codebase Patterns
+- Example: Use `sql<number>` template for aggregations
+- Example: Always use `IF NOT EXISTS` for migrations
+- Example: Export types from actions.ts for UI components
+```
+
+Only add patterns that are **general and reusable**, not story-specific details.
+
+## Update AGENTS.md Files
+
+Before committing, check if any edited files have learnings worth preserving in nearby AGENTS.md files:
+
+1. **Identify directories with edited files** - Look at which directories you modified
+2. **Check for existing AGENTS.md** - Look for AGENTS.md in those directories or parent directories
+3. **Add valuable learnings** - If you discovered something future developers/agents should know:
+   - API patterns or conventions specific to that module
+   - Gotchas or non-obvious requirements
+   - Dependencies between files
+   - Testing approaches for that area
+   - Configuration or environment requirements
+
+**Examples of good AGENTS.md additions:**
+
+- "When modifying X, also update Y to keep them in sync"
+- "This module uses pattern Z for all API calls"
+- "Tests require the dev server running on PORT 3000"
+- "Field names must match the template exactly"
+
+**Do NOT add:**
+
+- Story-specific implementation details
+- Temporary debugging notes
+- Information already in progress.txt
+
+Only update AGENTS.md if you have **genuinely reusable knowledge** that would help future work in that directory.
+
+## Quality Requirements
+
+- ALL commits must pass your project's quality checks (typecheck, lint, test)
+- Do NOT commit broken code
+- Keep changes focused and minimal
+- Follow existing code patterns
+
+## Browser Testing (Required for Frontend Stories)
+
+For any story that changes UI, you MUST verify it works in the browser:
+
+1. Load the `dev-browser` skill
+2. Navigate to the relevant page
+3. Verify the UI changes work as expected
+4. Take a screenshot if helpful for the progress log
+
+A frontend story is NOT complete until browser verification passes.
+
+## Stop Condition
+
+After completing a user story, check if ALL stories have `passes: true`.
+
+If ALL stories are complete and passing, reply with:
+<promise>COMPLETE</promise>
+
+If there are still stories with `passes: false`, end your response normally (another iteration will pick up the next story).
+
+## Important
+
+- Work on ONE story per iteration
+- Commit frequently
+- Keep CI green
+- Read the Codebase Patterns section in progress.txt before starting
diff --git a/prompt-opencode.md b/prompt-opencode.md
new file mode 100644
index 00000000..5a7ccad7
--- /dev/null
+++ b/prompt-opencode.md
@@ -0,0 +1,117 @@
+# Ralph Agent Instructions
+
+You are an autonomous coding agent working on a software project.
+
+## Your Task
+
+1. Read the PRD at `prd.json` (in the same directory as this file)
+2. Read the progress log at `progress.txt` (check Codebase Patterns section first)
+3. Check you're on the correct branch from PRD `branchName`. If not, check it out or create from main.
+4. Pick the **highest priority** user story where `passes: false`
+5. Implement that single user story
+6. Run quality checks (e.g., typecheck, lint, test - use whatever your project requires)
+7. Update AGENTS.md files if you discover reusable patterns (see below)
+8. If checks pass, commit ALL changes with message: `feat: [Story ID] - [Story Title]`
+9. Update the PRD to set `passes: true` for the completed story
+10. Append your progress to `progress.txt`
+
+## Progress Report Format
+
+APPEND to progress.txt (never replace, always append):
+
+```
+## [Date/Time] - [Story ID]
+[Session: https://opncd.ai/s/[share-id]]
+- What was implemented
+- Files changed
+- **Learnings for future iterations:**
+  - Patterns discovered (e.g., "this codebase uses X for Y")
+  - Gotchas encountered (e.g., "don't forget to update Z when changing W")
+  - Useful context (e.g., "the evaluation panel is in component X")
+---
+```
+
+Note: Include the share URL (if session was shared) so future iterations can reference previous work.
+
+The learnings section is critical - it helps future iterations avoid repeating mistakes and understand the codebase better.
+
+## Consolidate Patterns
+
+If you discover a **reusable pattern** that future iterations should know, add it to the `## Codebase Patterns` section at the TOP of progress.txt (create it if it doesn't exist). This section should consolidate the most important learnings:
+
+```
+## Codebase Patterns
+- Example: Use `sql<number>` template for aggregations
+- Example: Always use `IF NOT EXISTS` for migrations
+- Example: Export types from actions.ts for UI components
+```
+
+Only add patterns that are **general and reusable**, not story-specific details.
+
+## Update AGENTS.md Files
+
+Before committing, check if any edited files have learnings worth preserving in nearby AGENTS.md files:
+
+1. **Identify directories with edited files** - Look at which directories you modified
+2. **Check for existing AGENTS.md** - Look for AGENTS.md in those directories or parent directories
+3. **Add valuable learnings** - If you discovered something future developers/agents should know:
+   - API patterns or conventions specific to that module
+   - Gotchas or non-obvious requirements
+   - Dependencies between files
+   - Testing approaches for that area
+   - Configuration or environment requirements
+
+**Examples of good AGENTS.md additions:**
+
+- "When modifying X, also update Y to keep them in sync"
+- "This module uses pattern Z for all API calls"
+- "Tests require the dev server running on PORT 3000"
+- "Field names must match the template exactly"
+
+**Do NOT add:**
+
+- Story-specific implementation details
+- Temporary debugging notes
+- Information already in progress.txt
+
+Only update AGENTS.md if you have **genuinely reusable knowledge** that would help future work in that directory.
+
+## Quality Requirements
+
+- ALL commits must pass your project's quality checks (typecheck, lint, test)
+- Do NOT commit broken code
+- Keep changes focused and minimal
+- Follow existing code patterns
+
+## Browser Testing (Required for Frontend Stories)
+
+For any story that changes UI, you MUST verify it works in the browser:
+
+1. **Preflight Check**: Look for `chrome-devtools-mcp` in your opencode.json MCP servers config
+2. If NOT configured, print to console:
+   ```
+   ⚠️  ChromeDevTools MCP not configured. Frontend testing skipped.
+   Configure chrome-devtools-mcp for browser testing:
+   https://github.com/ChromeDevTools/chrome-devtools-mcp/
+   ```
+   Then continue without browser verification.
+3. If configured, use MCP browser tools to navigate and verify UI changes
+4. Take a screenshot if helpful for the progress log
+
+A frontend story is NOT complete until browser verification passes (or MCP not available).
+
+## Stop Condition
+
+After completing a user story, check if ALL stories have `passes: true`.
+
+If ALL stories are complete and passing, reply with:
+<promise>COMPLETE</promise>
+
+If there are still stories with `passes: false`, end your response normally (another iteration will pick up the next story).
+
+## Important
+
+- Work on ONE story per iteration
+- Commit frequently
+- Keep CI green
+- Read the Codebase Patterns section in progress.txt before starting
diff --git a/ralph.sh b/ralph.sh
index 677b120c..ab070614 100755
--- a/ralph.sh
+++ b/ralph.sh
@@ -1,11 +1,25 @@
 #!/bin/bash
 # Ralph Wiggum - Long-running AI agent loop
-# Usage: ./ralph.sh [max_iterations]
+# Usage: ./ralph.sh [max_iterations] [cli_tool] [model] [share]
+# cli_tool: amp (default) or opencode
+# model: opencode model ID or amp mode (smart/rush)
+# share: true/false (default: false) - share session for opencode
 
 set -e
 
 MAX_ITERATIONS=${1:-10}
+CLI_TOOL=${2:-amp}
+MODEL=${3:-}
+SHARE=${4:-false}
 SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+PROMPT_FILE="$SCRIPT_DIR/prompt-$CLI_TOOL.md"
+
+# Set opencode permissions via environment variable (equivalent to --dangerously-allow-all)
+if [ "$CLI_TOOL" = "opencode" ]; then
+	export OPENCODE_PERMISSION='{"*": "allow"}'
+	export OPENCODE_DISABLE_AUTOCOMPACT=true
+fi
+
 PRD_FILE="$SCRIPT_DIR/prd.json"
 PROGRESS_FILE="$SCRIPT_DIR/progress.txt"
 ARCHIVE_DIR="$SCRIPT_DIR/archive"
@@ -13,65 +27,86 @@ LAST_BRANCH_FILE="$SCRIPT_DIR/.last-branch"
 
 # Archive previous run if branch changed
 if [ -f "$PRD_FILE" ] && [ -f "$LAST_BRANCH_FILE" ]; then
-  CURRENT_BRANCH=$(jq -r '.branchName // empty' "$PRD_FILE" 2>/dev/null || echo "")
-  LAST_BRANCH=$(cat "$LAST_BRANCH_FILE" 2>/dev/null || echo "")
-  
-  if [ -n "$CURRENT_BRANCH" ] && [ -n "$LAST_BRANCH" ] && [ "$CURRENT_BRANCH" != "$LAST_BRANCH" ]; then
-    # Archive the previous run
-    DATE=$(date +%Y-%m-%d)
-    # Strip "ralph/" prefix from branch name for folder
-    FOLDER_NAME=$(echo "$LAST_BRANCH" | sed 's|^ralph/||')
-    ARCHIVE_FOLDER="$ARCHIVE_DIR/$DATE-$FOLDER_NAME"
-    
-    echo "Archiving previous run: $LAST_BRANCH"
-    mkdir -p "$ARCHIVE_FOLDER"
-    [ -f "$PRD_FILE" ] && cp "$PRD_FILE" "$ARCHIVE_FOLDER/"
-    [ -f "$PROGRESS_FILE" ] && cp "$PROGRESS_FILE" "$ARCHIVE_FOLDER/"
-    echo "   Archived to: $ARCHIVE_FOLDER"
-    
-    # Reset progress file for new run
-    echo "# Ralph Progress Log" > "$PROGRESS_FILE"
-    echo "Started: $(date)" >> "$PROGRESS_FILE"
-    echo "---" >> "$PROGRESS_FILE"
-  fi
+	CURRENT_BRANCH=$(jq -r '.branchName // empty' "$PRD_FILE" 2>/dev/null || echo "")
+	LAST_BRANCH=$(cat "$LAST_BRANCH_FILE" 2>/dev/null || echo "")
+
+	if [ -n "$CURRENT_BRANCH" ] && [ -n "$LAST_BRANCH" ] && [ "$CURRENT_BRANCH" != "$LAST_BRANCH" ]; then
+		# Archive the previous run
+		DATE=$(date +%Y-%m-%d)
+		# Strip "ralph/" prefix from branch name for folder
+		FOLDER_NAME=$(echo "$LAST_BRANCH" | sed 's|^ralph/||')
+		ARCHIVE_FOLDER="$ARCHIVE_DIR/$DATE-$FOLDER_NAME"
+
+		echo "Archiving previous run: $LAST_BRANCH"
+		mkdir -p "$ARCHIVE_FOLDER"
+		[ -f "$PRD_FILE" ] && cp "$PRD_FILE" "$ARCHIVE_FOLDER/"
+		[ -f "$PROGRESS_FILE" ] && cp "$PROGRESS_FILE" "$ARCHIVE_FOLDER/"
+		echo "   Archived to: $ARCHIVE_FOLDER"
+
+		# Reset progress file for new run
+		echo "# Ralph Progress Log" >"$PROGRESS_FILE"
+		echo "Started: $(date)" >>"$PROGRESS_FILE"
+		echo "---" >>"$PROGRESS_FILE"
+	fi
 fi
 
 # Track current branch
 if [ -f "$PRD_FILE" ]; then
-  CURRENT_BRANCH=$(jq -r '.branchName // empty' "$PRD_FILE" 2>/dev/null || echo "")
-  if [ -n "$CURRENT_BRANCH" ]; then
-    echo "$CURRENT_BRANCH" > "$LAST_BRANCH_FILE"
-  fi
+	CURRENT_BRANCH=$(jq -r '.branchName // empty' "$PRD_FILE" 2>/dev/null || echo "")
+	if [ -n "$CURRENT_BRANCH" ]; then
+		echo "$CURRENT_BRANCH" >"$LAST_BRANCH_FILE"
+	fi
 fi
 
 # Initialize progress file if it doesn't exist
 if [ ! -f "$PROGRESS_FILE" ]; then
-  echo "# Ralph Progress Log" > "$PROGRESS_FILE"
-  echo "Started: $(date)" >> "$PROGRESS_FILE"
-  echo "---" >> "$PROGRESS_FILE"
+	echo "# Ralph Progress Log" >"$PROGRESS_FILE"
+	echo "Started: $(date)" >>"$PROGRESS_FILE"
+	echo "---" >>"$PROGRESS_FILE"
 fi
 
 echo "Starting Ralph - Max iterations: $MAX_ITERATIONS"
+if [ -n "$MODEL" ]; then
+	echo "Using CLI: $CLI_TOOL (model: $MODEL)"
+else
+	echo "Using CLI: $CLI_TOOL (default model)"
+fi
+if [ "$CLI_TOOL" = "opencode" ]; then
+	echo "Share session: $SHARE"
+fi
 
 for i in $(seq 1 $MAX_ITERATIONS); do
-  echo ""
-  echo "═══════════════════════════════════════════════════════"
-  echo "  Ralph Iteration $i of $MAX_ITERATIONS"
-  echo "═══════════════════════════════════════════════════════"
-  
-  # Run amp with the ralph prompt
-  OUTPUT=$(cat "$SCRIPT_DIR/prompt.md" | amp --dangerously-allow-all 2>&1 | tee /dev/stderr) || true
-  
-  # Check for completion signal
-  if echo "$OUTPUT" | grep -q "<promise>COMPLETE</promise>"; then
-    echo ""
-    echo "Ralph completed all tasks!"
-    echo "Completed at iteration $i of $MAX_ITERATIONS"
-    exit 0
-  fi
-  
-  echo "Iteration $i complete. Continuing..."
-  sleep 2
+	echo ""
+	echo "═══════════════════════════════════════════════════════"
+	echo "  Ralph Iteration $i of $MAX_ITERATIONS"
+	echo "═══════════════════════════════════════════════════════"
+
+	# Run amp or opencode with the ralph prompt
+	if [ "$CLI_TOOL" = "opencode" ]; then
+		OPENCODE_MODEL=${MODEL:-opencode/big-pickle}
+		if [ "$SHARE" = "true" ]; then
+			OUTPUT=$(cat "$PROMPT_FILE" | opencode run -m "$OPENCODE_MODEL" --agent build --share - 2>&1 | tee /dev/stderr) || true
+		else
+			OUTPUT=$(cat "$PROMPT_FILE" | opencode run -m "$OPENCODE_MODEL" --agent build - 2>&1 | tee /dev/stderr) || true
+		fi
+	else
+		if [ -n "$MODEL" ]; then
+			OUTPUT=$(cat "$PROMPT_FILE" | amp --dangerously-allow-all --mode "$MODEL" 2>&1 | tee /dev/stderr) || true
+		else
+			OUTPUT=$(cat "$PROMPT_FILE" | amp --dangerously-allow-all 2>&1 | tee /dev/stderr) || true
+		fi
+	fi
+
+	# Check for completion signal
+	if echo "$OUTPUT" | grep -q "<promise>COMPLETE</promise>"; then
+		echo ""
+		echo "Ralph completed all tasks!"
+		echo "Completed at iteration $i of $MAX_ITERATIONS"
+		exit 0
+	fi
+
+	echo "Iteration $i complete. Continuing..."
+	sleep 2
 done
 
 echo ""