diff --git a/.github/PULL_REQUEST_TEMPLATE.md b/.github/PULL_REQUEST_TEMPLATE.md
new file mode 100644
index 000000000..acf4d0c60
--- /dev/null
+++ b/.github/PULL_REQUEST_TEMPLATE.md
@@ -0,0 +1,315 @@
+# Pull Request: [Title]
+
+<!--
+  Guidelines for a great PR:
+  - Use a clear, descriptive title following conventional commits format
+  - Fill out all relevant sections below
+  - Delete sections that don't apply (but keep the core sections)
+  - Reference related issues and PRs
+  - Add screenshots/videos for UI changes
+  - Ensure all tests pass and code is properly formatted
+-->
+
+## 📋 Summary
+
+<!--
+  Provide a clear, concise summary (2-4 sentences) of what this PR does.
+  Focus on WHAT changed and WHY, not HOW (code explains the how).
+-->
+
+## 🎯 Related Issues
+
+<!--
+  Link to related issues, PRs, or documentation:
+  - Closes #123
+  - Related to #456
+  - Depends on #789
+  - Reference: [Document Name](/path/to/doc.md)
+-->
+
+Closes #
+
+## 🚀 What's New
+
+<!--
+  Detail the changes made in this PR. Organize by feature/component.
+  Use subheadings (###) for major sections.
+  Include code snippets for complex changes.
+-->
+
+### Core Changes
+
+#### 1. [Feature/Component Name]
+
+**Purpose**: [Why this change was made]
+
+**Implementation**:
+
+- Change 1
+- Change 2
+- Change 3
+
+**Key Code** (if applicable):
+
+```javascript
+// Show important code snippets with file paths
+// /path/to/file.js:123-145
+```
+
+## 📊 Type of Change
+
+<!-- Check all that apply -->
+
+- [ ] 🐛 Bug fix (non-breaking change that fixes an issue)
+- [ ] ✨ New feature (non-breaking change that adds functionality)
+- [ ] 💥 Breaking change (fix or feature that would cause existing functionality to change)
+- [ ] 📝 Documentation update
+- [ ] 🔧 Configuration change
+- [ ] ♻️ Code refactoring (no functional changes)
+- [ ] ⚡ Performance improvement
+- [ ] 🎨 UI/UX change
+- [ ] 🧪 Test coverage improvement
+- [ ] 🔒 Security fix
+
+## 🧪 Testing
+
+<!--
+  Describe testing performed to validate changes.
+  Include both automated tests and manual testing.
+-->
+
+### Automated Tests
+
+- [ ] Unit tests added/updated
+- [ ] Integration tests added/updated
+- [ ] All existing tests pass
+
+**Test Coverage**:
+
+- [ ] New code has test coverage
+- [ ] Edge cases covered
+- [ ] Error handling tested
+
+**Test Results**:
+
+```bash
+# Include test output or summary
+✓ 42 tests passing
+✓ 0 tests failing
+```
+
+### Manual Testing
+
+<!-- Describe manual testing steps performed -->
+
+**Testing Checklist**:
+
+- [ ] Tested in development environment
+- [ ] Tested in staging environment (if applicable)
+- [ ] Tested with real data/production-like scenarios
+- [ ] Tested error scenarios
+- [ ] Verified no console errors/warnings
+- [ ] Checked browser console for issues (frontend changes)
+
+**Environments Tested**:
+
+- [ ] Development
+- [ ] Staging
+- [ ] Production (if safe to test)
+
+## 📸 Screenshots/Videos
+
+<!--
+  Include screenshots or videos for UI changes.
+  Use before/after comparisons for visual changes.
+  Delete this section if not applicable.
+-->
+
+### Before
+
+<!-- Screenshot/video of previous behavior -->
+
+### After
+
+<!-- Screenshot/video of new behavior -->
+
+## 🚀 Deployment Strategy
+
+<!--
+  Describe how this should be deployed.
+  Include rollout plan for risky changes.
+-->
+
+### Deployment Steps
+
+1. Step 1
+2. Step 2
+3. Step 3
+
+### Configuration Changes
+
+<!-- List any environment variables, feature flags, or config changes needed -->
+
+- [ ] Environment variables added/updated: `VARIABLE_NAME=value`
+- [ ] Feature flags required: `FEATURE_FLAG=true`
+- [ ] Database migrations needed
+- [ ] External service configuration required
+
+### Phased Rollout (if applicable)
+
+- [ ] **Phase 1**: Deploy to staging for validation (recommended duration: X days)
+- [ ] **Phase 2**: Deploy to production with feature flag disabled
+- [ ] **Phase 3**: Enable feature flag for production traffic
+- [ ] **Phase 4**: Monitor metrics and remove feature flag
+
+## 🔙 Rollback Plan
+
+<!--
+  Describe how to quickly rollback if issues occur.
+  Critical for production deployments.
+-->
+
+**Quick Rollback**:
+
+- Disable feature flag: `FEATURE_FLAG=false` and restart service (< 1 minute)
+- OR: Revert to previous deployment revision
+- OR: Git revert commit hash
+
+**Cleanup Required** (if rollback is performed):
+
+- [ ] Database changes to revert
+- [ ] Cache to clear
+- [ ] External services to notify
+
+## 💰 Cost Impact
+
+<!--
+  Estimate cost impact for cloud services, APIs, storage, etc.
+  Delete if not applicable.
+-->
+
+**Expected Cost Changes**:
+
+- Cloud Run: +/- $X/month
+- Storage: +/- $X/month
+- API calls: +/- $X/month
+- **Total Estimated Impact**: +/- $X/month
+
+**Cost Optimization Notes**:
+
+- [Explain any cost optimizations included]
+
+## ⚡ Performance Impact
+
+<!--
+  Describe performance impact (positive or negative).
+  Include benchmarks for significant changes.
+-->
+
+**Expected Performance Changes**:
+
+- Response time: +/- Xms
+- Memory usage: +/- XMB
+- Database queries: +/- X queries
+- API calls: +/- X calls
+
+**Benchmarks** (if applicable):
+
+```text
+Before: Xms average response time
+After:  Xms average response time
+```
+
+## 🔍 Code Quality
+
+<!--
+  Pre-commit hooks should catch most issues automatically.
+  Confirm code quality checks passed.
+-->
+
+- [x] ESLint passed (auto-checked by pre-commit hooks)
+- [x] Prettier formatting applied (auto-checked by pre-commit hooks)
+- [x] Markdownlint passed for docs (auto-checked by pre-commit hooks)
+- [x] Commit messages follow conventional commits
+- [ ] Code reviewed by AI agent or peer
+- [ ] No console.log statements in production code
+- [ ] No commented-out code left behind
+- [ ] Error handling implemented for edge cases
+- [ ] Security considerations reviewed (XSS, SQL injection, auth, etc.)
+
+## 📚 Documentation
+
+<!--
+  Ensure documentation is updated for changes.
+  Delete sections that don't apply.
+-->
+
+- [ ] README.md updated (if user-facing changes)
+- [ ] CONTRIBUTING.md updated (if dev workflow changes)
+- [ ] API documentation updated (if API changes)
+- [ ] Inline code comments added for complex logic
+- [ ] Architecture documentation updated (if structural changes)
+- [ ] CLAUDE.md updated (for AI context in future sessions)
+
+## 🔐 Security Considerations
+
+<!--
+  Address security implications of changes.
+  Required for security-sensitive changes.
+-->
+
+- [ ] No sensitive data logged or exposed
+- [ ] Authentication/authorization implemented correctly
+- [ ] Input validation added for user input
+- [ ] SQL injection prevention (parameterized queries)
+- [ ] XSS prevention (sanitized output)
+- [ ] CSRF protection (if applicable)
+- [ ] Secrets stored securely (not in code/logs)
+- [ ] Rate limiting considered (if applicable)
+
+## 📋 Pre-Merge Checklist
+
+<!--
+  Final checklist before merging.
+  All items should be checked.
+-->
+
+- [ ] All tests pass locally
+- [ ] All pre-commit hooks pass
+- [ ] Code has been self-reviewed
+- [ ] Changes generate no new warnings
+- [ ] Dependent changes have been merged
+- [ ] Documentation has been updated
+- [ ] Reviewer(s) have approved the PR
+- [ ] Branch is up to date with base branch
+- [ ] Commit messages are clean and descriptive
+- [ ] Ready for production deployment
+
+## 🔗 Additional Context
+
+<!--
+  Add any additional context, screenshots, benchmarks, or notes.
+  Links to external resources, design docs, API references, etc.
+-->
+
+## 🚦 Status
+
+<!-- Update as PR progresses -->
+
+- [ ] 🔴 Draft - Work in progress
+- [ ] 🟡 Ready for Review - Code complete, needs review
+- [ ] 🟢 Approved - Ready to merge
+- [ ] 🔵 Merged - Deployed to staging
+- [ ] ✅ Complete - Deployed to production
+
+---
+
+<!--
+  For Reviewers:
+  - Check code quality and adherence to project standards
+  - Verify tests cover new functionality
+  - Confirm documentation is updated
+  - Test changes locally if possible
+  - Ensure security considerations are addressed
+  - Validate deployment plan is safe
+-->
diff --git a/src/agents/system-prompt.ts b/src/agents/system-prompt.ts
index ed97fd539..9624fdb2d 100644
--- a/src/agents/system-prompt.ts
+++ b/src/agents/system-prompt.ts
@@ -83,21 +83,21 @@ function buildMessagingSection(params: {
     "- Never use exec/curl for provider messaging; Moltbot handles all routing internally.",
     params.availableTools.has("message")
       ? [
-          "",
-          "### message tool",
-          "- Use `message` for proactive sends + channel actions (polls, reactions, etc.).",
-          "- For `action=send`, include `to` and `message`.",
-          `- If multiple channels are configured, pass \`channel\` (${params.messageChannelOptions}).`,
-          `- If you use \`message\` (\`action=send\`) to deliver your user-visible reply, respond with ONLY: ${SILENT_REPLY_TOKEN} (avoid duplicate replies).`,
-          params.inlineButtonsEnabled
-            ? "- Inline buttons supported. Use `action=send` with `buttons=[[{text,callback_data}]]` (callback_data routes back as a user message)."
-            : params.runtimeChannel
-              ? `- Inline buttons not enabled for ${params.runtimeChannel}. If you need them, ask to set ${params.runtimeChannel}.capabilities.inlineButtons ("dm"|"group"|"all"|"allowlist").`
-              : "",
-          ...(params.messageToolHints ?? []),
-        ]
-          .filter(Boolean)
-          .join("\n")
+        "",
+        "### message tool",
+        "- Use `message` for proactive sends + channel actions (polls, reactions, etc.).",
+        "- For `action=send`, include `to` and `message`.",
+        `- If multiple channels are configured, pass \`channel\` (${params.messageChannelOptions}).`,
+        `- If you use \`message\` (\`action=send\`) to deliver your user-visible reply, respond with ONLY: ${SILENT_REPLY_TOKEN} (avoid duplicate replies).`,
+        params.inlineButtonsEnabled
+          ? "- Inline buttons supported. Use `action=send` with `buttons=[[{text,callback_data}]]` (callback_data routes back as a user message)."
+          : params.runtimeChannel
+            ? `- Inline buttons not enabled for ${params.runtimeChannel}. If you need them, ask to set ${params.runtimeChannel}.capabilities.inlineButtons ("dm"|"group"|"all"|"allowlist").`
+            : "",
+        ...(params.messageToolHints ?? []),
+      ]
+        .filter(Boolean)
+        .join("\n")
       : "",
     "",
   ];
@@ -282,15 +282,15 @@ export function buildAgentSystemPrompt(params: {
       : undefined;
   const reasoningHint = params.reasoningTagHint
     ? [
-        "ALL internal reasoning MUST be inside <think>...</think>.",
-        "Do not output any analysis outside <think>.",
-        "Format every reply as <think>...</think> then <final>...</final>, with no other text.",
-        "Only the final user-visible reply may appear inside <final>.",
-        "Only text inside <final> is shown to the user; everything else is discarded and never seen by the user.",
-        "Example:",
-        "<think>Short internal reasoning.</think>",
-        "<final>Hey there! What would you like to do next?</final>",
-      ].join(" ")
+      "ALL internal reasoning MUST be inside <think>...</think>.",
+      "Do not output any analysis outside <think>.",
+      "Format every reply as <think>...</think> then <final>...</final>, with no other text.",
+      "Only the final user-visible reply may appear inside <final>.",
+      "Only text inside <final> is shown to the user; everything else is discarded and never seen by the user.",
+      "Example:",
+      "<think>Short internal reasoning.</think>",
+      "<final>Hey there! What would you like to do next?</final>",
+    ].join(" ")
     : undefined;
   const reasoningLevel = params.reasoningLevel ?? "off";
   const userTimezone = params.userTimezone?.trim();
@@ -336,21 +336,21 @@ export function buildAgentSystemPrompt(params: {
     toolLines.length > 0
       ? toolLines.join("\n")
       : [
-          "Pi lists the standard tools above. This runtime enables:",
-          "- grep: search file contents for patterns",
-          "- find: find files by glob pattern",
-          "- ls: list directory contents",
-          "- apply_patch: apply multi-file patches",
-          `- ${execToolName}: run shell commands (supports background via yieldMs/background)`,
-          `- ${processToolName}: manage background exec sessions`,
-          "- browser: control clawd's dedicated browser",
-          "- canvas: present/eval/snapshot the Canvas",
-          "- nodes: list/describe/notify/camera/screen on paired nodes",
-          "- cron: manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)",
-          "- sessions_list: list sessions",
-          "- sessions_history: fetch session history",
-          "- sessions_send: send to another session",
-        ].join("\n"),
+        "Pi lists the standard tools above. This runtime enables:",
+        "- grep: search file contents for patterns",
+        "- find: find files by glob pattern",
+        "- ls: list directory contents",
+        "- apply_patch: apply multi-file patches",
+        `- ${execToolName}: run shell commands (supports background via yieldMs/background)`,
+        `- ${processToolName}: manage background exec sessions`,
+        "- browser: control clawd's dedicated browser",
+        "- canvas: present/eval/snapshot the Canvas",
+        "- nodes: list/describe/notify/camera/screen on paired nodes",
+        "- cron: manage cron jobs and wake events (use for reminders; when scheduling a reminder, write the systemEvent text as something that will read like a reminder when it fires, and mention that it is a reminder depending on the time gap between setting and firing; include recent context in reminder text if appropriate)",
+        "- sessions_list: list sessions",
+        "- sessions_history: fetch session history",
+        "- sessions_send: send to another session",
+      ].join("\n"),
     "TOOLS.md does not control tool availability; it is user guidance for how to use external tools.",
     "If a task is more complex or takes longer, spawn a sub-agent. It will do the work for you and ping you when it's done. You can always check up on it.",
     "",
@@ -375,11 +375,11 @@ export function buildAgentSystemPrompt(params: {
     hasGateway && !isMinimal ? "## Moltbot Self-Update" : "",
     hasGateway && !isMinimal
       ? [
-          "Get Updates (self-update) is ONLY allowed when the user explicitly asks for it.",
-          "Do not run config.apply or update.run unless the user explicitly requests an update or config change; if it's not explicit, ask first.",
-          "Actions: config.get, config.schema, config.apply (validate + write full config, then restart), update.run (update deps or git, then restart).",
-          "After restart, Moltbot pings the last active session automatically.",
-        ].join("\n")
+        "Get Updates (self-update) is ONLY allowed when the user explicitly asks for it.",
+        "Do not run config.apply or update.run unless the user explicitly requests an update or config change; if it's not explicit, ask first.",
+        "Actions: config.get, config.schema, config.apply (validate + write full config, then restart), update.run (update deps or git, then restart).",
+        "After restart, Moltbot pings the last active session automatically.",
+      ].join("\n")
       : "",
     hasGateway && !isMinimal ? "" : "",
     "",
@@ -399,47 +399,57 @@ export function buildAgentSystemPrompt(params: {
     "Treat this directory as the single global workspace for file operations unless explicitly instructed otherwise.",
     ...workspaceNotes,
     "",
+    ...(runtimeInfo?.os?.toLowerCase().includes("windows")
+      ? [
+        "## Windows Shell Guidance",
+        "You are running on Windows (PowerShell).",
+        "- Use PowerShell syntax (e.g. `$env:VAR` instead of `%VAR%` or `$VAR`).",
+        "- Do NOT use Unix commands like `grep`, `sed`, `awk`, `head`, `tail` unless you are sure they are installed.",
+        "- Use `findstr` or `Select-String` instead of `grep`.",
+        "- Use `Get-ChildItem` (dir/ls) with `-Recurse` instead of `find`.",
+        "",
+      ]
+      : []),
     ...docsSection,
     params.sandboxInfo?.enabled ? "## Sandbox" : "",
     params.sandboxInfo?.enabled
       ? [
-          "You are running in a sandboxed runtime (tools execute in Docker).",
-          "Some tools may be unavailable due to sandbox policy.",
-          "Sub-agents stay sandboxed (no elevated/host access). Need outside-sandbox read/write? Don't spawn; ask first.",
-          params.sandboxInfo.workspaceDir
-            ? `Sandbox workspace: ${params.sandboxInfo.workspaceDir}`
+        "You are running in a sandboxed runtime (tools execute in Docker).",
+        "Some tools may be unavailable due to sandbox policy.",
+        "Sub-agents stay sandboxed (no elevated/host access). Need outside-sandbox read/write? Don't spawn; ask first.",
+        params.sandboxInfo.workspaceDir
+          ? `Sandbox workspace: ${params.sandboxInfo.workspaceDir}`
+          : "",
+        params.sandboxInfo.workspaceAccess
+          ? `Agent workspace access: ${params.sandboxInfo.workspaceAccess}${params.sandboxInfo.agentWorkspaceMount
+            ? ` (mounted at ${params.sandboxInfo.agentWorkspaceMount})`
+            : ""
+          }`
+          : "",
+        params.sandboxInfo.browserBridgeUrl ? "Sandbox browser: enabled." : "",
+        params.sandboxInfo.browserNoVncUrl
+          ? `Sandbox browser observer (noVNC): ${params.sandboxInfo.browserNoVncUrl}`
+          : "",
+        params.sandboxInfo.hostBrowserAllowed === true
+          ? "Host browser control: allowed."
+          : params.sandboxInfo.hostBrowserAllowed === false
+            ? "Host browser control: blocked."
             : "",
-          params.sandboxInfo.workspaceAccess
-            ? `Agent workspace access: ${params.sandboxInfo.workspaceAccess}${
-                params.sandboxInfo.agentWorkspaceMount
-                  ? ` (mounted at ${params.sandboxInfo.agentWorkspaceMount})`
-                  : ""
-              }`
-            : "",
-          params.sandboxInfo.browserBridgeUrl ? "Sandbox browser: enabled." : "",
-          params.sandboxInfo.browserNoVncUrl
-            ? `Sandbox browser observer (noVNC): ${params.sandboxInfo.browserNoVncUrl}`
-            : "",
-          params.sandboxInfo.hostBrowserAllowed === true
-            ? "Host browser control: allowed."
-            : params.sandboxInfo.hostBrowserAllowed === false
-              ? "Host browser control: blocked."
-              : "",
-          params.sandboxInfo.elevated?.allowed
-            ? "Elevated exec is available for this session."
-            : "",
-          params.sandboxInfo.elevated?.allowed
-            ? "User can toggle with /elevated on|off|ask|full."
-            : "",
-          params.sandboxInfo.elevated?.allowed
-            ? "You may also send /elevated on|off|ask|full when needed."
-            : "",
-          params.sandboxInfo.elevated?.allowed
-            ? `Current elevated level: ${params.sandboxInfo.elevated.defaultLevel} (ask runs exec on host with approvals; full auto-approves).`
-            : "",
-        ]
-          .filter(Boolean)
-          .join("\n")
+        params.sandboxInfo.elevated?.allowed
+          ? "Elevated exec is available for this session."
+          : "",
+        params.sandboxInfo.elevated?.allowed
+          ? "User can toggle with /elevated on|off|ask|full."
+          : "",
+        params.sandboxInfo.elevated?.allowed
+          ? "You may also send /elevated on|off|ask|full when needed."
+          : "",
+        params.sandboxInfo.elevated?.allowed
+          ? `Current elevated level: ${params.sandboxInfo.elevated.defaultLevel} (ask runs exec on host with approvals; full auto-approves).`
+          : "",
+      ]
+        .filter(Boolean)
+        .join("\n")
       : "",
     params.sandboxInfo?.enabled ? "" : "",
     ...buildUserIdentitySection(ownerLine, isMinimal),
@@ -472,22 +482,22 @@ export function buildAgentSystemPrompt(params: {
     const guidanceText =
       level === "minimal"
         ? [
-            `Reactions are enabled for ${channel} in MINIMAL mode.`,
-            "React ONLY when truly relevant:",
-            "- Acknowledge important user requests or confirmations",
-            "- Express genuine sentiment (humor, appreciation) sparingly",
-            "- Avoid reacting to routine messages or your own replies",
-            "Guideline: at most 1 reaction per 5-10 exchanges.",
-          ].join("\n")
+          `Reactions are enabled for ${channel} in MINIMAL mode.`,
+          "React ONLY when truly relevant:",
+          "- Acknowledge important user requests or confirmations",
+          "- Express genuine sentiment (humor, appreciation) sparingly",
+          "- Avoid reacting to routine messages or your own replies",
+          "Guideline: at most 1 reaction per 5-10 exchanges.",
+        ].join("\n")
         : [
-            `Reactions are enabled for ${channel} in EXTENSIVE mode.`,
-            "Feel free to react liberally:",
-            "- Acknowledge messages with appropriate emojis",
-            "- Express sentiment and personality through reactions",
-            "- React to interesting content, humor, or notable events",
-            "- Use reactions to confirm understanding or agreement",
-            "Guideline: react whenever it feels natural.",
-          ].join("\n");
+          `Reactions are enabled for ${channel} in EXTENSIVE mode.`,
+          "Feel free to react liberally:",
+          "- Acknowledge messages with appropriate emojis",
+          "- Express sentiment and personality through reactions",
+          "- React to interesting content, humor, or notable events",
+          "- Use reactions to confirm understanding or agreement",
+          "Guideline: react whenever it feels natural.",
+        ].join("\n");
     lines.push("## Reactions", guidanceText, "");
   }
   if (reasoningHint) {