diff --git a/gsd-openclaw/.planning/phases/03-orchestration/03-VALIDATION.md b/gsd-openclaw/.planning/phases/03-orchestration/03-VALIDATION.md
new file mode 100644
index 0000000..f63e0a0
--- /dev/null
+++ b/gsd-openclaw/.planning/phases/03-orchestration/03-VALIDATION.md
@@ -0,0 +1,82 @@
+---
+phase: 03
+slug: orchestration
+status: draft
+nyquist_compliant: false
+wave_0_complete: false
+created: 2026-03-11
+---
+
+# Phase 3 — Validation Strategy
+
+> Per-phase validation contract for feedback sampling during execution.
+
+---
+
+## Test Infrastructure
+
+| Property | Value |
+|----------|-------|
+| **Framework** | pytest (existing from Phase 1) |
+| **Config file** | tests/conftest.py (existing) |
+| **Quick run command** | `pytest tests/ -v -x` |
+| **Full suite command** | `pytest tests/ -v --cov=src/gsd_openclaw` |
+| **Estimated runtime** | ~15 seconds |
+
+---
+
+## Sampling Rate
+
+- **After every task commit:** Run `pytest tests/ -v -x`
+- **After every plan wave:** Run `pytest tests/ -v --cov=src/gsd_openclaw`
+- **Before `/gsd:verify-work`:** Full suite must be green
+- **Max feedback latency:** 15 seconds
+
+---
+
+## Per-Task Verification Map
+
+| Task ID | Plan | Wave | Requirement | Test Type | Automated Command | File Exists | Status |
+|---------|------|------|-------------|-----------|-------------------|-------------|--------|
+| 03-01-01 | 01 | 1 | BRDG-01 | unit | `pytest tests/test_orchestrator.py::test_route_command -v` | ❌ W0 | ⬜ pending |
+| 03-01-02 | 01 | 1 | OCLW-03 | unit | `pytest tests/test_orchestrator.py::test_command_router -v` | ❌ W0 | ⬜ pending |
+| 03-02-01 | 02 | 1 | BRDG-02 | unit | `pytest tests/test_command_executor.py::test_capture_output -v` | ❌ W0 | ⬜ pending |
+| 03-03-01 | 03 | 2 | BRDG-04 | unit | `pytest tests/test_approval_handler.py -v` | ❌ W0 | ⬜ pending |
+| 03-04-01 | 04 | 2 | BRDG-05 | unit | `pytest tests/test_progress_monitor.py -v` | ❌ W0 | ⬜ pending |
+| 03-05-01 | 05 | 3 | BRDG-03 | unit | `pytest tests/test_orchestrator.py::test_error_detection -v` | ❌ W0 | ⬜ pending |
+| 03-06-01 | 06 | 3 | OCLW-05 | integration | Manual verification | N/A | ⬜ pending |
+| 03-06-02 | 06 | 3 | OCLW-06 | integration | Manual verification | N/A | ⬜ pending |
+
+*Status: ⬜ pending · ✅ green · ❌ red · ⚠️ flaky*
+
+---
+
+## Wave 0 Requirements
+
+- [ ] `tests/test_orchestrator.py` — stubs for BRDG-01, BRDG-03, OCLW-03
+- [ ] `tests/test_command_executor.py` — stubs for BRDG-02
+- [ ] `tests/test_approval_handler.py` — stubs for BRDG-04
+- [ ] `tests/test_progress_monitor.py` — stubs for BRDG-05
+- [ ] Mock fixtures for tmux pane operations
+
+---
+
+## Manual-Only Verifications
+
+| Behavior | Requirement | Why Manual | Test Instructions |
+|----------|-------------|------------|-------------------|
+| OpenClaw dmPolicy integration | OCLW-05 | Requires running OpenClaw gateway | Deploy skill to OpenClaw, send test message from unauthorized user, verify rejection |
+| Multi-channel support | OCLW-06 | Requires multiple chat platforms | Test /gsd:* commands via Feishu, verify card rendering and callbacks |
+
+---
+
+## Validation Sign-Off
+
+- [ ] All tasks have `<automated>` verify or Wave 0 dependencies
+- [ ] Sampling continuity: no 3 consecutive tasks without automated verify
+- [ ] Wave 0 covers all MISSING references
+- [ ] No watch-mode flags
+- [ ] Feedback latency < 15s
+- [ ] `nyquist_compliant: true` set in frontmatter
+
+**Approval:** pending