diff --git a/conductor/directives/profile_first_optimize_second/meta.md b/conductor/directives/profile_first_optimize_second/meta.md
new file mode 100644
index 00000000..0a81bcf4
--- /dev/null
+++ b/conductor/directives/profile_first_optimize_second/meta.md
@@ -0,0 +1,9 @@
+# profile_first_optimize_second
+
+## v1
+
+**Why this iteration:** Lifted from `docs/reports/2026-05-11/ai_decoupling_revert_report.md` §"Lessons Learned". The agent decoupled the AI client SDK imports from the main GUI under the assumption that the heavy SDKs caused startup latency; profiling later showed RAG initialization was the actual 5+ second bottleneck. The decoupling work was reverted; the lazy RAG import fix landed instead. The principle generalizes: do not reach for an architectural change until profiling has named the specific bottleneck.
+**Source:** `docs/reports/2026-05-11/ai_decoupling_revert_report.md:116-121`
+
+---
+**Lifted:** 2026-07-03 (scavenge sweep batch 2/5: docs/reports/2026-05-11 + 2026-06-01)
\ No newline at end of file
diff --git a/conductor/directives/profile_first_optimize_second/v1.md b/conductor/directives/profile_first_optimize_second/v1.md
new file mode 100644
index 00000000..74a6a669
--- /dev/null
+++ b/conductor/directives/profile_first_optimize_second/v1.md
@@ -0,0 +1 @@
+# Profile and measure the actual bottleneck before attempting any architectural change to address it
\ No newline at end of file
diff --git a/conductor/directives/surface_gaps_at_discovery_not_checkpoint/meta.md b/conductor/directives/surface_gaps_at_discovery_not_checkpoint/meta.md
new file mode 100644
index 00000000..6c93dabf
--- /dev/null
+++ b/conductor/directives/surface_gaps_at_discovery_not_checkpoint/meta.md
@@ -0,0 +1,9 @@
+# surface_gaps_at_discovery_not_checkpoint
+
+## v1
+
+**Why this iteration:** Lifted from `docs/reports/2026-06-01/...` references and the explicit "Lessons (Tech Lead Process)" section in `qwen_llama_grok_followup_audit_20260611.md` and "Lessons Learned" in `qwen_llama_grok_followup_session_end_20260611.md`. The Tech Lead completed Phase 1 with a "all good!" checkpoint that hid a deferred-vendor scope gap; the user pushed back: "did you find something that the spec/plan didn't cover and not report it properly?". The correct pattern is to report scope issues immediately when discovered, not buried in a commit body or footnote.
+**Source:** `docs/reports/2026-06-08/qwen_llama_grok_followup_audit_20260611.md` §"Lessons (Tech Lead Process)" + `docs/reports/2026-06-08/qwen_llama_grok_followup_session_end_20260611.md` §"Lessons Learned (Session-Wide)" item 3
+
+---
+**Lifted:** 2026-07-03 (scavenge sweep batch 2/5: docs/reports/2026-05-11 + 2026-06-01)
\ No newline at end of file
diff --git a/conductor/directives/surface_gaps_at_discovery_not_checkpoint/v1.md b/conductor/directives/surface_gaps_at_discovery_not_checkpoint/v1.md
new file mode 100644
index 00000000..98cd6895
--- /dev/null
+++ b/conductor/directives/surface_gaps_at_discovery_not_checkpoint/v1.md
@@ -0,0 +1 @@
+# Surface scope gaps and architectural deviations the moment they are discovered, not buried in a checkpoint commit
\ No newline at end of file