diff --git a/conductor/directives/convention_enforcement_4_mechanisms/meta.md b/conductor/directives/convention_enforcement_4_mechanisms/meta.md
new file mode 100644
index 00000000..9209849a
--- /dev/null
+++ b/conductor/directives/convention_enforcement_4_mechanisms/meta.md
@@ -0,0 +1,7 @@
+# convention_enforcement_4_mechanisms
+
+## v1
+
+**Why this iteration:** Lifted verbatim from `docs/AGENTS.md:27-62 (Convention Enforcement §4 mechanisms)`.
+**Source:** `docs/AGENTS.md:27-62 (Convention Enforcement §4 mechanisms)`
+**Lifted:** 2026-07-02 (Phase A expansion harvest; user directive 2026-07-02)
diff --git a/conductor/directives/convention_enforcement_4_mechanisms/v1.md b/conductor/directives/convention_enforcement_4_mechanisms/v1.md
new file mode 100644
index 00000000..550a2fad
--- /dev/null
+++ b/conductor/directives/convention_enforcement_4_mechanisms/v1.md
@@ -0,0 +1,27 @@
+## Convention Enforcement: the 4 mechanisms (defense-in-depth)
+
+1. **`conductor/code_styleguides/data_oriented_design.md` §8.5 (The Python Type Promotion Mandate)** — the canonical mandate. Banned patterns: `dict[str, Any]`, `Any`, `Optional[T]`, `hasattr()` for entity dispatch, `getattr()` for type-dispatch, `.get()` on known fields.
+
+2. **`conductor/code_styleguides/python.md` §17 (LLM Default Anti-Patterns)** — the explicit cheatsheet. Each banned pattern has a before/after example.
+
+3. **`conductor/code_styleguides/error_handling.md`** — the `Result[T]` + `NIL_T` convention. Replaces `Optional[T]` returns.
+
+4. **The enforcement audit scripts** — the project-level enforcement set:
+ - `scripts/audit_weak_types.py --strict` — flags `dict[str, Any]`, `Any`, anonymous tuples
+ - `scripts/audit_optional_in_3_files.py --strict` — flags `Optional[T]` return types in the baseline refactored files. An all-`src/*.py` successor (`audit_optional_returns.py`) is referenced in older planning docs but is NOT yet built — the live script today is `audit_optional_in_3_files.py`.
+ - `scripts/audit_exception_handling.py --strict` — the data-oriented error handling convention
+ - `scripts/audit_main_thread_imports.py` — always strict; the import graph gate
+ - `scripts/audit_no_models_config_io.py` — the config-I/O ownership gate
+ - The boundary-layer audit (planned in `conductor/tracks/cruft_elimination_20260627/spec.md`) — documents every `Metadata` usage
+
+**Pre-commit workflow (recommended):**
+
+```bash
+uv run python scripts/audit_weak_types.py
+uv run python scripts/audit_optional_in_3_files.py
+uv run python scripts/audit_exception_handling.py
+uv run python scripts/audit_main_thread_imports.py
+uv run python scripts/audit_no_models_config_io.py
+```
+
+**Why this is enforced:** the convention prevents the LLM-training-data problem. Without these mechanisms, AI agents writing new code will revert to idiomatic patterns — exactly the tech rot the user is preventing. The 5+ mechanisms (Core Value + 3 styleguides + 5 audit scripts) are the defense-in-depth.
diff --git a/conductor/directives/core_value_read_first/meta.md b/conductor/directives/core_value_read_first/meta.md
new file mode 100644
index 00000000..8c3afb8a
--- /dev/null
+++ b/conductor/directives/core_value_read_first/meta.md
@@ -0,0 +1,7 @@
+# core_value_read_first
+
+## v1
+
+**Why this iteration:** Lifted verbatim from `docs/AGENTS.md:17-25 (Convention Enforcement §Core Value)`.
+**Source:** `docs/AGENTS.md:17-25 (Convention Enforcement §Core Value)`
+**Lifted:** 2026-07-02 (Phase A expansion harvest; user directive 2026-07-02)
diff --git a/conductor/directives/core_value_read_first/v1.md b/conductor/directives/core_value_read_first/v1.md
new file mode 100644
index 00000000..1674ac0f
--- /dev/null
+++ b/conductor/directives/core_value_read_first/v1.md
@@ -0,0 +1,11 @@
+### Core Value (Added 2026-06-25)
+
+**C11/Odin/Jai semantics in a Python runtime.** The project is written in Python because of practical constraints (time, dependencies, LLM codegen ability), but the convention is to make Python behave as close to a statically-typed value-typed language as the runtime allows.
+
+LLMs default to opaque types (`dict[str, Any]`, `Any`, `Optional[T]`, `hasattr()` polymorphism) because that's what idiomatic Python training data looks like. **That defaults to mediocrity. This rule overrides it.**
+
+The canonical mandate is in `conductor/code_styleguides/data_oriented_design.md` §8.5 (The Python Type Promotion Mandate). The banned patterns are in `conductor/code_styleguides/python.md` §17 (LLM Default Anti-Patterns). The boundary-layer concept is in `conductor/code_styleguides/type_aliases.md`.
+
+**Every section of every styleguide and every deep-dive guide MUST be read through the lens of this Core Value.** If a section suggests `dict[str, Any]`, `Any`, `Optional[T]`, or `hasattr()` for entity dispatch in non-boundary code, that's an anti-pattern; flag it and ask.
+
+**READ THIS BEFORE WRITING ANY PYTHON IN THIS REPO.**