diff --git a/src/plyngent/cli/app.py b/src/plyngent/cli/app.py
index a722059..0860d3c 100644
--- a/src/plyngent/cli/app.py
+++ b/src/plyngent/cli/app.py
@@ -300,9 +300,14 @@ async def _run_chat(  # noqa: C901, PLR0912, PLR0915 — chat orchestration
         # Path denylist and policy confirm live on instance.workspace (no process bag).
         state.instance_state.workspace.path_denylist = tuple(store.agent_config.path_denylist or ())
         if interactive:
-            from plyngent.cli.limits import prompt_policy_command_confirm
+            from plyngent.cli.limits import prompt_policy_command_confirm, prompt_policy_fetch_confirm
+            from plyngent.tools.net import set_fetch_policy_confirm_hook
 
             state.instance_state.workspace.policy_confirm_hook = prompt_policy_command_confirm
+            set_fetch_policy_confirm_hook(
+                prompt_policy_fetch_confirm,
+                instance=state.instance_state,
+            )
         # Seed cache if we already fetched; else warm in background for Tab.
         if remote_ids is not None:
             state.seed_remote_models(remote_ids)
@@ -334,6 +339,10 @@ async def _run_chat(  # noqa: C901, PLR0912, PLR0915 — chat orchestration
         if isinstance(state_obj, ReplState):
             state_obj.instance_state.workspace.policy_confirm_hook = None
             state_obj.instance_state.workspace.policy_allowed_commands.clear()
+            from plyngent.tools.net import clear_private_grants, set_fetch_policy_confirm_hook
+
+            set_fetch_policy_confirm_hook(None, instance=state_obj.instance_state)
+            clear_private_grants(instance=state_obj.instance_state)
             await state_obj.instance_state.shutdown()
         else:
             # No ReplState: only PTY class cleanup (temps require instance allowlist).
diff --git a/src/plyngent/cli/limits.py b/src/plyngent/cli/limits.py
index 553d01e..b987940 100644
--- a/src/plyngent/cli/limits.py
+++ b/src/plyngent/cli/limits.py
@@ -232,6 +232,51 @@ def prompt_policy_command_confirm(
         return False
 
 
+def prompt_policy_fetch_confirm(
+    host: str,
+    port: int,
+    url: str,
+    timeout_seconds: float,
+) -> bool:
+    """Ask whether to allow fetch to a private/loopback host (timed).
+
+    Independent of YOLO: always prompts when interactive. Default is **deny**.
+    Timeout, cancel, or non-interactive → False. On approve, the host:port is
+    granted for the rest of this process (see net grants).
+    """
+    reason = (
+        f"fetch targets private/loopback host {host!r} port {port}\n"
+        f"url: {url}\n"
+        f"Allow this host:port for the rest of this process?\n"
+        f"(timeout {timeout_seconds:g}s defaults to DENY; not skipped by YOLO)"
+    )
+    try:
+        with pause_task_cancel_for_prompt():
+            backend = get_prompt_backend()
+            if not backend.is_interactive():
+                return False
+            backend.echo()
+            backend.secho(format_tool_confirm_box("policy", reason), fg="yellow")
+            backend.echo()
+            grant = f"{host}:{port}"
+            prompt = f"[policy] allow fetch {grant!r}? [y/N] (timeout {timeout_seconds:g}s): "
+            with contextlib.suppress(OSError):
+                _ = sys.stderr.write(prompt)
+                _ = sys.stderr.flush()
+            raw = _read_yes_no_line_with_timeout(timeout_seconds)
+            if raw is None:
+                with contextlib.suppress(OSError, NonInteractiveError):
+                    backend.secho(
+                        f"[policy] timed out after {timeout_seconds:g}s — denied",
+                        fg="red",
+                        err=True,
+                    )
+                return False
+            return raw.strip().lower() in {"y", "yes"}
+    except NonInteractiveError, KeyboardInterrupt, EOFError:
+        return False
+
+
 async def prompt_confirm_tool_async(name: str, args: Mapping[str, object], reason: str) -> bool | str:
     """Async confirm: True allow, False deny, str = deny with user comment."""
     del args
diff --git a/src/plyngent/config/models.py b/src/plyngent/config/models.py
index e9fccb9..8315d73 100644
--- a/src/plyngent/config/models.py
+++ b/src/plyngent/config/models.py
@@ -29,6 +29,14 @@ raise `max_replaces` or narrow `old_string`.
 for ordered pipelines (`pipe_out` / `mix_stderr` as needed).
 - Prefer `vcs_*` for status/diff/log/branch when enough.
 
+### Network
+- Prefer `fetch` (GET/POST/PUT/DELETE) for HTTP(S) docs/APIs over curl/wget via shell.
+- Set `user_agent` (or a User-Agent header) when the remote expects a specific client; \
+otherwise a small default is used. Never rely on shell to spoof identity.
+- Private/loopback/LAN hosts need an explicit human policy allow (not skipped by YOLO).
+- Prefer provider hosted search (e.g. web_search) for open-ended research; use `fetch` for known URLs.
+- Respect denials, size limits, and HTTPS→HTTP redirect blocks; do not re-fetch the same URL repeatedly.
+
 ### Humans & safety
 - Prefer `ask_user_line` / `ask_user_choice` / `ask_user_form` over waiting for the next free-form turn.
 - Overwrites, deletes, shells, and risky ops may require human confirm; hard denylists are not skipped by YOLO.