diff --git a/docs/cost.md b/docs/cost.md
index f59a66f..1ab5bae 100644
--- a/docs/cost.md
+++ b/docs/cost.md
@@ -28,6 +28,13 @@ monitor is now a stable feature (v2.1.98+) and is the preferred method for long-
 
 that $200 covers everything. hundreds of sessions, thousands of subagent spawns. run `/lore` to see your own numbers.
 
+
+
+
+### background sessions (v2.1.144+)
+
+background sessions started via `claude --bg` now support `/resume`, allowing you to check on agent progress without interrupting. background subagent completion notifications now show elapsed time (e.g. "Agent completed · 3h 2m 5s"). background sessions still count against your monthly budget; use them for long-running agents where you don't need real-time interaction.
+
 ### what your plan costs
 
 | plan | monthly | how billing works |
diff --git a/docs/hooks.md b/docs/hooks.md
index a553038..a1ad167 100644
--- a/docs/hooks.md
+++ b/docs/hooks.md
@@ -53,6 +53,13 @@ PreToolUse hooks (safety-guard, no-squash) fire on every Bash call -- 10K+ times
 
 
 
+
+
+
+### note on background sessions and hooks (v2.1.144+)
+
+hooks fire normally in background sessions. PreToolUse hooks will continue to block dangerous commands even when agents run in the background. SessionEnd hooks fire when the background session completes.
+
 ### hook performance notes (v2.1.140+)
 PreToolUse hooks on Bash commands need to complete in <50ms to avoid user-facing latency. the hooks listed above are optimized for speed -- they use jq for JSON parsing and regex for pattern matching rather than spawning subprocesses. profile your custom hooks with `time` if you add new ones.
 
diff --git a/docs/tips/README.md b/docs/tips/README.md
index e7d6e89..e8dc5d3 100644
--- a/docs/tips/README.md
+++ b/docs/tips/README.md
@@ -23,3 +23,7 @@ short, standalone claude code tips. each one is a specific technique you can use
 ---
 
 | [monitor](./monitor.md) | watch background processes, react to output in real time (v2.1.98+, stable as of v2.1.140) |
+
+---
+
+| [background sessions](./background-sessions.md) | run agents in the background, resume later, track elapsed time (v2.1.144+) |
diff --git a/docs/tips/fast-mode.md b/docs/tips/fast-mode.md
index e857e68..c45b8ad 100644
--- a/docs/tips/fast-mode.md
+++ b/docs/tips/fast-mode.md
@@ -8,6 +8,13 @@ fast mode keeps you on opus. it does not switch to a cheaper or smaller model. w
 
 this is the most common misconception i see. people assume fast mode = dumber model. it's not. it's the same opus with a tighter thinking budget.
 
+
+
+
+### note on model defaults (v2.1.144+)
+
+`/model` now changes the model for the current session only. to set a default model for all new sessions, press `d` in the model picker. this means you can switch models mid-session without affecting future sessions.
+
 ## why i don't use it
 
 never use fast mode. i mean it. the only scenario where fast mode makes sense is if you're at a hackathon with 30 minutes left before demo, or you're someone who literally doesn't care about burning through usage. fast mode can easily run up over a hundred dollars of usage in half an hour.