Skip to content
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 7 additions & 0 deletions docs/cost.md
Original file line number Diff line number Diff line change
Expand Up @@ -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 |
Expand Down
7 changes: 7 additions & 0 deletions docs/hooks.md
Original file line number Diff line number Diff line change
Expand Up @@ -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.

Expand Down
4 changes: 4 additions & 0 deletions docs/tips/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -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+) |
7 changes: 7 additions & 0 deletions docs/tips/fast-mode.md
Original file line number Diff line number Diff line change
Expand Up @@ -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.
Expand Down