The status line, the prompt hook, and the /sled skill.
Claude Code is the first harness. sleds init points it at your seat, installs the status line, the /sled skill and the hooks, and changes nothing else. Nothing happens in your session until you ask for an estimate or hit a limit; then the exits arrive before your next prompt and one word answers them. sleds off returns the agent to your seat directly.
Wall: usage limit reached. Session snapshotted.
Provider: Weekly limit reached. Resets Thursday 9:00 am.
Remaining work: $4.10–9.30 · 20–55 min · 82%
1 Continue now platform key · allowance left $38.00
2 Hold until reset free · resumes 9:00 am EDT · saves ≈ $6.70 vs continuing now
3 Run overnight batch tier · ½ price
4 Switch model sonnet 5 · platform key · $0.90–2.10 · same time · rest of session
5 Hand off to Dana (idle 42m) · Slack + /sled pickup
6 Defer to reset runs itself 9:00 am EDT · same model · full price · $4.10–9.30
Reply /sled 1, /sled 2, /sled 3, /sled 4, /sled 5 or /sled 6. wall jd7k2m9qa41p
> /sled 6
Deferred. It runs itself when your seat resets — same model, done in minutes, full price. Starts 9:00 am EDT → /sled jobs to watch.Reads
Bars, credits, the reset, the session, the model.
The /sled commands: intake, estimate, jobs, resume, pickup, 1–6 at a wall.
The provider's limit error and a snapshot of the request, so the session can resume or travel.
Writes
⛷ fable 62% · resets thu 9:00 · $38 allowance. Amber at 90%, red at the wall.
Printed inside the session; the policy's default marked.
Hold, defer or hand off, and the session comes back where it was.
In Claude Code, in its own words.
Everything sleds writes into Claude Code is something Claude Code already knows how to show. If you leave, it keeps the rows.
Next. The musher for defer and overnight already runs Claude Code headless; the next step is pre-parking a hand-off before the wall when the estimate says it will cross.