How I Auto-Resume a Rate-Limited Claude Code Session with PROGRESS.md and Retries

My previous post, Making costs visible by monitoring output tokens, was about stopping overuse. This time it's the opposite problem: how to keep waking up a session that has stalled — the story of resume-on-ratelimit.sh.

I got burned more than once by handing a long task to Claude Code, stepping away from my desk, and coming back to find it had halted on a rate limit. Restarting by hand is tedious, and when the restart is delayed, it forgets the earlier context and starts over. This article is a record of how I solved that problem in 20 lines of shell script.

The problem: long tasks stall halfway on rate limits

When you run a headless task with claude -p, the process exits non-zero the moment it hits your plan's 5h block or 7d block. Two things go wrong here.

1. The record of "how far the task got" disappears — a plain re-run starts over from the beginning
2. You don't notice — if you're not watching the terminal, you don't even know it stopped

The pattern I settled on: use PROGRESS.md as a "handoff ticket" and carry the work forward with --continue retries.

Using PROGRESS.md as a handoff ticket

When I hand a task to Claude, I include an instruction in the first prompt: "update PROGRESS.md at each work boundary." Claude naturally follows this, continuously writing completed steps, remaining steps, and notes into the file.

# PROGRESS.md（Claude が自動更新）

## 完了
- [x] 依存パッケージの調査
- [x] ディレクトリ構造の設計

## 進行中
- [ ] 各モジュールのスケルトン生成

## 次に実行すること
モジュールAのテストを先に書く。設計メモは ./design.md 参照。

With this in place, the restart prompt can be a single line: "Read PROGRESS.md and continue the interrupted work". Claude reads the file and resumes from what's left.

The full resume-on-ratelimit.sh

Here is the complete script quoted from the real file (~/.claude/scripts/resume-on-ratelimit.sh).

#!/usr/bin/env bash
# レートリミットで止まったら自動で再開するラッパー
# 使い方: bash resume-on-ratelimit.sh [追加の指示]
#         bash resume-on-ratelimit.sh "PROGRESS.mdを読んで作業を再開して"

set -euo pipefail

WAIT_MINUTES=${WAIT_MINUTES:-5}
MAX_RETRIES=${MAX_RETRIES:-20}
TASK="${1:-PROGRESS.mdを読んで中断した作業を続けて。作業済みなら何もしない。}"
RETRY=0

notify() {
  osascript -e "display notification \"$1\" with title \"Claude Code\"" 2>/dev/null || true
}

echo "[$(date '+%H:%M')] 起動: $TASK"

while [ $RETRY -lt $MAX_RETRIES ]; do
  if [ $RETRY -eq 0 ]; then
    claude --dangerously-skip-permissions --continue -p "$TASK"
    EXIT=$?
  else
    echo "[$(date '+%H:%M')] リトライ $RETRY / $MAX_RETRIES"
    claude --dangerously-skip-permissions --continue -p "PROGRESS.mdを読んで中断した作業を続けて。"
    EXIT=$?
  fi

  if [ $EXIT -eq 0 ]; then
    echo "[$(date '+%H:%M')] 完了"
    notify "Claude Code: 作業完了"
    exit 0
  fi

  RETRY=$((RETRY + 1))
  echo "[$(date '+%H:%M')] レートリミット検出 (exit: $EXIT)。${WAIT_MINUTES}分後にリトライ..."
  notify "Claude Code: レートリミット。${WAIT_MINUTES}分後に再開します"
  sleep $((WAIT_MINUTES * 60))
done

echo "最大リトライ回数に達しました"
notify "Claude Code: 最大リトライ超過。手動確認してください"
exit 1

The whole design fits in a 20-line loop.

The exit code is the only signal for detecting a rate limit

The claude command returns exit 0 on a clean finish and non-zero otherwise. As it stands, any exit code other than 0 on a rate limit can be used for the check. I do not strictly separate out "this is the rate-limit-specific code."

The script's premise is a deliberate simplification: non-zero = a state that should wait and retry. It has the side effect of also retrying tasks that are completely failing, but capping the count with MAX_RETRIES prevents an infinite loop.

--dangerously-skip-permissions is essential for unattended operation. Without it, a confirmation prompt appears on every tool use and blocks. That said, when you use this flag, narrow allowedTools in the prompt or scope it strictly to trusted, task-specific work.

The MAX_RETRIES guard

With the defaults MAX_RETRIES=20 and WAIT_MINUTES=5, it waits for at most 100 minutes (20 × 5 min). A 7d block resets a week later, so in practice these parameters cover "rate limits within a few hours."

They can be overridden via environment variables, so you can tune them to the situation.

# 10分ごとに最大5回だけ待つ例
WAIT_MINUTES=10 MAX_RETRIES=5 bash resume-on-ratelimit.sh "重いタスク"

When MAX_RETRIES is reached, it exits with exit 1 and fires a notification. A parent script or launchd can catch this exit 1 and wire it up to an alert.

Combining with macOS notifications

notify() fires a macOS system notification via osascript.

notify() {
  osascript -e "display notification \"$1\" with title \"Claude Code\"" 2>/dev/null || true
}

The || true is there so that even under the script's set -e, a failed notification (no notification permission, etc.) doesn't kill the process.

Notifications fire at three moments: when a rate limit is detected, when a retry succeeds, and when MAX_RETRIES is exceeded. Even when you're away from your desk, the Dock bounce lets you notice.

Integration with autopilot.sh: three launches via launchd

autopilot.sh is launched by launchd (com.lily.autopilot.plist) three times a day: at 2:00, 5:00, and 23:00.

<key>StartCalendarInterval</key>
<array>
  <dict><key>Hour</key><integer>2</integer><key>Minute</key><integer>0</integer></dict>
  <dict><key>Hour</key><integer>5</integer><key>Minute</key><integer>0</integer></dict>
  <dict><key>Hour</key><integer>23</integer><key>Minute</key><integer>0</integer></dict>
</array>

2 AM and 11 PM are the "set a long task running" hours; 5 AM is meant to "make progress before I wake up." What covers the gaps outside these launch windows is resume-on-ratelimit.sh, which I use as a wrapper when I manually run a long task.

autopilot.sh is designed to stop autonomously after one Phase (up to 40 turns), so it doesn't need a retry loop, but resume-on-ratelimit.sh is for the case where the user wants to "keep it running until this process finishes."

Pitfalls I hit

• Re-running without --continue starts a new session → the previous context is gone, and even reading PROGRESS.md, it has no memory of "which files it was touching." Always use --continue together with it.
• If you forget to instruct it to update PROGRESS.md, the handoff ticket comes up empty → the restart prompt whiffs on "do nothing if already done" and just ends. Always put "update PROGRESS.md at each boundary" in the first prompt.
• A non-zero exit isn't always a rate limit → if it dies on a syntax error or misconfiguration, it will keep retrying. Once you exceed MAX_RETRIES, manual verification is needed.
• Watch out for combining set -euo pipefail with || true → if another command sneaks in before you capture EXIT=$?, the exit code gets overwritten. If you modify the script, be careful about when you capture the variable.
• launchd jobs are skipped while macOS is asleep → resume-on-ratelimit.sh, being a shell sleep loop, resumes after waking even if it was asleep. If you need the autopilot side, configure wake on schedule with pmset.

Summary

• Use PROGRESS.md as a handoff ticket: just instruct Claude to "update it at each boundary," and the restart prompt is a single line
• Exit-code checks are enough for rate-limit detection: non-zero → wait → resume with --continue, a loop you can build in 20 lines
• A MAX_RETRIES guard is essential: set an upper bound so a fully stuck task isn't retried forever
• macOS notifications are a one-liner with osascript: don't forget || true, so a failed notification doesn't kill the process under set -e
• Its role differs from the launchd autopilot: autopilot is a scheduled, autonomous improvement loop; resume-on-ratelimit is an attended-job wrapper for "just until this task finishes"

Next time I'll write about a problem that ironically emerged because this automation foundation grew — the story of how skills and agents multiplied until context injection hit 228 KB, and the audit that trimmed it to 48 KB.

Written by **Lily* — I ship iOS apps and automate my content stack with Claude Code.
Follow along: Portfolio · X · GitHub*