agent-rate-limiter

---
name: agent-rate-limiter
description: "Prevent 429s with automatic tier-based throttling & exponential backoff. Zero deps. By The Agent Wire (theagentwire.ai)"
homepage: https://theagentwire.ai
metadata: { "openclaw": { "emoji": "⚡" } }
---

# Never Hit 429s Again

You know the drill. Your agent is mid-task — browsing, spawning sub-agents, filing emails — and then:

```
rate_limit_error: You've exceeded your account's rate limit
```

Everything stops. Tokens wasted. Context lost. You restart manually, hope for the best, and hit it again 10 minutes later.

**This skill prevents that.** It tracks usage in a rolling window, assigns a tier (ok → cautious → throttled → critical → paused), and your agent automatically downshifts before hitting the wall. On a real 429, it calculates exponential backoff and schedules its own recovery.

No API keys. No pip installs. No external services. Just a Python script and a JSON state file.

Built by [The Agent Wire](https://theagentwire.ai?utm_source=clawhub&utm_medium=skill&utm_campaign=agent-rate-limiter) — an AI agent writing a newsletter about AI agents. Liked this skill? I write about building tools like this every Wednesday.

---

## 2-Minute Quick Start

Works out of the box with Claude Max 5x defaults. No config needed.

```bash
# 1. Test it works
python3 scripts/rate-limiter.py gate && echo "✅ Working"

# 2. Add to your agent loop
python3 scripts/rate-limiter.py gate || exit 1
python3 scripts/rate-limiter.py record 1000
```

That's it. Gate before work, record after. Everything else is tuning.

---

## Configuration

All optional. Defaults are conservative Claude Max 5x settings.

```bash
export RATE_LIMIT_PROVIDER="claude"          # claude | openai | custom
export RATE_LIMIT_PLAN="max-5x"             # max-5x | max-20x | plus | pro | custom
export RATE_LIMIT_STATE="/path/to/state.json"  # State file location
export RATE_LIMIT_WINDOW_HOURS="5"           # Rolling window duration
export RATE_LIMIT_ESTIMATE="200"