# Budgets and Rate Limits — AI Coding-Agent Guardrails

Source: https://www.geekswithgeeks.com/en/coding-agent-guardrails/hook-budgets

> Cap steps, time, tokens and risky actions per session.

## Limit how much damage one session can do

Add limits that apply to the **whole session**: maximum steps, wall-clock time, tokens or spend, and a cap on **risky actions** (for example no more than 5 file deletions or 3 package installs). Hitting a limit should stop the agent and ask a human to continue. This catches loops and runaway behaviour that no single action check would notice.

## A simple action limiter, run

I ran this. With a limit of 3, the first three risky actions pass and the next two are refused.

```python
class Limiter:
    def __init__(self, n): self.n, self.used = n, 0
    def hit(self):
        self.used += 1
        return self.used <= self.n

l = Limiter(3)
print([l.hit() for _ in range(5)])
```

Output:

```
[True, True, True, False, False]
```

## Ask a human at the limit

When a budget is hit, show what the agent did and what it wanted to do next. A person can then extend the limit knowingly, instead of the agent silently carrying on.

**Quiz:** What does a session-wide budget catch that per-action checks miss?

- [ ] Spelling mistakes
- [x] Loops and runaway behaviour across many individually fine actions
- [ ] Slow keyboards
- [ ] Missing semicolons

*Answer:* Loops and runaway behaviour across many individually fine actions. Each action may look fine alone while the total is clearly excessive.