provider-limits

provider-limits is a command for coding agents from AttendantLion8/provider-fallback-plugin. It costs 14 tokens per session (848 once invoked), scanned A, original, MIT.

A command for setting daily and monthly token limits for individual AI providers. Token limits are usage caps, and reaching one causes automatic switching to the next provider in the priority list.

In plain words
What is it for?
Use it to view limits or set them for a provider with values such as 500K, 1M, a raw number, or unlimited.
Why use it?
It helps control provider usage and avoid continuing to send requests after an allowance is reached. It also reduces manual work when switching providers.

Command

Installs and runs on its own, but its text points at files inside the plugin that ships it — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed.

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/attendantlion8/provider-fallback-plugin/provider-limits
Clone the repo
git clone --depth 1 https://github.com/AttendantLion8/provider-fallback-plugin

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for provider-limits

README.md
[![agentmods](https://agentmods.dev/badge/commands/attendantlion8/provider-fallback-plugin/provider-limits.svg)](https://agentmods.dev/commands/attendantlion8/provider-fallback-plugin/provider-limits)
Your own site
<a href="https://agentmods.dev/commands/attendantlion8/provider-fallback-plugin/provider-limits"><img src="https://agentmods.dev/badge/commands/attendantlion8/provider-fallback-plugin/provider-limits.svg" alt="Measured on agentmods" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 848 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00014 $0.00848
Opus 5 $0.00007 $0.00424
Sonnet 5 $0.00003 $0.00170
Haiku 4.5 $0.00001 $0.00085

Measured 5d ago against content hash 31d052d02690, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

provider-limits scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

commands/provider-limits.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Provider Usage Limits Configuration

Configure token usage limits for each provider. When a provider reaches its limit, the system automatically switches to the next provider in the priority list.

Usage

View All Limits

/provider-limits

Set Limits for a Provider

/provider-limits <provider> --daily <limit> --monthly <limit>

Examples

# Set Anthropic limits to 1M daily, 10M monthly
/provider-limits anthropic --daily 1M --monthly 10M

# Set Bedrock with higher limits
/provider-limits bedrock --daily 5M --monthly 50M

# Set OpenRouter limits
/provider-limits openrouter --daily 500K --monthly 5M

Limit Format

Limits can be specified in multiple formats:

Format Example Value
Raw number 1000000 1,000,000 tokens
K suffix 500K 500,000 tokens
M suffix 1M 1,000,000 tokens
Unlimited 0 or unlimited No limit

Implementation

When this command is invoked:

  1. Parse provider and limit arguments
  2. Convert limit strings to numbers
  3. Update configuration in ~/.opencode/provider-fallback/config.json
  4. Display updated limits

Parse Limit Helper

function parseLimit(value) {
  if (!value || value === 'unlimited') return 0;
  
  const str = value.toString().toUpperCase();
  
  if (str.endsWith('M')) {
    return parseFloat(str) * 1000000;
  } else if (str.endsWith('K')) {
    return parseFloat(str) * 1000;
  }
  
  return parseInt(str, 10);
}

Display Current Limits

const { loadConfig } = require('${CLAUDE_PLUGIN_ROOT}/lib/providers.js');
const config = loadConfig();

console.log('\n=== Provider Usage Limits ===\n');

for (const [provider, limits] of Object.entries(config.usageLimits)) {
  const daily = limits.dailyTokens === 0 ? 'Unlimited' : limits.dailyTokens.toLocaleString();
  const monthly = limits.monthlyTokens === 0 ? 'Unlimited' : limits.monthlyTokens.toLocaleString();
  
  console.log(`${provider}:`);
  console.log(`  Daily:   ${daily} tokens`);
  console.log(`  Monthly: ${monthly} tokens`);
  console.log('');
}

Read the full file on GitHub · 122 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 122 lines · 14 tokens per session scan A 31d052d02690

Subscribe to this mod's changes

provider-limits is a command published in the GitHub repository AttendantLion8/provider-fallback-plugin (2 stars, last pushed 8mo ago), licensed MIT. It adds 14 tokens to every session and 848 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.