balance

balance is a command for coding agents from rhan1/crewline. It costs 13 tokens per session (281 once invoked), scanned A, original, MIT.

A command that checks spending limits across AI service providers and recommends where the next task should run.

In plain words
What is it for?
Use it before substantial work to decide whether to spread tasks across providers or keep them with one provider.
Why use it?
It prevents one provider from running out of allowance while another provider's allowance expires unused. It also turns quota data into a short routing decision.

Command

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/rhan1/crewline/balance
Clone the repo
git clone --depth 1 https://github.com/rhan1/crewline

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 balance

README.md
[![agentmods](https://agentmods.dev/badge/commands/rhan1/crewline/balance.svg)](https://agentmods.dev/commands/rhan1/crewline/balance)
Your own site
<a href="https://agentmods.dev/commands/rhan1/crewline/balance"><img src="https://agentmods.dev/badge/commands/rhan1/crewline/balance.svg" alt="Measured on agentmods" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 281 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 $0.00013 $0.00281
Opus 5 $0.00006 $0.00140
Sonnet 5 $0.00003 $0.00056
Haiku 4.5 $0.00001 $0.00028

Measured 3d ago against content hash 3539a13e7793, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

balance 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 3d 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/balance.md · 22 lines

What it actually says

Run the cross-provider quota balancer and explain the result in plain English.

node ~/.claude/scripts/quota-balance.mjs

Then give Raza a short read-out — no jargon, no table repetition:

  1. Who's in trouble — any provider in FLOOR BREACH or CONSERVE, and how long until it refills. A provider at 0% with days to go is the headline; say it first.
  2. What's about to be wasted — any provider in SPEND state whose reset is within ~24h. That budget disappears unused. Name it and say how long is left to burn it.
  3. Where work should go right now — the ROUTE TO line, translated: "mechanical work goes to X today, not Y."

Then, if he's about to start something substantial, say explicitly whether to fan out wide or stay narrow.

Keep the whole reply under ~8 lines. He wants the call, not the arithmetic.

Reading the surplus number: it's % budget left − % of the window still to come. Positive means he's underspending and will forfeit budget at reset; negative means he's outrunning the refill and will strand himself. Zero is perfectly on pace. That single number is the only thing being ranked.

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. 3d ago First seen · 22 lines · 13 tokens per session scan A 3539a13e7793

Subscribe to this mod's changes

balance is a command published in the GitHub repository rhan1/crewline (2 stars, last pushed 9d ago), licensed MIT. It adds 13 tokens to every session and 281 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.