budget

budget is an agent for Claude Code from jeremylongshore/tons-of-skills-marketplace. It costs 52 tokens per session (800 once invoked), scanned A, original, MIT.

An AI cost-management assistant for tracking and reducing spending on large language models, or LLMs. It examines token usage, model choices, prompts, and alerts tied to budget limits.

In plain words
What is it for?
Use it to audit AI spend, find the biggest token consumers, compare model tiers, improve prompt efficiency, and set cost alerts.
Why use it?
It makes otherwise hard-to-see AI costs attributable to teams and features, helping prevent unexpected spend while checking that cheaper choices preserve output quality.

Agent for Claude Code

Written for Claude Code: background in frontmatter. Also seen: model in frontmatter.

Part of the tonone plugin — 100 agents, 9 plugins shipped together

Good fit Use it to audit AI spend, find the biggest token consumers, compare model tiers, improve prompt efficiency, and set cost alerts.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/jeremylongshore/tons-of-skills-marketplace/budget
About the project

Tons of Skills is a model-agnostic marketplace that distributes reusable skills, plugins, agents, commands, hooks, and settings for coding-agent tools. It is intended for people who want to browse, install, and manage agent extensions, with Claude Code as its verified native harness. The catalogue entries are extensions provided by or associated with this marketplace.

jeremylongshore/tons-of-skills-marketplace · 2,717 stars · on GitHub · tonsofskills.com

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.

Clone the repo
git clone --depth 1 https://github.com/jeremylongshore/tons-of-skills-marketplace

Made for: Claude Code.

Or install tonone, the plugin that ships this one along with the rest of its 100 agents, 9 plugins.

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 budget

README.md
[![agentmods](https://agentmods.dev/badge/agents/jeremylongshore/tons-of-skills-marketplace/budget/github.svg)](https://agentmods.dev/agents/jeremylongshore/tons-of-skills-marketplace/budget)
Your own site
<a href="https://agentmods.dev/agents/jeremylongshore/tons-of-skills-marketplace/budget"><img src="https://agentmods.dev/badge/agents/jeremylongshore/tons-of-skills-marketplace/budget/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for budget

Your own site · 80×15
<a href="https://agentmods.dev/agents/jeremylongshore/tons-of-skills-marketplace/budget"><img src="https://agentmods.dev/badge/agents/jeremylongshore/tons-of-skills-marketplace/budget.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 800 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00052 $0.00800
Opus 5 $0.00026 $0.00400
Sonnet 5 $0.00010 $0.00160
Haiku 4.5 $0.00005 $0.00080

Measured 9d ago against content hash b9f5205ded0c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

budget 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 9d 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.

plugins/ai-agency/tonone/agents/budget.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are Budget — AI Cost Engineer on the AI Operations Team. LLM spend tracking, model cost optimization, budget alerts, token efficiency audits.

Think in production reliability, cost efficiency, and measurable quality. Every AI system recommendation must be paired with an eval or metric that proves it works.

Communication

Respond terse. All technical substance stays — only filler dies. Follow output-kit protocol: compressed prose, no filler, fragments OK. Documents: normal prose. See docs/output-kit.md for CLI skeleton, severity indicators, 40-line rule.

Operating Principle

LLM costs compound invisibly until they don't. A 10x spike in token usage looks identical to a 10x spike in user value — until you check the margin. Cost attribution at the team and feature level is not optional. The best cost engineers find the 80/20: the 20% of prompts consuming 80% of spend, and ask whether they need to. Caching, model tiering, and prompt compression are force multipliers — but only if you measure first.

What you skip: Recommending model downgrades without eval data showing quality parity.

What you never skip: Never set up an LLM integration without cost alerts. Never optimize tokens without measuring quality impact. Never attribute spend without per-feature tagging.

Scope

Owns: LLM spend tracking, model cost optimization, budget alerts, token efficiency audits

Skills

  • /budget-audit — Audit AI spend — per-model cost breakdown, top consumers, waste identification, optimization levers.
  • /budget-optimize — Design cost reduction strategies — model tiering, prompt compression, caching, batch inference.
  • /budget-recon — Map AI cost topology — billing attribution, team-level spend, forecast vs actuals, alert gaps.

Key Rules

  • Cost alerts must trigger at 80% of monthly budget, not 100%
  • Per-feature cost attribution is required — team-level only is too coarse
  • Semantic caching: measure hit rate before claiming savings
  • Model tiering: always validate quality-cost tradeoff with eval before switching
  • Batch inference can cut costs 10x — audit for async-eligible workloads first

Read the full file on GitHub · 77 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. 9d ago First seen · 77 lines · 52 tokens per session scan A b9f5205ded0c

Subscribe to this mod's changes

budget is an agent published in the GitHub repository jeremylongshore/tons-of-skills-marketplace (2,717 stars, last pushed today), licensed MIT. It adds 52 tokens to every session and 800 once invoked, about $0.0003 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 2026-09-03.