cost-awareness

Guidance for choosing AI models with their request costs in mind, especially for Cursor Enterprise teams.

In plain words
What is it for?
Use it when selecting models or planning AI-assisted coding, reviews, edits, and multi-step agent tasks.
Why use it?
It helps avoid unnecessary spending by matching expensive models and open-ended agent work to tasks that truly need them.

Cursor rule

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 rules/ofershap/cursor-usage/cost-awareness
Clone the repo
git clone --depth 1 https://github.com/ofershap/cursor-usage
Per session 184 This file is loaded in full into every session.
When invoked 184 The same file — it is already loaded in full.
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 $0.00184 $0.00184
Opus 5 $0.00092 $0.00092
Sonnet 5 $0.00037 $0.00037
Haiku 4.5 $0.00018 $0.00018

Measured yesterday against content hash f30e554008f1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cost-awareness 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 yesterday.

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

rules/cost-awareness.mdc · 13 lines

What it actually says

When discussing model selection, code generation approaches, or AI-assisted workflows, keep cost implications in mind:

  • Premium models (Opus, GPT-5) cost 10-50x more per request than standard models (Sonnet, GPT-4o, Gemini Flash).
  • Most coding tasks — completions, inline edits, chat questions, code review — work well with standard-tier models.
  • Reserve premium models for genuinely complex multi-step reasoning, architectural decisions, or agent mode tasks that require deep understanding.
  • Agent mode loops are the #1 cause of unexpected spend spikes. Prefer focused, well-scoped agent tasks over open-ended exploration.
  • If the user has the cursor-usage MCP server configured, you can check their team's actual spending with get_team_overview or get_spending.
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. yesterday First seen · 13 lines · 184 tokens per session scan A f30e554008f1

Subscribe to this mod's changes

cost-awareness is a cursor rule published in the GitHub repository ofershap/cursor-usage (8 stars, last pushed 6mo ago), licensed MIT. It adds 184 tokens to every session, about $0.0009 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.