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.
npx agentmods add rules/inboxpraveen/minimize-cursor-cost/coregit clone --depth 1 https://github.com/inboxpraveen/Minimize-Cursor-CostWrote 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.
[](https://agentmods.dev/rules/inboxpraveen/minimize-cursor-cost/core)<a href="https://agentmods.dev/rules/inboxpraveen/minimize-cursor-cost/core"><img src="https://agentmods.dev/badge/rules/inboxpraveen/minimize-cursor-cost/core.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00816 | $0.00816 |
| Opus 5 | $0.00408 | $0.00408 |
| Sonnet 5 | $0.00163 | $0.00163 |
| Haiku 4.5 | $0.00082 | $0.00082 |
Grade B, and why
core scanned grade B with 1 finding 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.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
- Do not add disclaimers unless they affect correctness. How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Core Rules — Always Active
Minimize cost per accepted change, not tokens per response. Preserve correctness while removing padding, duplicated work, and unnecessary code.
1. Response Discipline
- Start with the answer or the code. No preamble.
- No affirmations: skip "Sure", "Great question", "Of course", "Certainly", "Absolutely".
- No sign-off: skip "Hope that helps", "Let me know if…", "Happy coding".
- Do not restate the user's question.
- Do not summarize what you just did after doing it.
- Do not add disclaimers unless they affect correctness.
- Banned filler: "it's worth noting", "as mentioned", "keep in mind", "importantly", "essentially", "basically", "simply".
2. Edit Format — Patch, Don't Reprint
- Default to patches: changed lines + 3–5 lines of context for location.
- Use
// ... existing code(or language-appropriate equivalent) to elide. - Show the FULL file only when one of these is true:
- It's a brand-new file
- The file is < 40 lines
- The user explicitly said "full file"
- Never reprint unchanged imports, unchanged class members, or unchanged tests.
3. Scope and Questions
- If a fact cannot be inferred or checked cheaply, ask exactly one highest-impact question.
- If work grows beyond the user's requested scope and would touch > 3 files or
150 lines, pause and ask where to start.
- If the user explicitly requested larger work, proceed in bounded phases.
- Never silently expand scope.
4. Silent Reuse-First Gate
Before tools or edits, check internally:
- Can the supplied context answer the request without another read?
- Before creating a helper, type, file, dependency, fixture, or abstraction, is there an existing equivalent to reuse? Search once if not already known.
- Can the requirement be met by extending the nearest existing pattern?
- What is the smallest safe edit and cheapest acceptance check?
- Is any missing fact truly blocking, or can it be inferred or checked cheaply?
Do not narrate this checklist. Prefer reuse and a small patch, but create new code when the requirement has no reasonable existing home.
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.
- 5d ago First seen · 86 lines · 816 tokens per session scan B 78190933b28a
core is a cursor rule published in the GitHub repository inboxpraveen/Minimize-Cursor-Cost (7 stars, last pushed 19d ago), licensed Apache-2.0. It adds 816 tokens to every session, about $0.0041 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other cursor rules, from other repositories
sample_cursor_rule
React component best practices.
performance
Frontend performance optimization rules. Apply when optimizing UI or bundle.
solana-transaction-safety
Safe Solana transaction submission patterns using Helius Sender.
data-fetching
Data fetching patterns with TanStack Query, Server Components, and Supabase.
verification-before-completion
Require fresh, scope-appropriate evidence before any completion claim. Distinguishes implemented, locally verified, repository-green, PR-green, deployed, and observed-stable states.
55-data-model-versioning
Dataset versioning, model checkpoint management, and training reproducibility rules.