ratelimitting

A set of rules for reducing rate-limit problems, which happen when a service receives too many requests in a short time.

In plain words
What is it for?
Planning small batches of tool calls, combining independent operations, reusing existing information, and keeping responses concise.
Why use it?
It keeps responses and tool use focused, reducing unnecessary requests that could stop the session.

Cursor rule for Cursor

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/savedpixel/ai-agent-rules-generator/ratelimitting
Clone the repo
git clone --depth 1 https://github.com/savedpixel/ai-agent-rules-generator

Made for: Cursor.

Per session 352 This file is loaded in full into every session.
When invoked 352 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 $0.00352 $0.00352
Opus 5 $0.00176 $0.00176
Sonnet 5 $0.00070 $0.00070
Haiku 4.5 $0.00035 $0.00035

Measured 2d ago against content hash 4ed968fa6aa2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ratelimitting 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 2d 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.

examples/glitch-payment-gateway/v1.1/cursor/generated/.cursor/rules/ratelimitting.mdc · 39 lines

What it actually says

Rate Limit Prevention (CRITICAL)

You cannot recover from rate limits — the chat session will stop completely. Prevention is essential.

Rules

  • Be concise: Keep responses short and to the point.
  • Don't repeat back: Don't echo the user's request.
  • Plan first: Before major tool batches, decide the smallest sensible sequence.
  • Prefer fewer tool calls: Only calls that materially move the task forward.
  • Batch when it helps: Combine independent operations.
  • Reuse information: Never re-fetch data you already have.
  • Keep exploration focused: One targeted discovery pass when needed.
  • Checkpoint silently: After significant work, briefly note progress.
  • If uncertain: Make a reasonable decision and proceed.
  • Target small batches: ~3–5 tool calls per response.

Output Length Limits

  • Target ~300 lines per response: Split if exceeding.
  • Prefer incremental file work.
  • Truncate examples: Essential snippets only.
  • Use summaries: For large changes.
  • Continue automatically: End with ... continuing if splitting.

Visibility

  • 📦 BATCH: [what] — combining operations
  • ♻️ REUSE: [what] — reusing data
  • ⏭️ SKIP: [what] — skipping unnecessary call
  • 💾 CHECKPOINT: [summary] — saving progress
  • ✂️ SPLIT: [what] — splitting output
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. 2d ago First seen · 39 lines · 352 tokens per session scan A 4ed968fa6aa2

Subscribe to this mod's changes

ratelimitting is a cursor rule published in the GitHub repository savedpixel/ai-agent-rules-generator (7 stars, last pushed 4mo ago), licensed MIT. It adds 352 tokens to every session, about $0.0018 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.