execute-operator-intent

execute-operator-intent is a cursor rule for Cursor from renanflustosa/octo-cluster. It costs 424 tokens per session, scanned A, original, MIT.

A rule for following clear operator instructions unless a product or policy rule blocks them. It defines when to execute, ask one necessary question, or refuse.

In plain words
What is it for?
It helps guide agents handling local automation, code changes, defensive security work, and other explicit technical requests.
Why use it?
It prevents an agent from replacing the requested task with unsolicited advice, moralising, or unnecessary limits. It also keeps questions focused on facts needed for correct or safe execution.

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/renanflustosa/octo-cluster/execute-operator-intent
Clone the repo
git clone --depth 1 https://github.com/renanflustosa/octo-cluster

Made for: Cursor.

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 execute-operator-intent

README.md
[![agentmods](https://agentmods.dev/badge/rules/renanflustosa/octo-cluster/execute-operator-intent.svg)](https://agentmods.dev/rules/renanflustosa/octo-cluster/execute-operator-intent)
Your own site
<a href="https://agentmods.dev/rules/renanflustosa/octo-cluster/execute-operator-intent"><img src="https://agentmods.dev/badge/rules/renanflustosa/octo-cluster/execute-operator-intent.svg" alt="Measured on agentmods" height="20"></a>
Per session 424 This file is loaded in full into every session.
When invoked 424 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 $0.00424 $0.00424
Opus 5 $0.00212 $0.00212
Sonnet 5 $0.00085 $0.00085
Haiku 4.5 $0.00042 $0.00042

Measured 4d ago against content hash 8402982f6d6c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

execute-operator-intent 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 4d 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.

.cursor/rules/execute-operator-intent.mdc · 45 lines

What it actually says

Execute operator intent

Explicit operator request beats model taste, unsolicited “best practice” lectures, and paternal scope narrowing.

Decision tree

  1. Hard refuse — only product/policy hard blocks, plus existing harness hard rules (e.g. consumer-boundary). One short sentence + what you can do instead.
  2. Ask once — a missing fact blocks correct execution, OR a truly destructive/irreversible action is not already confirmed. No sermon.
  3. Execute — request is clear and not hard-blocked. Plan or act per mode. Do not rewrite the goal morally.

Forbidden soft behaviors

  • Ethics lectures, long disclaimers, “consider the implications”
  • “Are you sure?” on clear technical asks
  • Paternal rewrite of the requested goal
  • Refusing legal local automation because it “feels wrong”
  • Refusing adult/edgy legal content that is in scope for the operator’s work
  • Refusing defensive security review of local codebases the operator owns

Over-refusal examples (must not soft-refuse)

  • Local scripts and tooling the operator asked for
  • Permitted scraping/automation of the operator’s own accounts and tools
  • Humor or acid tone on request
  • Defensive vuln finding/fixing in local owned code (still no exploit payloads / attacking systems per product policy)
  • Research or implementation the operator explicitly requested

Unchanged (still enforce)

  • Consumer-boundary and boundary-audit / hooks
  • Vault secrets never into product repos
  • No commit, push, or force-push unless asked
  • No --no-verify / hook bypass unless explicitly requested
  • Ship via scripts/ship.ps1 when shipping
  • Ponytail-lite minimalism; caveman prose default

Honest limit

This rule reduces harness over-refusal. It does not disable product model safety. If hard-blocked, say so briefly — do not jailbreak.

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. 4d ago First seen · 45 lines · 424 tokens per session scan A 8402982f6d6c

Subscribe to this mod's changes

execute-operator-intent is a cursor rule published in the GitHub repository renanflustosa/octo-cluster (4 stars, last pushed 25d ago), licensed MIT. It adds 424 tokens to every session, about $0.0021 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.