paid-submit-safety

paid-submit-safety is a cursor rule for coding agents from Modellix/modellix-plugin. It costs 218 tokens per session, scanned A, original, MIT.

Safety rules for submitting paid jobs to the Modellix service. They explain how to check whether an unclear submission already succeeded before starting another one.

In plain words
What is it for?
Checking task history after uncertain submissions, downloading results promptly, handling trusted CDN network blocks, and reviewing confirmation prompts before repeating paid commands.
Why use it?
They help prevent duplicate paid jobs when a submission result is unknown. They also remind you to save downloads before their temporary links expire.

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/modellix/modellix-plugin/paid-submit-safety
Clone the repo
git clone --depth 1 https://github.com/Modellix/modellix-plugin

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 paid-submit-safety

README.md
[![agentmods](https://agentmods.dev/badge/rules/modellix/modellix-plugin/paid-submit-safety.svg)](https://agentmods.dev/rules/modellix/modellix-plugin/paid-submit-safety)
Your own site
<a href="https://agentmods.dev/rules/modellix/modellix-plugin/paid-submit-safety"><img src="https://agentmods.dev/badge/rules/modellix/modellix-plugin/paid-submit-safety.svg" alt="Measured on agentmods" height="20"></a>
Per session 218 This file is loaded in full into every session.
When invoked 218 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.00218 $0.00218
Opus 5 $0.00109 $0.00109
Sonnet 5 $0.00044 $0.00044
Haiku 4.5 $0.00022 $0.00022

Measured 3d ago against content hash 5961c3552f41, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

paid-submit-safety scanned grade A 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 3d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- If download fails because the CDN host resolves into a private/reserved range (e.g. proxy DNS `198.18.0.0/15`), retry with `--allow-private-network` for trusted Modellix CDN hosts, or curl the resource URL.
rules/paid-submit-safety.mdc · 12 lines

What it actually says

  • Paid modellix-cli model run / REST async POSTs must not be blindly retried when the outcome is unknown or ambiguous.
  • On unclear submit results, use modellix-cli task history (or equivalent task lookup) before creating a new paid task.
  • Persist downloads promptly (task download); resource URLs expire (~7 days).
  • If download fails because the CDN host resolves into a private/reserved range (e.g. proxy DNS 198.18.0.0/15), retry with --allow-private-network for trusted Modellix CDN hosts, or curl the resource URL.
  • Hosts that load this plugin's hooks will ask for confirmation on a repeated paid submit or an unbounded model batch; treat that prompt as a signal to check task history, not as a reason to rephrase the same command.
  • Details: skills/modellix/SKILL.md and references/cli-playbook.md.
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. 3d ago First seen · 12 lines · 218 tokens per session scan A 5961c3552f41

Subscribe to this mod's changes

paid-submit-safety is a cursor rule published in the GitHub repository Modellix/modellix-plugin (1 stars, last pushed 22d ago), licensed MIT. It adds 218 tokens to every session, about $0.0011 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.