zip-contents-protection.crux

zip-contents-protection.crux is a cursor rule for Cursor from zotoio/CRUX-Compress. It costs 495 tokens per session, scanned A, original, MIT.

A project rule that controls when files may be added to a CRUX release ZIP archive. It requires a user request before changing the archive and records approved changes in a manifest.

In plain words
What is it for?
Use it when preparing CRUX ZIP releases, adding files to a distribution archive, or changing the archive’s contents.
Why use it?
It prevents scripts, rules, or other files from being added to a release package by accident. It also makes archive changes traceable and warns that they may require a version increase.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/. Also seen: mentions AGENTS.md.

Good fit Use it when preparing CRUX ZIP releases, adding files to a distribution archive, or changing the archive’s contents.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/zotoio/crux-compress/zip-contents-protection.crux
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.

Clone the repo
git clone --depth 1 https://github.com/zotoio/CRUX-Compress

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 zip-contents-protection.crux

README.md
[![agentmods](https://agentmods.dev/badge/rules/zotoio/crux-compress/zip-contents-protection.crux/github.svg)](https://agentmods.dev/rules/zotoio/crux-compress/zip-contents-protection.crux)
Your own site
<a href="https://agentmods.dev/rules/zotoio/crux-compress/zip-contents-protection.crux"><img src="https://agentmods.dev/badge/rules/zotoio/crux-compress/zip-contents-protection.crux/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for zip-contents-protection.crux

Your own site · 80×15
<a href="https://agentmods.dev/rules/zotoio/crux-compress/zip-contents-protection.crux"><img src="https://agentmods.dev/badge/rules/zotoio/crux-compress/zip-contents-protection.crux.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 495 This file is loaded in full into every session.
When invoked 495 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00495 $0.00495
Opus 5 $0.00247 $0.00247
Sonnet 5 $0.00099 $0.00099
Haiku 4.5 $0.00049 $0.00049

Measured 12d ago against content hash 683807b94768, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

zip-contents-protection.crux 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 12d 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/zip-contents-protection.crux.mdc · 57 lines

What it actually says

[!IMPORTANT] Generated file - do not edit!

Zip Contents Protection Rule

⟦CRUX:zip-contents-protection.md
P.⊛{¬auto-Δ scripts/create-crux-zip.py w/o user req!}

Κ{script=scripts/create-crux-zip.py→dist;
 manifest=.crux/dist-manifest.json}

P.never{auto-add: .cursor/rules/*.mdc|.cursor/skills/*/|
 scripts/*.py|any files}

P.only{Δ zip: user says
 "add to dist zip"|"include in release"|"modify zip contents"}

Λ.add{w/ perm→1.Δ script +path;
 2.run script→manifest records path;
 3.Δ CONTRIBUTORS.md; 4.warn: +→ver bump}

M.zip{CRUX.md;install.crux.md;AGENTS.crux.md←AGENTS.md;
 .crux/[crux.json,crux-release-files.json];
 .cursor/[hooks.json,
  agents/crux/crux-cursor-[rule-manager,memory-manager,
   meditation-guide].md,
  commands/crux/crux-[compress,amnesia,dream,forget,
   meditate,recall,remember].md,
  hooks/crux-[detect-changes,detect-memory-changes,
   session-start].py,
  rules/crux/[_CRUX-RULE.mdc,
   crux-memories-integration.crux.mdc],
  skills/crux/[crux-utils/[SKILL.md,scripts/crux-utils.py],
   crux-skill-memory-[crud,compress,extract,index,
    rebalance,reference-tracker]/SKILL.md,
   crux-skill-memory-index/scripts/[memory-index.py,
    post-dream.py],
   crux-skill-memory-meditation-[research,quick,ensemble,
    review,report,coordination]/SKILL.md]]}

Ω{dist=minimal;+→[↑size,?conflicts,↑updates,↑maint]}
⟧
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. 12d ago First seen · 57 lines · 495 tokens per session scan A 683807b94768

Subscribe to this mod's changes

zip-contents-protection.crux is a cursor rule published in the GitHub repository zotoio/CRUX-Compress (8 stars, last pushed 5d ago), licensed MIT. It adds 495 tokens to every session, about $0.0025 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.