write-operation-safety

write-operation-safety is a cursor rule for coding agents from zscaler/zscaler-mcp-server. It costs 153 tokens per session, scanned A, original, MIT.

Safety rules for operations that create, change, or delete data. Write actions need an explicit setting and allowlist, while deletions require a short-lived confirmation token.

In plain words
What is it for?
Controlling write permissions, confirming changes with the user, protecting delete operations, and preserving the order of ZPA access-control rules.
Why use it?
It reduces the risk of accidental changes or data loss when an agent uses administrative tools.

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/zscaler/zscaler-mcp-server/write-operation-safety
Clone the repo
git clone --depth 1 https://github.com/zscaler/zscaler-mcp-server

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 write-operation-safety

README.md
[![agentmods](https://agentmods.dev/badge/rules/zscaler/zscaler-mcp-server/write-operation-safety.svg)](https://agentmods.dev/rules/zscaler/zscaler-mcp-server/write-operation-safety)
Your own site
<a href="https://agentmods.dev/rules/zscaler/zscaler-mcp-server/write-operation-safety"><img src="https://agentmods.dev/badge/rules/zscaler/zscaler-mcp-server/write-operation-safety.svg" alt="Measured on agentmods" height="20"></a>
Per session 153 This file is loaded in full into every session.
When invoked 153 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 5.1 $0.00153 $0.00153
Opus 5 $0.00077 $0.00077
Sonnet 5 $0.00031 $0.00031
Haiku 4.5 $0.00015 $0.00015

Measured 5d ago against content hash 0bdeeb4b935f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

write-operation-safety 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 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.

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.

rules/write-operation-safety.mdc · 13 lines

What it actually says

Write operation safety

  1. Write tools are disabled by default. They must be enabled with --write-tools and an explicit allowlist.
  2. Always confirm with the user before executing create, update, or delete operations.
  3. Delete operations return an HMAC-SHA256 confirmation token that must be passed back to confirm execution within 5 minutes.
  4. ZDX is read-only — no create, update, or delete operations exist except zdx_start_deep_trace.
  5. ZPA policy rules are evaluated top-to-bottom. New rules append at the end — order matters for access control.
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. 5d ago First seen · 13 lines · 153 tokens per session scan A 0bdeeb4b935f

Subscribe to this mod's changes

write-operation-safety is a cursor rule published in the GitHub repository zscaler/zscaler-mcp-server (50 stars, last pushed 12d ago), licensed MIT. It adds 153 tokens to every session, about $0.0008 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 2026-08-30.