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.
npx agentmods add rules/zscaler/zscaler-mcp-server/write-operation-safetygit clone --depth 1 https://github.com/zscaler/zscaler-mcp-serverWrote 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.
[](https://agentmods.dev/rules/zscaler/zscaler-mcp-server/write-operation-safety)<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>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.
| Model | Per session | Once 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 |
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.
What it actually says
Write operation safety
- Write tools are disabled by default. They must be enabled with
--write-toolsand an explicit allowlist. - Always confirm with the user before executing create, update, or delete operations.
- Delete operations return an HMAC-SHA256 confirmation token that must be passed back to confirm execution within 5 minutes.
- ZDX is read-only — no create, update, or delete operations exist except
zdx_start_deep_trace. - ZPA policy rules are evaluated top-to-bottom. New rules append at the end — order matters for access control.
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.
- 5d ago First seen · 13 lines · 153 tokens per session scan A 0bdeeb4b935f
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.
Other cursor rules, from other repositories
about-codebase
General information about the Lineai MCP Server codebase and its purpose.
toc-readme
When updating README.md, the table of contents should contain only the second-level headings below it.
cursorrules
Robot control server. Do not move the physical robot without checking health first.
runwhen-infrastructure
Infrastructure conventions for scripts targeting Kubernetes and databases via RunWhen runners.
cursorrules
When the user asks about social media, use social-media-ai-mcp tools: schedulepost, generatehashtags, analyzeengagement, plancontentcalendar, getaudienceinsights.
validate-design-early
Ask for design approval before implementing 100+ lines.