316-zero-trust

316-zero-trust is a cursor rule for Cursor from d-padmanabhan/agent-engineering-handbook. It costs 5,072 tokens per session, scanned A, original, MIT.

Rules for applying Zero Trust security to identities, networks, data, workloads, and AI systems. Zero Trust means every request is checked instead of automatically trusting users, services, models, or tools because they are inside a network.

In plain words
What is it for?
Use it when designing or reviewing systems, MCP servers, autonomous agents, access controls, network boundaries, or data flows that need continuous verification.
Why use it?
It provides threat-model-driven guidance for deciding trust boundaries and reducing the damage caused by compromised accounts, services, agent tools, or untrusted data.

Cursor rule for Cursor

Written for Cursor: a Cursor rule (.mdc). Also seen: mentions subagents.

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/d-padmanabhan/agent-engineering-handbook/316-zero-trust
Clone the repo
git clone --depth 1 https://github.com/d-padmanabhan/agent-engineering-handbook

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 316-zero-trust

README.md
[![agentmods](https://agentmods.dev/badge/rules/d-padmanabhan/agent-engineering-handbook/316-zero-trust.svg)](https://agentmods.dev/rules/d-padmanabhan/agent-engineering-handbook/316-zero-trust)
Your own site
<a href="https://agentmods.dev/rules/d-padmanabhan/agent-engineering-handbook/316-zero-trust"><img src="https://agentmods.dev/badge/rules/d-padmanabhan/agent-engineering-handbook/316-zero-trust.svg" alt="Measured on agentmods" height="20"></a>
Per session 5,072 This file is loaded in full into every session.
When invoked 5,072 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 $0.05072 $0.05072
Opus 5 $0.02536 $0.02536
Sonnet 5 $0.01014 $0.01014
Haiku 4.5 $0.00507 $0.00507

Measured 6d ago against content hash 4345f5fa77f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

316-zero-trust 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 6d 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/316-zero-trust.mdc · 408 lines

How it starts

The opening of the file, as written. The whole thing — 408 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Distinguished Engineer - Zero Trust

Audience: engineers designing, reviewing, or operating any system that processes data, serves users, or runs autonomously (including AI agents and MCP servers).

Voice: this rule speaks as a Distinguished Engineer in design review. It is opinionated. It prefers principles over recipes, threat models over checklists, and reversibility over cleverness. It will tell you "no" and explain why.

[!IMPORTANT] This rule complements, it does not replace:

  • 310-security.mdc - OWASP and secure coding (the what)
  • 315-iam.mdc - identity protocols reference (the how for identity)
  • 412-aws-iam.mdc - AWS-specific IAM (the how for AWS)
  • 020-agent-audit.mdc - agent-local guardrails (the how for AI runs)

Use this rule when designing systems, reviewing architectures, scoping tools for agents, or arguing about trust boundaries.


Golden Rules (read first)

These are non-negotiable. Violations require an explicit, documented, time-boxed waiver with an owner.

  1. Never trust, always verify. Treat every request - from humans, services, models, tool outputs, and RAG content - as untrusted input until it passes explicit verification. Perimeter is not a control.
  2. Least privilege, per call, per session. Short-lived, scoped, purpose-bound credentials. No long-lived keys in code, config, env vars, or agent memory. No "admin for convenience".
  3. Assume breach. Segment aggressively. Log immutably. Rotate frequently. Contain blast radius before you need to. Every secret will leak; design so leaking one costs you little.
  4. Deterministic guardrails before LLM decisions. Anything consequential - money, data changes, deploys, messages, deletions - passes a deterministic policy check before the model gets a vote. LLMs advise; policy decides.
  5. Auditability for every trust decision. Every tool call, secret access, privilege escalation, and data egress is logged with who/what/when/why/result to an append-only store. If you cannot answer "who did this and why" in under 5 minutes, you do not have Zero Trust.

Read the full file on GitHub · 408 lines

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. 6d ago First seen · 408 lines · 5,072 tokens per session scan A 4345f5fa77f2

Subscribe to this mod's changes

316-zero-trust is a cursor rule published in the GitHub repository d-padmanabhan/agent-engineering-handbook (16 stars, last pushed 6d ago), licensed MIT. It adds 5,072 tokens to every session, about $0.0254 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.