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/d-padmanabhan/agent-engineering-handbook/316-zero-trustgit clone --depth 1 https://github.com/d-padmanabhan/agent-engineering-handbookWrote 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/d-padmanabhan/agent-engineering-handbook/316-zero-trust)<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>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 | $0.05072 | $0.05072 |
| Opus 5 | $0.02536 | $0.02536 |
| Sonnet 5 | $0.01014 | $0.01014 |
| Haiku 4.5 | $0.00507 | $0.00507 |
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.
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.
- 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.
- 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".
- 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.
- 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.
- Auditability for every trust decision. Every tool call, secret access, privilege escalation, and data egress is logged with
who/what/when/why/resultto an append-only store. If you cannot answer "who did this and why" in under 5 minutes, you do not have Zero Trust.
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.
- 6d ago First seen · 408 lines · 5,072 tokens per session scan A 4345f5fa77f2
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.
Other cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.