agents

A privacy rule requiring personally identifiable information, or PII such as information that can identify a person, to be handled by a local AI model.

In plain words
What is it for?
Use it when defining how agents handle personal data and private development materials. It guides whether local or cloud-based models may access them.
Why use it?
It limits exposure of private information to cloud services. Cloud-backed agents must not access private notes, secrets, private repositories, or unrestricted home directories in privacy-focused use cases.

Cursor rule for Cursor

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/onesimplecode/agent-engineering-standards/agents
Clone the repo
git clone --depth 1 https://github.com/onesimplecode/agent-engineering-standards

Made for: Cursor.

Per session 102 This file is loaded in full into every session.
When invoked 102 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 $0.00102 $0.00102
Opus 5 $0.00051 $0.00051
Sonnet 5 $0.00020 $0.00020
Haiku 4.5 $0.00010 $0.00010

Measured yesterday against content hash 2a6fab093ac8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agents 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 yesterday.

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.

examples/cursor-rules/.cursor/rules/agents.mdc · 13 lines

What it actually says

Agents

TR-SEC-003 — PII routed to local LLM only

For privacy-focused use cases, local LLMs must be used. Cloud-backed agents must not access private notes, secrets, private repos, or unrestricted home directories.

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. yesterday First seen · 13 lines · 102 tokens per session scan A 2a6fab093ac8

Subscribe to this mod's changes

agents is a cursor rule published in the GitHub repository onesimplecode/agent-engineering-standards (3 stars, last pushed 3d ago), licensed MIT. It adds 102 tokens to every session, about $0.0005 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.