ai safety cursor rules

32 tagged ai safety, measured the same way as everything else here.

Browse within: ai-governance 12Guardrails 7Autonomous Agents 6ai-orchestration 6enterprise-ai 5gemini 5

changelog

01

OrlojHQ/orloj

Cursor rule Cursor

Update CHANGELOG.md for user-visible changes (Keep a Changelog).

117 4d ago A 196 tokens original Apache-2.0

crd-sync

02

OrlojHQ/orloj

Cursor rule Cursor

Regenerate CRD manifests when Go types that define CRD schemas change.

117 4d ago A 0 tokens original Apache-2.0

openapi-sync

03

OrlojHQ/orloj

Cursor rule Cursor

Keep OpenAPI in sync when the v1 API or CLI-exposed HTTP surface changes.

117 4d ago A 0 tokens original Apache-2.0

p8-enforcement

05

Aquifer-sea/pattern8

Cursor rule Cursor

P8 Enforcement Rules — Injected into every Agent conversation.

49 5mo ago C 513 tokens original MIT

feedback-capture

09

IgorGanapolsky/ThumbGate

Cursor rule

After any mistake or unexpected behavior, prompt to capture structured feedback with context, history-aware lesson distillation, and tags.

26 yesterday A 24 tokens original MIT

pre-action-gates

10

IgorGanapolsky/ThumbGate

Cursor rule

Before risky tool calls (git push, rm -rf, npm publish, deploy), check prevention rules via the thumbgate MCP server. If a rule matches, STOP and explain why.

26 yesterday C 236 tokens original MIT

cursorrules

12

ashlrai/phantom-secrets

Cursor rule Cursor

This project uses Phantom Secrets to protect API keys from AI leaks.

16 14d ago A 479 tokens original MIT

cursorrules

13

Sim-xia/Blind-Auditor

Cursor rule Cursor

A rule that requires generated code to pass through a review service before it is shown to the user.

11 8mo ago A 144 tokens original MIT

diplomat-reviewer

20

Diplomat-ai/diplomat-agent

Cursor rule Cursor

Reviews Python code for unguarded AI agent tool calls. Use when reviewing agent code, scanning for security issues, or checking tool call safety.

7 2mo ago A 0 tokens original Apache-2.0

cursorrules

21

DmiyDing/clarify-first

Cursor rule Cursor

When a request is ambiguous, high-impact, or potentially destructive, follow the "Risk Triage -> Align -> Act" protocol defined in skill.md.

6 5mo ago A 947 tokens original Apache-2.0

agentguard

22

bmdhodl/agent47

Cursor rule Cursor

AgentGuard local-first safety.

4 3d ago A 0 tokens original MIT

cursorrules

23

AUTHENSOR/AUTHENSOR

Cursor rule Cursor

When working with AI agents in this project, use Authensor for safety.

2 1mo ago A 237 tokens original MIT

cursorrules

24

SieveAI-dev/sieve

Cursor rule Cursor

README.md # 唯一放在根目录的文档(项目入口) .cursorrules # 本文件 docs/ ├── design/ # 设计文档(architecture.md / data-model.md) ├── api/ # API 文档(api-reference.md) ├── specs/ # 功能技术规格(SPEC-NNN-.md,含 SPEC-005 IPC 权威源) ├── guides/ # 使用指南(development.md / deployment.md) ├── changelog/ # 变更日志(CHANGELOG.md) ├── research/ # 调研材料.

2 1mo ago A 2,862 tokens original Apache-2.0