cursor

An integration for Cursor, an AI-powered code editor, that adds ToolShield safety rules to Cursor's global user settings. It stores those rules in Cursor's internal SQLite database while preserving existing rules.

In plain words
What is it for?
It is for importing ToolShield settings for tools such as PostgreSQL, terminal, or filesystem access, and unloading those injected settings later.
Why use it?
It lets you add or remove ToolShield guidance without replacing the personal rules already configured in Cursor.

Agent

Part of the reins plugin — 1 skill, 5 agents, 2 hooks, 1 plugin shipped together

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 agents/pegasi-ai/reins/cursor
Clone the repo
git clone --depth 1 https://github.com/pegasi-ai/reins

Or install reins, the plugin that ships this one along with the rest of its 1 skill, 5 agents, 2 hooks, 1 plugin.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 346 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00000 $0.00346
Opus 5 $0.00000 $0.00173
Sonnet 5 $0.00000 $0.00069
Haiku 4.5 $0.00000 $0.00035

Measured 3d ago against content hash dffa527fde9f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursor 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 3d 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.

src/core/toolshield/docs/agents/cursor.md · 45 lines

What it actually says

ToolShield + Cursor

Cursor is an AI-powered code editor. ToolShield injects safety guidelines into Cursor's global user rules stored in its internal SQLite database.

How It Works

Cursor stores user rules in a SQLite database (state.vscdb) under the key aicontext.personalContext. ToolShield reads the existing rules, appends safety guidelines, and writes them back. Your existing rules are fully preserved.

Import

toolshield import \
  --exp-file postgres-mcp.json \
  --agent cursor

You can import multiple tools — each appends to the existing rules:

toolshield import --exp-file terminal-mcp.json --agent cursor
toolshield import --exp-file filesystem-mcp.json --agent cursor

Unload

toolshield unload --agent cursor

This removes all ToolShield-injected guidelines while preserving your existing user rules.

Database Location

Platform Path
macOS ~/Library/Application Support/Cursor/User/globalStorage/state.vscdb
Linux ~/.config/Cursor/User/globalStorage/state.vscdb
Windows %APPDATA%\Cursor\User\globalStorage\state.vscdb

Notes

  • ToolShield writes to the global user rules (not project-level .cursor/rules/), so guidelines apply across all projects.
  • Cursor must be restarted (or the rules reloaded) for changes to take effect.
  • If Cursor is installed in a non-default location, use --source_location to point to a plain text file instead.
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. 3d ago First seen · 45 lines · 0 tokens per session scan A dffa527fde9f

Subscribe to this mod's changes

cursor is an agent published in the GitHub repository pegasi-ai/reins (408 stars, last pushed 3mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 346 tokens. 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.