A set of rules for safer work with environments, Git, and file structure. Git is a tool for tracking code changes, and environments such as production are places where software runs.

Classifying the environment, applying stricter safeguards outside development, preserving references, and limiting Git and structural operations.

It prevents risky changes such as deploying, rewriting Git history, or moving files without explicit approval.

030-safety — Cursor rule for Cursor by Tholem-AI/Tholem-Cursor-Kit

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.

Clone the repo

git clone --depth 1 https://github.com/Tholem-AI/Tholem-Cursor-Kit

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.

README.md

[![agentmods](https://agentmods.dev/badge/rules/tholem-ai/tholem-cursor-kit/030-safety/github.svg)](https://agentmods.dev/rules/tholem-ai/tholem-cursor-kit/030-safety)

Your own site

<a href="https://agentmods.dev/rules/tholem-ai/tholem-cursor-kit/030-safety"><img src="https://agentmods.dev/badge/rules/tholem-ai/tholem-cursor-kit/030-safety/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/rules/tholem-ai/tholem-cursor-kit/030-safety"><img src="https://agentmods.dev/badge/rules/tholem-ai/tholem-cursor-kit/030-safety.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 285 This file is loaded in full into every session.

When invoked 285 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00285	$0.00285
Opus 5.5	$0.00114	$0.00114
Sonnet 5.5	$0.00057	$0.00057
Haiku 4.5	$0.00028	$0.00028

Measured 2mo ago against content hash 76c9a5707258, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

030-safety 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 2mo 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.

staging/.cursor/rules/030-safety.mdc · 40 lines

What it actually says

030-safety

Purpose

Provide non-destructive safety constraints for environment, git behavior, and file structure changes.

Mandatory policy

Do not modify production environment values or trigger deploy/environment switching without explicit user approval.
Detect environment context from explicit signals (for example user-declared environment, CI/deployment labels, branch conventions, or environment configuration values). When uncertain, assume DEV and surface warning context.
Apply stricter risk posture in STAGING/PROD than DEV/TEST.
Do not perform destructive or history-rewriting git operations unless explicitly requested by the user.
Do not commit, merge, rebase, reset, or push without explicit user approval.
Do not move or rename files/directories without explicit user approval.
Preserve import/reference integrity when proposing structural changes.

Safe default git operations

git status
git diff
git log
git show
read-only branch listing

Integration points

Governance authority: .cursor/rules/010-governance.mdc
Execution lifecycle: .cursor/rules/020-execution.mdc
Validation gates: .cursor/rules/040-quality.mdc

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.

2mo ago First seen · 40 lines · 285 tokens per session scan A 76c9a5707258

Subscribe to this mod's changes

030-safety is a cursor rule published in the GitHub repository Tholem-AI/Tholem-Cursor-Kit (4 stars, last pushed 5mo ago), licensed MIT. It adds 285 tokens to every session, about $0.0011 per session on Opus 5.5. 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.

Git and workflow Security

030-safety

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

030-safety

Purpose

Mandatory policy

Safe default git operations

Integration points

What this file has done since we first saw it

Other cursor rules, from other repositories

iris

rebase-only-merged-agents

git-workflow

release-checklist

branching-merging-strategy

ponytail