safety

A safety rule for source-code changes in a Sitecore and Next.js project. It lists generated output, installed packages, secrets, deployment settings, lock files, and other files that should not be edited directly.

In plain words
What is it for?
Use it when modifying the project to identify safe source files and avoid editing folders such as .next, dist, node_modules, local environment files, and deployment configuration.
Why use it?
It helps prevent changes from being overwritten by builds or from exposing secrets and damaging deployment configuration. It keeps edits focused on files that are intended to be maintained by developers.

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/sitecore/xmcloud-starter-js/safety
Clone the repo
git clone --depth 1 https://github.com/Sitecore/xmcloud-starter-js

Made for: Cursor.

Per session 522 This file is loaded in full into every session.
When invoked 522 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 $0.00522 $0.00522
Opus 5 $0.00261 $0.00261
Sonnet 5 $0.00104 $0.00104
Haiku 4.5 $0.00052 $0.00052

Measured 2d ago against content hash c17d991770e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 2d 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.

.cursor/rules/safety.mdc · 59 lines

What it actually says

Safety Rules

Do Not Edit Compiled Artifacts

Never edit compiled or generated files:

  • Node modules: node_modules/ contains installed packages
  • Build outputs: .next/, dist/, out/, build/ are generated during build
  • Cache directories: .cache/, .sitecore/ (except component-map.ts)
  • Lock files: package-lock.json, yarn.lock, pnpm-lock.yaml
  • Source maps: *.js.map, *.css.map, *.d.ts.map

Do Not Edit Configuration Files

Avoid modifying sensitive configuration:

  • Sitecore configs: scjssconfig.json, .sitecore/user.json
  • Docker files: Dockerfile, docker-compose*.yml
  • CI/CD configs: .github/workflows/, deployment configurations

Do Not Edit Package Files

Never modify package artifacts:

  • Sitecore packages: *.itempackage, *.sicpackage
  • Archive files: *.tgz, *.tar.gz, *.zip
  • Binary files: *.exe, *.dll, *.obj

Do Not Edit Environment Files

Never commit or edit sensitive environment files:

  • Local environment: .env.local, .env.*.local
  • Secret files: *.deploysecret.config
  • User-specific configs: .sitecore/user.json

Source Files Only

Focus editing on:

  • Source code: .ts, .tsx, .js, .jsx files in src/
  • Configuration: next.config.js, tsconfig.json, package.json
  • Documentation: README.md, CONTRIBUTING.md
  • Styles: .css, .scss files
  • Component maps: .sitecore/component-map.ts

When in Doubt

If unsure whether to edit a file:

  1. Check if it's in node_modules/ - never edit
  2. Check if it's generated during build - never edit
  3. Check if it contains secrets - never edit
  4. Ask yourself: "Did I create this file?" - if no, be cautious

Referenced: @.gitignore @.cursorignore @examples/*/package.json

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. 2d ago First seen · 59 lines · 522 tokens per session scan A c17d991770e3

Subscribe to this mod's changes

safety is a cursor rule published in the GitHub repository Sitecore/xmcloud-starter-js (29 stars, last pushed 8d ago), licensed Apache-2.0. It adds 522 tokens to every session, about $0.0026 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.