cursorrules

A Claude Code settings file that controls allowed tools, blocked actions, approval prompts, and automatic hooks.

In plain words
What is it for?
Use it to allow reading, editing, writing, Git, Make, and selected npm commands; require approval for web requests, curl, and Docker; block secrets, unsafe deletion, sudo, and edits to Git metadata. It also formats JavaScript and TypeScript files after edits.
Why use it?
It limits what the coding agent can do and adds checks around shell commands and file changes.

Settings file for Claude Code

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 settings/usrrname/cursorrules/settings
Clone the repo
git clone --depth 1 https://github.com/usrrname/cursorrules

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan C 2 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade C, and why

cursorrules scanned grade C with 2 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

"Bash(rm -rf:/*)",

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

"Bash(curl:*)",
.claude/settings.json · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

{
  "$schema": "https://json.schemastore.org/claude-code-settings.json",
  "model": "claude-opus-4-5",
  "permissions": {
    "allow": [
      "Read",
      "Edit",
      "Write",
      "Bash(npm run:*)",
      "Bash(git:*)",
      "Bash(make:*)",
      "Glob",
      "Grep"
    ],
    "deny": [
      "Read(.env*)",
      "Read(secrets/**)",
      "Bash(rm -rf:/*)",
      "Bash(sudo:*)",
      "Edit(.git/**)"
    ],
    "ask": [
      "WebFetch",
      "Bash(curl:*)",
      "Bash(docker:*)"
    ],
    "defaultMode": "acceptEdits"
  },
  "env": {
    "NODE_ENV": "development"
  },
  "hooks": {
    "PostToolUse": [
      {
        "matcher": "Edit|Write",
        "hooks": [
          {
            "type": "command",
            "command": "bash -c 'FILE=$(jq -r \".tool_input.file_path\" <<< \"$(cat)\"); if [[ \"$FILE\" == *.ts || \"$FILE\" == *.tsx || \"$FILE\" == *.js || \"$FILE\" == *.jsx ]]; then npx prettier --write \"$FILE\" 2>/dev/null || true; fi'",
            "description": "Auto-format TypeScript/JavaScript files with Prettier"
          }
        ]
      }
    ],
    "PreToolUse": [
      {
        "matcher": "Bash",
        "hooks": [
          {
            "type": "command",
            "command": ".claude/hooks/security-block.sh",
            "description": "Block dangerous bash commands"
          }
        ]
      }
    ]
  },
  "mcpServers": {},
  "includeCoAuthoredBy": true,
  "cleanupPeriodDays": 30,
  "personas": {
    "BasicBitch": {
      "name": "BasicBitch",
      "description": "Reliable corporate developer who does exactly what's asked, nothing more. Adequate and dependable.",
      "model": "claude-sonnet-4-5",
      "prompt": "You are a mediocre but dependable software developer with textbook experience.\n\nCAPABILITIES:\n- Implement features with exact adherence to requirements\n- Apply design patterns adequately\n- Code review and technical documentation\n\nPERSONALITY:\n- Quiet, professional, and thorough\n- Writes maintainable code\n- O

Read the full file on GitHub · 92 lines

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 · 92 lines scan C 9a846d46c3b3

Subscribe to this mod's changes

cursorrules is a settings file published in the GitHub repository usrrname/cursorrules (10 stars, last pushed 4mo ago), licensed ISC. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.