shell

shell is a cursor rule for Cursor from bordenet/golden-agents. It costs 0 tokens per session (865 once invoked), scanned A, original, MIT.

Shell scripting rules for Bash, including safe variable handling, filename processing, input validation, error behavior, and ShellCheck review. ShellCheck is a tool that finds common shell-script mistakes.

In plain words
What is it for?
Use them when writing or reviewing Bash scripts, especially scripts that process files, run commands, validate inputs, or need to work on macOS and Linux.
Why use it?
They help avoid scripts that lose command results, break on spaces in filenames, accept invalid paths, or stop behaving predictably when errors occur.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/. Also seen: mentions AGENTS.md.

Good fit Use them when writing or reviewing Bash scripts, especially scripts that process files, run commands, validate inputs, or need to work on macOS and Linux.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/bordenet/golden-agents/shell
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/bordenet/golden-agents

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.

agentmods badge for shell

README.md
[![agentmods](https://agentmods.dev/badge/rules/bordenet/golden-agents/shell/github.svg)](https://agentmods.dev/rules/bordenet/golden-agents/shell)
Your own site
<a href="https://agentmods.dev/rules/bordenet/golden-agents/shell"><img src="https://agentmods.dev/badge/rules/bordenet/golden-agents/shell/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.

agentmods 80×15 button for shell

Your own site · 80×15
<a href="https://agentmods.dev/rules/bordenet/golden-agents/shell"><img src="https://agentmods.dev/badge/rules/bordenet/golden-agents/shell.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 865 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00865
Opus 5.5 $0.00000 $0.00346
Sonnet 5.5 $0.00000 $0.00173
Haiku 4.5 $0.00000 $0.00086

Measured 5d ago against content hash f10880b855ac, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

shell 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 5d 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/shell.mdc · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Shell Script Conventions

Priority: HIGH - Apply to all shell scripts
Source: scripts/AGENTS.md (extensive documentation)

Common Pitfalls to Avoid

SC2155 - Declare and assign separately

# ❌ Wrong - masks return value
local output=$(some_command)

# ✅ Correct - preserves return value
local output
output=$(some_command)

Filename Handling

# ❌ Wrong - breaks on spaces/special chars
for file in $(ls); do

# ✅ Correct - safe iteration
for file in *; do
    [[ -e "$file" ]] || continue

Input Sanitization

# ✅ Always quote variables
"$variable"

# ✅ Use [[ ]] for conditionals (safer than [ ])
if [[ -z "$var" ]]; then

# ✅ Validate inputs before use
[[ -f "$file" ]] || { echo "File not found"; exit 1; }

Script Template

#!/usr/bin/env bash
set -euo pipefail

# Description: [What this script does]
# Usage: script.sh [options] <args>

SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"

main() {
    # Implementation here
    :
}

main "$@"

Pre-Commit Checklist

  1. Run ShellCheck: shellcheck script.sh
  2. Test with set -euo pipefail
  3. Test with empty inputs
  4. Test with paths containing spaces
  5. Verify works on macOS (BSD tools vs GNU)
  6. Check variable exports for libraries

Platform Compatibility

macOS uses BSD tools, Linux uses GNU. Common differences:

Command macOS (BSD) Linux (GNU)
sed -i sed -i '' sed -i
grep -P Not available Available
date Different flags Different flags
# ✅ Portable sed in-place
if [[ "$(uname)" == "Darwin" ]]; then
    sed -i '' 's/old/new/' file
else
    sed -i 's/old/new/' file
fi

Commands

# Lint with ShellCheck
shellcheck -x script.sh

# Check syntax
bash -n script.sh

Failure Cases & Lessons Learned

Source: scripts/AGENTS.md - Document failures to prevent recurrence

Failure 1: Untested Export

Symptom: Script works standalone, fails when sourced Cause: Variables not exported for subshells Fix: Test both ./script.sh AND source script.sh

Read the full file on GitHub · 145 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. 5d ago First seen · 145 lines · 0 tokens per session scan A f10880b855ac

Subscribe to this mod's changes

shell is a cursor rule published in the GitHub repository bordenet/golden-agents (2 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 865 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 2026-11-12.

Related

shell compared with cursor rules from other repositories

shell next to 6 cursor rules from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
shellbordenet/golden-agentsCursor rule23d agoMITA0Cursor
ponytailDietrichGebert/ponytailCursor rule192k18d agoMITA604Cursor
angular-20angular/angularCursor rule101ktodayMITA0Cursor
dev-standardapache/supersetCursor rule76ktodayApache-2.0A1,147Cursor
prefer-assertions-over-defensive-checksprisma/ormCursor rule48ktodayApache-2.0A0Cursor
prefer-direct-imports-over-module-mocksprisma/ormCursor rule48ktodayApache-2.0A0Cursor
as-contract-cast-smellprisma/ormCursor rule48ktodayApache-2.0A943Cursor