cli-tools

cli-tools is a cursor rule for Cursor from bordenet/golden-agents. It costs 439 tokens per session, scanned A, original, MIT.

Development rules for command-line tools and shell scripts. They describe integration tests, which test a program through its real command interface, along with exit codes, output, errors, portability, and safe shell practices.

In plain words
What is it for?
Use them when building or reviewing terminal commands, shell scripts, error messages, progress output, and tests that run commands as a user would.
Why use it?
They help catch failures that ordinary function tests may miss, such as incorrect command output or error codes. They also reduce script failures caused by empty inputs, spaces in filenames, or differences between macOS and Linux.

Cursor rule for Cursor

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

Good fit Use them when building or reviewing terminal commands, shell scripts, error messages, progress output, and tests that run commands as a user would.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/rules/bordenet/golden-agents/cli-tools"><img src="https://agentmods.dev/badge/rules/bordenet/golden-agents/cli-tools.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 439 This file is loaded in full into every session.
When invoked 439 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00439 $0.00439
Opus 5.5 $0.00176 $0.00176
Sonnet 5.5 $0.00088 $0.00088
Haiku 4.5 $0.00044 $0.00044

Measured 5d ago against content hash 00051b65a347, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cli-tools 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/cli-tools.mdc · 97 lines

What it actually says

CLI Tools Conventions

Priority: HIGH - Apply to CLI/terminal tools
Source: codebase-reviewer, scripts AGENTS.md

CLI integration tests

CLI tools need integration tests that verify:

  • Command execution with various inputs
  • Exit codes (0 for success, non-zero for errors)
  • Output format correctness
  • Error message quality

Shell Script Standards

Self-Contained

Scripts should be:

  • Executable without external setup
  • Include all needed helpers inline
  • Document dependencies at top

Robust

Scripts should:

  • Use set -euo pipefail
  • Handle empty inputs gracefully
  • Quote all variables
  • Provide helpful error messages

macOS-Aware

Test on macOS and Linux:

  • BSD vs GNU tool differences
  • Path conventions
  • Available commands

Output Patterns

Progress Indicators

echo "Processing files..."
for file in "${files[@]}"; do
    echo "  - $file"
    process "$file"
done
echo "Done. Processed ${#files[@]} files."

Error Output

# Errors to stderr
echo "Error: File not found: $file" >&2
exit 1

Exit Codes

Code Meaning
0 Success
1 General error
2 Misuse/invalid args
126 Permission denied
127 Command not found

Help Text Pattern

usage() {
    cat << EOF
Usage: ${0##*/} [OPTIONS] <input>

Description of what the command does.

Options:
    -h, --help     Show this help message
    -v, --verbose  Enable verbose output
    -o, --output   Output directory (default: .)

Examples:
    ${0##*/} input.txt
    ${0##*/} -v -o ./out input.txt
EOF
}
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 · 97 lines · 439 tokens per session scan A 00051b65a347

Subscribe to this mod's changes

cli-tools is a cursor rule published in the GitHub repository bordenet/golden-agents (2 stars, last pushed 3d ago), licensed MIT. It adds 439 tokens to every session, about $0.0018 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 2026-11-12.

Related

cli-tools compared with cursor rules from other repositories

cli-tools next to 6 cursor rules from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
cli-toolsbordenet/golden-agentsCursor rule23d agoMITA439Cursor
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