Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/eddiebelaval/squirenpx agentmods add skills/eddiebelaval/squire/cli-builderWrote 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.
[](https://agentmods.dev/skills/eddiebelaval/squire/cli-builder)<a href="https://agentmods.dev/skills/eddiebelaval/squire/cli-builder"><img src="https://agentmods.dev/badge/skills/eddiebelaval/squire/cli-builder/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.
<a href="https://agentmods.dev/skills/eddiebelaval/squire/cli-builder"><img src="https://agentmods.dev/badge/skills/eddiebelaval/squire/cli-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Rogue Agent · line 111 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- high Rogue Agent · line 495 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- medium Excessive Agency · line 357 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 777 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00047 | $0.05043 |
| Opus 5.5 | $0.00019 | $0.02017 |
| Sonnet 5.5 | $0.00009 | $0.01009 |
| Haiku 4.5 | $0.00005 | $0.00504 |
Grade A, and why
cli-builder 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 865 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLI Builder Skill
Core Workflows
Workflow 1: Primary Action
- Analyze the input and context
- Validate prerequisites are met
- Execute the core operation
- Verify the output meets expectations
- Report results
Overview
This skill helps you build professional command-line interfaces with excellent user experience. Covers argument parsing, interactive prompts, progress indicators, colored output, and cross-platform compatibility.
CLI Design Philosophy
Principles of Good CLI Design
- Predictable: Follow conventions users expect
- Helpful: Provide clear help text and error messages
- Composable: Work well with pipes and other tools
- Forgiving: Accept common variations in input
Design Guidelines
- DO: Use conventional flag names (
-v,--verbose,-h,--help) - DO: Provide meaningful exit codes
- DO: Support
--versionand--helpon all commands - DO: Use colors meaningfully (errors=red, success=green)
- DON'T: Require interactive input when running in pipes
- DON'T: Print to stdout when outputting errors
- DON'T: Ignore signals (Ctrl+C should exit cleanly)
Node.js CLI Development
Project Setup
# Initialize CLI project
mkdir my-cli && cd my-cli
npm init -y
# Install core dependencies
npm install commander chalk ora inquirer
# Optional: TypeScript support
npm install -D typescript @types/node @types/inquirer ts-node
Package.json Configuration
{
"name": "my-cli",
"version": "1.0.0",
"description": "A powerful CLI tool",
"bin": {
"mycli": "./bin/cli.js"
},
"files": [
"bin",
"dist"
],
"scripts": {
"build": "tsc",
"dev": "ts-node src/cli.ts",
"link": "npm link"
},
"engines": {
"node": ">=18.0.0"
}
}
Commander.js - Command Structure
// src/cli.ts
import { Command } from 'commander';
import { version } from '../package.json';
const program = new Command();
program
.name('mycli')
.description('A powerful CLI for doing awesome things')
.version(version, '-v, --version', 'Display version number');
// Simple command
program
.command('init')
.description('Initialize a new project')
.argument('[name]', 'Project name', 'my-project')
.option('-t, --template <type>', 'Template to use', 'default')
.option('--no-git', 'Skip git initialization')
.option('-f, --force', 'Overwrite existing files')
.action(async (name, options) => {
console.log(`Creating project: ${name}`);
console.log(`Template: ${options.template}`);
console.log(`Git: ${options.git}`);
});
// Command with subcommands
const config = program
.command('config')
.description('Manage configuration');
config
.command('get <key>')
.description('Get a configuration value')
.action((key) => {
console.log(`Getting config: ${key}`);
});
config
.command('set <key> <value>')
.description('Set a configuration value')
.action((key, value) => {
console.log(`Setting ${key} = ${value}`);
});
config
.command('list')
.description('List all configuration')
.option('--json', 'Output as JSON')
.action((options) => {
if (options.json) {
console.log(JSON.stringify({ key: 'value' }, null, 2));
} else {
console.log('key = value');
}
});
// Parse arguments
program.parse();
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.
- 1mo ago First seen · 865 lines · 47 tokens per session scan A 984a05da3901
cli-builder is a skill published in the GitHub repository eddiebelaval/squire (21 stars, last pushed 2mo ago), licensed MIT. It adds 47 tokens to every session and 5,043 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
langgraph-docs
Fetches and references LangGraph Python documentation to build stateful agents, create multi-agent workflows, and implement human-in-the-loop patterns. Use when the user asks about LangGraph, graph agents, state machines, agent orchestration, LangGraph API, or needs LangGraph implementation guidance.
stripe-projects
Use after E2B sandbox/API access has been provisioned through Stripe Projects and the user needs to use the resulting E2B API key with the E2B CLI, JavaScript SDK, Python SDK, or Code Interpreter SDK.
python-backend
Production Python async patterns including asyncio TaskGroup, FastAPI dependency injection and middleware, SQLAlchemy 2.0 async sessions, and database connection pool tuning. Python 3.11+ runtime concerns such as ExceptionGroup, cancellation semantics, and session rollback. Use when building async services, wiring…
calle-developer
Build or debug application integrations with the CALL-E Developer API and TypeScript or Python SDKs, including call payloads, structured results, recovery and webhooks. Use for application code, not for operating calls through the calle CLI.
NestJS Framework
Node.js/TypeScript backend framework with dependency injection and modular architecture.
developing-with-python
Python 3.11+ development with type hints, async patterns, FastAPI, and pytest. Use for backend services, CLI tools, data processing, and API development.