cleye

cleye is a skill for Claude Code, Codex from bendrucker/claude. It costs 53 tokens per session (780 once invoked), scanned A, original, MIT.

A type-safe argument parser for Bun scripts, which reads command-line flags, positional values, and subcommands with checked types.

In plain words
What is it for?
Use it when creating or editing Bun scripts that accept options, required or optional values, lists of values, or help flags.
Why use it?
It avoids hand-written argument handling and makes script inputs easier to describe and use consistently.

Skill for Claude CodeCodex

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 skills/bendrucker/claude/cleye
Any agent
npx skills add bendrucker/claude --skill cleye
Clone the repo
git clone --depth 1 https://github.com/bendrucker/claude

Made for: Claude Code, Codex.

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 cleye

README.md
[![agentmods](https://agentmods.dev/badge/skills/bendrucker/claude/cleye.svg)](https://agentmods.dev/skills/bendrucker/claude/cleye)
Your own site
<a href="https://agentmods.dev/skills/bendrucker/claude/cleye"><img src="https://agentmods.dev/badge/skills/bendrucker/claude/cleye.svg" alt="Measured on agentmods" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 780 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00053 $0.00780
Opus 5 $0.00026 $0.00390
Sonnet 5 $0.00011 $0.00156
Haiku 4.5 $0.00005 $0.00078

Measured 4d ago against content hash 8ea7b087fe65, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cleye 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 4d 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.

.claude/skills/cleye/SKILL.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

cleye

Type-safe CLI argument parsing for Bun scripts. Used across plugin scripts for flags, parameters, and subcommands.

Basic Usage

#!/usr/bin/env bun

import { cli } from "cleye";

const argv = cli({
  name: "my-script",
  parameters: ["<file>"],
  flags: {
    output: {
      type: String,
      alias: "o",
      description: "Output path",
    },
    verbose: Boolean,
  },
});

console.log(argv._.file);       // string (required)
console.log(argv.flags.output); // string | undefined
console.log(argv.flags.verbose); // boolean | undefined

Parameters

Positional arguments mapped to named properties on argv._:

parameters: [
  "<required>",     // must be provided
  "[optional]",     // may be omitted
  "<files...>",     // required variadic (1+), must be last
  "[files...]",     // optional variadic (0+), must be last
]

Required parameters must precede optional. Variadic must be last.

Access: argv._.required, argv._.optional, argv._.files.

Flags

Flags accept a type constructor or a config object:

flags: {
  name: String,                    // shorthand
  count: {
    type: Number,
    alias: "n",
    default: 10,
    description: "Max results",
  },
  tags: {
    type: [String],                // array: -t foo -t bar
    description: "Tag names",
  },
  json: {
    type: Boolean,
    description: "Output as JSON",
  },
}

Kebab-case flags (--dry-run) become camelCase properties (argv.flags.dryRun).

Help Text

Set help.description on cli() for a summary line above the generated usage block:

const argv = cli({
  name: "scan",
  parameters: ["<path>"],
  help: {
    description: "Scan repository prose for AI writing tropes.",
  },
  flags: { ... },
});

Subcommands

Define each subcommand as a named command() const with its callback, pass them via the commands array, and give the root cli() a callback that shows help when no subcommand matches:

import { cli, command } from "cleye";

const replyCmd = command(
  {
    name: "reply",
    parameters: ["<thread-id>"],
    flags: {
      body: { type: String, description: "Reply text" },
    },
  },
  async (parsed) => {
    console.log(parsed._.threadId, parsed.flags.body);
  },
);

cli(
  {
    name: "review-threads",
    commands: [replyCmd],
  },
  (parsed) => {
    parsed.showHelp();
  },
);

Read the full file on GitHub · 130 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. 4d ago First seen · 130 lines · 53 tokens per session scan A 8ea7b087fe65

Subscribe to this mod's changes

cleye is a skill published in the GitHub repository bendrucker/claude (16 stars, last pushed yesterday), licensed MIT. It adds 53 tokens to every session and 780 once invoked, about $0.0003 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.