rust-agent-friendly-cli

rust-agent-friendly-cli is a skill for Claude Code, Codex from heyAyushh/stacc. It costs 46 tokens per session (1,301 once invoked), scanned A, original, MIT.

A guide to designing Rust command-line programs that people, scripts, and coding agents can run without interactive questions.

In plain words
What is it for?
Use it when building or reviewing Rust command-line tools, including their flags, standard-input handling, JSON output, help text, and dry-run behavior.
Why use it?
It helps make command inputs, outputs, errors, and potentially destructive actions clear and predictable for automation.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex.

Good fit Use it when building or reviewing Rust command-line tools, including their flags, standard-input handling, JSON output, help text, and dry-run behavior.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/heyayushh/stacc/agent-friendly-cli
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.

Any agent
npx skills add heyAyushh/stacc --skill agent-friendly-cli
Clone the repo
git clone --depth 1 https://github.com/heyAyushh/stacc

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 rust-agent-friendly-cli

README.md
[![agentmods](https://agentmods.dev/badge/skills/heyayushh/stacc/agent-friendly-cli/github.svg)](https://agentmods.dev/skills/heyayushh/stacc/agent-friendly-cli)
Your own site
<a href="https://agentmods.dev/skills/heyayushh/stacc/agent-friendly-cli"><img src="https://agentmods.dev/badge/skills/heyayushh/stacc/agent-friendly-cli/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 rust-agent-friendly-cli

Your own site · 80×15
<a href="https://agentmods.dev/skills/heyayushh/stacc/agent-friendly-cli"><img src="https://agentmods.dev/badge/skills/heyayushh/stacc/agent-friendly-cli.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,301 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 $0.00046 $0.01301
Opus 5 $0.00023 $0.00651
Sonnet 5 $0.00009 $0.00260
Haiku 4.5 $0.00005 $0.00130

Measured 9d ago against content hash 21fc9b431063, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

rust-agent-friendly-cli 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 9d 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.

configs/stacks/rust/agent-friendly-cli/SKILL.md · 171 lines

How it starts

The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent-Friendly CLI

Layer 2: Interface Design

Core Question

Can another agent run this command correctly without an interactive back-and-forth?

Before adding or changing a CLI:

  • Are all required decisions available as flags or stdin?
  • Does --help show the exact working examples?
  • Do failures tell the caller how to retry?

Thinking Prompt

  1. What is the automation contract?

    • Inputs: path, stdin, config file, environment, or all of them
    • Outputs: human text, JSON, files, or exit status
    • Side effects: read-only, write, network, or destructive
  2. Can it run unattended?

    • No prompts on the default path
    • Every prompt has an explicit flag alternative
    • Destructive commands have --dry-run plus --yes or --force
  3. Can failures be fixed from the message?

    • Explain what was wrong
    • Name the expected input shape
    • Include one or two exact retry commands

CLI Contract Checklist

Area Requirement
Input Accept paths and stdin (--stdin or --input -) when useful
Identity Preserve virtual source names with flags like --stdin-path
Output Offer structured output such as --json for automation
Help Put real examples in top-level and subcommand help
Errors Return usage errors before doing work
Safety Require --dry-run and explicit confirmation for writes
Exit codes Keep stable meanings and document them

Rust Implementation Patterns

Need Rust Pattern
Command parsing clap::Parser or clap::CommandFactory
Example-rich help after_help / after_long_help constants
Usage validation Dedicated validation function before execution
Stdin support Read std::io::stdin() once at the command boundary
Structured output Serialize response types with serde
Actionable errors Small error type with Display examples
Testing assert_cmd, snapshot tests, or parser unit tests

Read the full file on GitHub · 171 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. 9d ago First seen · 171 lines · 46 tokens per session scan A 21fc9b431063

Subscribe to this mod's changes

rust-agent-friendly-cli is a skill published in the GitHub repository heyAyushh/stacc (3 stars, last pushed 2mo ago), licensed MIT. It adds 46 tokens to every session and 1,301 once invoked, about $0.0002 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 2026-09-03.