cli-review-runner

Community

Audit CLIs for agent-friendliness fast.

Authorselfagency
Version1.0.0
Installs0

System Documentation

What problem does it solve?

It helps you quickly assess whether a command-line tool is safe and usable for automated agent workflows, by running black-box probes and reporting which interaction, help, error, and output rules pass or fail.

Core Features & Use Cases

  • Automated agent-friendliness audit: Runs a 10-probe suite that checks help layering, actionable errors, stderr routing, exit-code distinguishability, stdin/flags composition, structured output behavior, and command structure.
  • Rule-catalog mapped findings: Produces a structured NDJSON/JSON/text report that maps each finding to a specific cli-for-agents rule ID (e.g., help-examples-in-help, err-stderr-not-stdout).
  • Safety-first default probing: Uses safe verbs with read-only, timeout-bounded black-box executions, and inspects destructive verbs via --help unless explicitly enabled.

Quick Start

Ask the skill to review a CLI named mycli by running it in your environment and returning a text table report of per-rule pass or fail results.

Dependency Matrix

Required Modules

None required

Components

scriptsreferences

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: cli-review-runner
Download link: https://github.com/selfagency/agentsy/archive/main.zip#cli-review-runner

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.