cli-agent-audit

Official

Autonomously audit AI-ready CLI behavior end-to-end

Authorcli-agent-spec
Version1.0.0
Installs0

System Documentation

What problem does it solve?

CLI tools often fail in ways that AI agents can’t reliably detect—leading to hangs, silent errors, data corruption, and wasted context—so agent pipelines become fragile and hard to debug.

Core Features & Use Cases

  • Run a full autonomous audit pipeline that installs (if needed), profiles, evaluates critical failure modes, and produces a complete report bundle in one go.
  • Generate machine-usable evaluation artifacts including environment, readiness, findings/issues, raw traces, and multiple report formats intended for both developers and agent builders.
  • Use a scoped evaluation strategy (critical only by default) with resumable/incremental evaluation to reduce wasted time and repeat work.

Quick Start

Ask the assistant to run the CLI Agent Audit for your tool (for example, pip:my-cli==2.1.0) so it produces the full evaluations/<cli>/ report bundle.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 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-agent-audit
Download link: https://github.com/cli-agent-spec/cli-agent-spec/archive/main.zip#cli-agent-audit

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.