OpenA2A CLI

The OpenA2A CLI is the unified entry point to the OpenA2A security toolchain. It is for developers and security teams who want one command to find credential leaks, shadow AI, unsigned configs, and ungoverned agents, then fix them. Run npx opena2a-cli review to assess a project, or opena2a protect to apply every auto-fixable finding. It delegates to HackMyAgent, Secretless, OASB, AIM, and the AI Trust registry through a single interface, across 24 commands and 5 input modes.

Installation

Which OpenA2A CLI do I want

There are four published CLIs in the toolchain. opena2a is the unified front door. Each underlying tool can also be installed and run standalone if that fits better.

If you are not sure where to start, run opena2a review in your project root. It tells you what is wrong and which underlying tool to invoke for the fix.

Built-in help

The CLI ships several discovery modes for finding the right command without leaving the terminal.

# bash
opena2a ?                              # recommendations for THIS project
opena2a ~shadow ai                     # semantic search ("ai" finds AI-related commands)
opena2a "find leaked credentials"      # natural language to matched command
opena2a                                # interactive guided wizard (no args)

Core Commands

Built-in commands with direct implementations.

Adapter Commands

Commands that delegate to external tools through the CLI's adapter system.

Global Flags

Guides

Command Categories

The 24 commands are organized into six functional categories that cover the full agent security lifecycle:

Quick Start

After installation, assess your project with the three-command workflow:

# 1. Assess project security posture and trust score
opena2a init

# 2. Auto-fix credential leaks, .gitignore gaps, and config signing
opena2a protect

# 3. Full multi-phase review with HTML report
opena2a review

For CI/CD pipelines, append --ci --format json to any command for machine-readable output and non-zero exit codes on failures. See the CI/CD Integration guide for full pipeline examples.

Post-incident review

Once opena2a identity integrate runs once, every event the OpenA2A toolchain captures auto-bridges into a single local audit log. No decorator in your agent code, no server. When something goes wrong, read back the unified log.

# bash
opena2a identity audit --limit 200
# 200 most recent events: credential injections, file accesses, config
# changes, scan findings, ARP runtime events. All in one timestamp-
# ordered JSON-lines view, sourced from Secretless, HackMyAgent,
# ConfigGuard, Shield, and ARP.

opena2a identity audit | jq 'select(.result == "denied")'
# just the denies

The audit log lives at ~/.opena2a/aim-core/audit.jsonl. Append-only, rotation at 50 MB, last 5 generations kept. Forward to Splunk or Sentinel via the standard tail-and-forward pattern.

Workspaces

This repo is a TypeScript turborepo. packages/cli is the binary, the rest are libraries it consumes.

# text
packages/
├── cli                  the opena2a binary
├── aim-core             local-first identity, audit log, policies
├── check-core           scanner orchestration
├── cli-ui               shared render primitives
├── credential-patterns
├── registry-client
├── ai-classifier
├── telemetry
├── contribute           skill scaffolding
└── shared               types + utilities

The CLI also depends on three sister packages published from their own repos: hackmyagent, secretless-ai, and ai-trust. opena2a scan delegates to hackmyagent, opena2a secrets delegates to secretless-ai, and opena2a trust queries via ai-trust.

Verify installation

$ opena2a --version
opena2a-cli v0.10.7

$ opena2a --help
Usage: opena2a <command> [options]

Commands:
  init, protect, guard, runtime, verify, shield,
  detect, mcp, trust, claim, demo, scan, secrets,
  benchmark, review, scan-soul, harden-soul, ...