⌨️ laravel × cli-tool

Ship cli tool on Laravel with sensible defaults.

Laravel is a PHP workable choice for cli tool. GreatCTO auto-detects both — adds the cli-tool archetype overlay, wires cli-tool-specific gates, and runs 83 specialist agents around your existing Laravel workflow.

What changes when GreatCTO joins your Laravel project

Detection → overlay → gates → reviewers.

1 · DETECT

Stack + archetype

GreatCTO reads your composer.json and detects laravel + cli-tool archetype from signals: imports, file structure, env vars, README hints.

2 · OVERLAY

Archetype pack

Attaches the cli-tool archetype overlay: archetype-specific reviewer + compliance gates. Override if your specifics differ; the defaults are sensible for Laravel-style projects.

3 · GATES

Laravel-aware reviewers

qa-engineer runs phpstan / phpunit / psalm; security-officer checks SQL injection + Laravel CSRF; performance-engineer reviews query N+1 + Redis cache patterns.

4 · MEMORY

Cross-project lessons

Bugs you've hit before in other Laravel projects (connection-pool exhaustion, ORM N+1 queries, retry storms) — the agent's Step 0 includes the prior detection order. MTTR drops 94 % on second occurrence (methodology).

First 10 minutes

Concrete walkthrough.

$ cd my-laravel-app && npx great-cto init
✓ scanning manifests… found manifest
✓ stack: laravel (PHP)
✓ archetype: cli-tool
⚠ archetype + stack combo is unusual — review overlay manually
✓ 83 agents ready

$ /start "add cli-tool feature"
▸ architect drafting ARCH-cli-tool.md…
▸ pm decomposing into beads tasks…
⚐ gate:plan — your approval needed

Approve → 3 senior-devs run in parallel worktrees → 5 reviewers fan out in parallel → gate:ship → deploy. One real run walked stage-by-stage: /proof.

What ships

The first feature, Laravel-idiomatic.

This is the shape of what senior-dev drafts for "cli-tool feature" — auth first, schema validation, and the audit line the cli-tool reviewer requires before gate:ship opens.

// app/Http/Controllers/CliToolController.php — reviewed by 5 agents
class CliToolController extends Controller
{
    public function __construct() {
        $this->middleware('auth');             // security-officer: auth before handler
    }
    public function store(StoreCliToolRequest $request) {
        $result = $this->service->handle($request->validated(), $request->user());
        AuditLog::record($request->user()->id, 'cli-tool feature',
                         $result->confidence);  // gate:cli-tool: every decision logged
        return response()->json($result);
    }
}
Where this combo lands

What teams build with Laravel + the cli-tool overlay.

1

Developer CLIs with shell-injection-safe argv handling.

2

CI/CD utilities with --json output and clean exit codes.

3

Internal ops tooling with secret redaction in verbose logs.

⚠ Honest caveat

Laravel (PHP) is not a typical fit for cli tool. The archetype overlay still attaches, but you may want to override defaults more aggressively. Check the cli-tool archetype page for the typical stack list and decide if your case is the right tool / right archetype.

Architecture

Every step of the pipeline, transparent.

No black-box "AI does it all" loop. GreatCTO is a deterministic state machine — 8 stages, 22 nodes, 2 human gates. Every node maps to a real agent on GitHub. Inspect the state machine →

Install

Laravel + GreatCTO in one command.

$ npx great-cto init

Free, MIT, runs locally. Built as a Claude Code plugin — install with one command.

Related deep-dives

More from the blog

AI

How I designed the SDLC state machine for agentic coding

Eight stages, two human gates, four memory layers. Why this exact shape, and what I tried that didn't work.

AI

First real shipped feature with this stack — receipts

One run, one feature, from prompt to merged PR. Time, cost, and gate-by-gate breakdown — no marketing math.

AI

How GreatCTO chooses which compliance pack to attach

Regex vs LLM-based archetype detection, the false-positive count, and why I keep rejecting the obvious fix.

AI

Why your agent system fails: missing gates, not missing intelligence

The bottleneck in agentic SDLC isn't model quality — it's process governance. Here's the state machine that closes the gap.