Gin is a Go natural fit for infrastructure / iac. GreatCTO auto-detects both — adds the infra archetype overlay, wires infra-specific gates, and runs 83 specialist agents around your existing Gin workflow.
GreatCTO reads your go.mod and detects gin + infra archetype from signals: imports, file structure, env vars, README hints.
Attaches the infra archetype overlay: archetype-specific reviewer + compliance gates. Override if your specifics differ; the defaults are sensible for Gin-style projects.
qa-engineer runs go vet / staticcheck / go test -race -cover; security-officer reviews context cancellation + goroutine leaks; performance-engineer profiles pprof CPU + heap.
Bugs you've hit before in other Gin 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).
$ cd my-gin-app && npx great-cto init ✓ scanning manifests… found manifest ✓ stack: gin (Go) ✓ archetype: infra ✓ overlay: applied ✓ 83 agents ready $ /start "add infra feature" ▸ architect drafting ARCH-infra.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.
This is the shape of what senior-dev drafts for "infra feature" — auth first, schema validation, and the audit line the infra reviewer requires before gate:ship opens.
// internal/handlers/infra.go — drafted by senior-dev, reviewed by 5 agents
func CreateInfra(c *gin.Context) {
user := middleware.RequireUser(c) // security-officer: auth before handler
var req InfraRequest
if err := c.ShouldBindJSON(&req); err != nil { // qa-engineer: binding validation
c.JSON(400, gin.H{"error": err.Error()}); return
}
result, err := service.Handle(c, req, user)
audit.Log(c, user.ID, "infra feature", result.Confidence) // gate:infra: every decision logged
c.JSON(200, result)
}infra overlay.Terraform / Pulumi stacks with drift detection.
IAM policies reviewed for least privilege.
Helm / CDK deploys with rollback paths enforced.
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 →
$ npx great-cto init
Free, MIT, runs locally. Built as a Claude Code plugin — install with one command.
Eight stages, two human gates, four memory layers. Why this exact shape, and what I tried that didn't work.
One run, one feature, from prompt to merged PR. Time, cost, and gate-by-gate breakdown — no marketing math.
Regex vs LLM-based archetype detection, the false-positive count, and why I keep rejecting the obvious fix.
The bottleneck in agentic SDLC isn't model quality — it's process governance. Here's the state machine that closes the gap.