GreatCTO reads your Cargo.toml and detects actix + iot-embedded archetype from signals: imports, file structure, env vars, README hints.
Attaches the iot-embedded archetype overlay: OTA strategy, secure boot, ETSI EN 303 645 baseline, watchdog patterns. Override if your specifics differ; the defaults are sensible for Actix-style projects.
qa-engineer runs cargo clippy / cargo test / cargo-tarpaulin; security-officer audits unsafe blocks + dependency tree; performance-engineer reviews allocator patterns.
Bugs you've hit before in other Actix 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-actix-app && npx great-cto init ✓ scanning manifests… found manifest ✓ stack: actix (Rust) ✓ archetype: iot-embedded ✓ overlay: applied ✓ 83 agents ready $ /start "add OTA update endpoint" ▸ architect drafting ARCH-iot-embedded.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 "OTA update endpoint" — auth first, schema validation, and the audit line the iot-embedded reviewer requires before gate:ship opens.
// src/handlers/iot_embedded.rs — drafted by senior-dev, reviewed by 5 agents
#[post("/iot-embedded")]
async fn create(
user: AuthenticatedUser, // security-officer: extractor rejects anon
payload: web::Json<IotEmbeddedRequest>, // qa-engineer: serde validation
audit: web::Data<AuditLog>,
) -> Result<impl Responder> {
let result = handle(payload.into_inner(), &user).await?;
audit.record(user.id, "OTA update endpoint", result.confidence).await?; // gate:iot-embedded
Ok(web::Json(result))
}iot-embedded overlay.Device firmware with secure boot and OTA strategy.
Sensor fleets under ETSI EN 303 645.
RTOS apps (Zephyr / ESP-IDF / embassy) with watchdog patterns.
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.