Phoenix is a Elixir workable choice for devtools / sdk. GreatCTO auto-detects both — adds the devtools archetype overlay, wires devtools-specific gates, and runs 83 specialist agents around your existing Phoenix workflow.
GreatCTO reads your mix.exs and detects phoenix + devtools archetype from signals: imports, file structure, env vars, README hints.
Attaches the devtools archetype overlay: archetype-specific reviewer + compliance gates. Override if your specifics differ; the defaults are sensible for Phoenix-style projects.
qa-engineer runs mix test --cover / credo --strict; security-officer audits Ecto query injection + Phoenix CSRF; performance-engineer profiles BEAM scheduler + Ecto pool.
Bugs you've hit before in other Phoenix 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-phoenix-app && npx great-cto init ✓ scanning manifests… found manifest ✓ stack: phoenix (Elixir) ✓ archetype: devtools ⚠ archetype + stack combo is unusual — review overlay manually ✓ 83 agents ready $ /start "add devtools feature" ▸ architect drafting ARCH-devtools.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 "devtools feature" — auth first, schema validation, and the audit line the devtools reviewer requires before gate:ship opens.
# lib/app_web/controllers/devtools_controller.ex — reviewed by 5 agents
defmodule AppWeb.DevtoolsController do
use AppWeb, :controller
plug :require_authenticated_user # security-officer: auth before handler
def create(conn, params) do
with {:ok, attrs} <- validate(params), # qa-engineer: changeset enforced
{:ok, result} <- Devtools.handle(attrs, conn.assigns.current_user) do
AuditLog.record(conn.assigns.current_user.id, "devtools feature", result.confidence) # gate:devtools
json(conn, result)
end
end
enddevtools overlay.IDE extensions with telemetry-leak prevention.
Build tools with reproducible builds and SLSA provenance.
Dev SDKs with signed update channels.
Phoenix (Elixir) is not a typical fit for devtools / sdk. The archetype overlay still attaches, but you may want to override defaults more aggressively. Check the devtools archetype page for the typical stack list and decide if your case is the right tool / right archetype.
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.