Django is a Python workable choice for library / sdk. GreatCTO auto-detects both — adds the library archetype overlay, wires library-specific gates, and runs 83 specialist agents around your existing Django workflow.
GreatCTO reads your pyproject.toml / requirements.txt and detects django + library archetype from signals: imports, file structure, env vars, README hints.
Attaches the library archetype overlay: archetype-specific reviewer + compliance gates. Override if your specifics differ; the defaults are sensible for Django-style projects.
qa-engineer runs mypy / ruff / pytest --cov; security-officer scans for SQL injection patterns common in ORMs (SQLAlchemy, Django ORM); performance-engineer profiles async patterns for I/O contention.
Bugs you've hit before in other Django 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-django-app && npx great-cto init ✓ scanning manifests… found pyproject.toml ✓ stack: django (Python) ✓ archetype: library ⚠ archetype + stack combo is unusual — review overlay manually ✓ 83 agents ready $ /start "add library feature" ▸ architect drafting ARCH-library.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 "library feature" — auth first, schema validation, and the audit line the library reviewer requires before gate:ship opens.
# library/views.py — drafted by senior-dev, reviewed by 5 agents
from django.contrib.auth.decorators import login_required
from .audit import audit_log # gate:library: every decision logged
@login_required # security-officer: auth before handler
def create(request):
form = LibraryForm(request.POST) # qa-engineer: form validation enforced
if form.is_valid():
result = handle(form.cleaned_data, request.user)
audit_log(who=request.user.pk, what="library feature", confidence=result.confidence)
return JsonResponse(result.as_dict())library overlay.Open-source SDKs with semver discipline and API diffing.
Internal shared libraries with backward-compat matrices.
Client libraries with supply-chain hardening (Sigstore).
Django (Python) is not a typical fit for library / sdk. The archetype overlay still attaches, but you may want to override defaults more aggressively. Check the library 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.