Do not just prompt the coding agent.Run the whole SDLC.

You could, and it would sound right. Ask one about Codex approval modes and there is a good chance you get `--approval-mode`, which is not a flag — the real one is `--ask-for-approval`, and its values are `untrusted`, `on-request` and `never`. Copy the invented one and Codex rejects the command outright — you do not get a wrong permission posture, you get an agent that will not start. What you are paying for is that someone checked, against a named release, and wrote down the version they checked against. It matters more the higher you run: an agent you watch at Level 2 gets corrected in a minute; an agent left unattended for twelve hours on an invented flag is twelve hours of nothing, discovered in the morning. We keep a list of the ones models keep inventing.

The six stages are familiar. What changes is how work moves between them: agents create and consume committed artifacts, build and test can run in nonlinear loops, every handoff carries evidence, and production feedback becomes new intent. Humans still own goals, architecture, risk, acceptance and high-impact approvals. The point is not a renamed waterfall; it is an auditable control loop built for agent execution.

You own intent, architecture, acceptance criteria, risk, production approval and exception handling. Agents can research, propose, implement, test and prepare evidence, but accountability does not move to the model. The workflow makes those human decisions explicit instead of hiding them inside a chat.

That is the most common reason people cancel, so start with one real change. Use the Setup Pack to add repository context, write intent.md, spec.md and plan.md, then run the matching tool adapter. You get a working artifact chain before reading the catalog. If it still is not for you, the 30-day first-purchase refund window covers it.

Tool fluency is not the same as an end-to-end delivery system. Ask whether every request becomes committed intent, spec and plan; whether execution is isolated; whether a PR carries acceptance evidence; and whether incidents update the next plan. The toolkit fills those lifecycle gaps and shows the current implementation in each tool.

The levels are a maturity overlay, not the curriculum. The curriculum is the six-stage SDLC; the scorecard asks how safely your agents can operate across it. A higher result requires stronger context, isolation, verification, permissions and operational feedback — not merely more agent-written code.

Free tutorials usually teach one feature in one tool. This starts with a durable, tool-neutral lifecycle and adds verified adapters for Claude Code, Cursor and Codex. Volatile details such as commands, permissions and capabilities can be corrected as releases change, while the artifact and evidence model stays stable.

Do not read everything. Start one change with intent.md → spec.md → plan.md, run the relevant tool adapter and capture test evidence. Then use the scorecard to identify the weakest lifecycle stage and read only the guide that strengthens it.

Yes. One click in your account settings. No questions asked, no hoops to jump through. Your access continues until the end of your billing period.

Yes — 30 days from your first purchase, for any reason. Email support@developertoolkit.ai and we refund it; we won't argue with you about why. Applies to first-time purchases, as set out in the Terms.

You keep full access until the end of the period you've already paid for — the subscription simply doesn't renew. Your account stays in place, so you can pick up where you left off anytime. Any ebooks you've downloaded are yours to keep.

Yes. Payments are handled by Polar, our merchant of record, which issues an invoice for every charge with the applicable VAT or sales tax for your country. It lands in your inbox right after payment — ready to expense or pass to your accountant.

Unlimited seats for one flat price. Everyone with an email address on your company domain gets full access automatically, and teams spread across domains can add named addresses instead — no per-seat billing, no invites to manage. Need custom onboarding, white-label, or an on-premise option? That's the Enterprise tier.

Our 100+ recipes cover React, Next.js, Vue, Python, Node.js, Go, Rust, and more. And the core of the system — context engineering, rules, MCP, review workflows — doesn't care what language you write. The recipes just make it concrete in yours.