Spec-driven development works when the specification is a workflow, not a document filed away after kickoff. The point is a sequence of reviewable artifacts — requirements, design, tasks, implementation, validation — each reducing ambiguity before anyone, human or agent, changes production code.

Three skill frameworks promise to make coding agents write better code: an autonomous pipeline, a full-lifecycle system with adversarial guards, and a requirements-first toolkit. Their repos differ in philosophy — and a measured same-feature bake-off puts numbers on the tradeoffs: 78 minutes and $34 against 148 minutes and $92.

The same Markdown file renders differently on GitHub, Hugo, Obsidian, and Pandoc — not because Markdown is unreliable, but because “Markdown” names a family of syntaxes, parsers, and platform features. CommonMark defines the portable core, GFM adds software-collaboration extensions, and Pandoc Markdown expands into a full document language.

Most coding agents keep getting bigger: planning modes, subagents, permission layers, IDE integrations, background workers. Pi walks the other way. Four default tools — read, write, edit, bash — with everything interesting left to extensions, skills, packages, and your own workflow. It is less a finished product than an editable harness, and that is exactly the point.

Claude Code isn’t autocomplete with better marketing — it’s a terminal-native junior engineer that needs review. This guide covers install, settings layering, self-hosted Ollama and llama.cpp backends, pricing rails, and troubleshooting.

Prompt injection gets the attention, but it stops being the whole problem once agents call tools and delegate work. Identity, authorization, delegation limits, and audit trails become first-class architecture — not optional hardening.

A spec nobody re-checks against the running system is worse than no spec: reviewers trust the document instead of the diff while the agent follows whatever the code actually does. Agents regenerate code fast, and each regeneration is a fresh chance for spec and implementation to diverge. The fix is a small enforceable link between requirement, design decision, tests, and the commits that changed them.

AI-generated code is cheap; judgment is scarce. When models write the code, nobody remembers why PostgreSQL beat DynamoDB, why AI emails must stay drafts, or why suggestions live in a side panel. Decision records — short, version-controlled documents capturing what was decided, why, and what was rejected — turn that judgment into durable project memory both humans and agents can read.

Developers comparing spec-driven setups in 2026 usually aren’t asking which model is smartest. They’re asking which workflow keeps an AI agent aligned without burying them in ceremony. Spec Kit, Kiro, and Claude Code custom workflows all implement specify-plan-tasks-implement-validate — but they bet differently on portability versus integration depth.

Spec-driven development entered 2026 as the serious developer’s answer to vibe coding drift: implement against a reviewed specification, not an ad-hoc prompt. Hacker News called it “Waterfall Strikes Back.” Both sides have a point — and the practical question was never which side wins, but how much spec a specific task needs.