DevArch is a set of directives, agents, and skills for Claude Code that enforce engineering discipline at every step. Session continuity, quality gates, behavioral testing, architecture decision records, and domain-driven design — all automatic. One developer. 500% productivity increase. The code to prove it.
Don't take our word for it. Look at the repos.
Sharpee is a full interactive fiction engine — TypeScript, multiple packages, Tauri desktop app, web deployment, behavioral test suite — built by one developer in six months with DevArch managing every session. Mainframe Zork, a large classic game, was ported to the engine in under two months. The code is public. Read it.
DevArch hooks into Claude Code's lifecycle. Every session follows this discipline automatically.
Every hook fires automatically. The developer never invokes them. Session context is preserved across conversations — start a new session tomorrow and the audit agent tells you exactly where you left off.
Sessions are the inner loop. Skills, artifacts, and decision records connect them into a coherent project.
Brainstorm before you build. Review the architecture periodically. Every session produces a summary. Every significant decision becomes an ADR. Nothing is lost between sessions.
Directives, agents, and skills that enforce engineering discipline automatically.
Session start hooks restore context. Work summaries capture state. Pre-session audits surface blockers. You never lose track of where you are.
Invariants and variants identified before writing code. Cohesive modularity enforced. Clear boundaries between domain logic and infrastructure. Not suggestions — rules.
Before editing files that own cross-boundary state — stores, reducers, projections, domain modules — the agent declares OWNER, SHARED?, PROMISE, and ALTERNATIVES. Per-consumer state can't quietly migrate into a shared module without an explicit conversation.
Every side-effect function gets a structured statement — DOES, WHEN, BECAUSE, REJECTS WHEN — before any test is written. If you can't state what the code does, it's not ready.
Tests derived from behavior statements are graded RED/YELLOW/GREEN. Tautological assertions, mock-only checks, and return-value-only tests are caught and rejected.
An agent runs after every side-effect function to verify tests assert on actual state changes — not just return values, not just "didn't throw."
Phases named after an integration must have a test that drives the real subprocess, runtime, or migration. A stub of an owned dependency can't be the acceptance gate for the integration with that dependency. "Carve-out" is never a valid modifier of "complete."
When a decision constrains future sessions, the agent asks "ADR-worthy?" Approved decisions are promoted to permanent record with context, rationale, and consequences.
Non-trivial goals are decomposed into phases before implementation starts. Budget tracking warns at 70%, 90%, and 100% of tool-call budget per phase.
Activate when complexity demands it. Bounded contexts, domain events, aggregates, value objects, ubiquitous language — captured through conversation, not ceremony.
Every hook ships in both Bash and PowerShell with verified functional parity. Windows users get the same discipline as macOS/Linux — no WSL required.
One product, everything included. Start with a free trial.
Everything included. No credit card. Use the form below to start.
Full repo access — all agents, hooks, skills, methodology docs, and templates. One seat.
Everything in Solo for your whole team. Ten seats, one license.
Unlimited seats. Same repo, same tooling — no per-developer math.
14 days, full access, no credit card. Tell us about your project.