Software Development at Constructured
A new-hire's path through how Constructured actually ships software: the philosophy, the required tools (beads, timbers, just, the gates), the recommended ones (codex, worktrees, RTK), and the day-to-day workflow from spec to merge.
Start the trail →Parts
-
Part 1
How We Build Here
What's changed about writing production software, and what this trail is going to teach you
-
Part 2
The Workshop
A map of every tool between you and a shipped pull request, and where each one comes from
-
Part 3
Beads, the Backbone
The CLI issue tracker that gives an agent a memory that survives the next compaction
-
Part 4
Where the Work Lives
Coordinating between GitHub and beads, for the people doing the planning and the people doing the building
-
Part 5
Timbers, the Ledger
The second ledger every commit needs — one line of what, why, and how, searchable forever
-
Part 6
Claude Code as Daily Driver
The agent harness most of us reach for first, what we run inside it, and the alternatives that are perfectly fine
-
Part 7
Just: One Place to Discover
The discovery surface that turns project incantations into a known place humans and agents both look first
-
Part 8
Your Box and Your Trust Model
What runs on your machine, and how much rope you give the agent — one has a project answer, the other is yours
-
Part 9
Codex as Second Opinion
When a single model is bluffing or stuck, a second model is the cheapest unblock available
-
Part 10
Quiet Power Tools
RTK, tokf, and the small CLI multipliers that compound across every session
-
Part 11
Working in Parallel (Mostly)
Worktrees, the bd worktree warning, and the one Docker constraint we have not solved yet
-
Part 12
Quality Gates: The Contract That Lets You Move Fast
Lint, types, tests, coverage, audits — the deterministic constraints that make agent-driven work safe to ship
-
Part 13
From Plan to Pull Request: A Day on Strike
One realistic feature, end to end, with every prior cairn put to work