Home

build-loop

A portable, multi-phase build loop for AI coding agents. It gives Claude Code, Codex, and any AGENTS.md-aware tool the same disciplined operating loop: assess, plan, execute, review, iterate, then learn.

build-loop helps AI coding agents — and the developers who run them — ship multi-step code changes by running every change through a planned, reviewed, verified loop. Best for non-trivial features, refactors, migrations, and bug hunts across more than one file. Skip it for one-line edits, pure Q&A, or status checks.

Current release: 0.36.0 · Apache-2.0 · hosts: Claude Code · Codex · AGENTS.md

Why build-loop

Hand an agent a multi-step task and it tends to dive straight into edits — no plan, no scope boundary, no independent check that the result matches the goal. The failures compound: wrong assumptions ride into code, fixes patch symptoms, and "it compiles" gets reported as "it works."

build-loop replaces that with a structured loop every change runs through. It assesses live repo state and memory, plans with explicit file ownership and pass/fail criteria, executes within scope, then runs an adversarial review (a critic, a fact-checker, a mock-data scanner) before iterating to green.

The differentiators:

• Portable — the same loop runs across Claude Code, Codex, and host-neutral AGENTS.md tools.
• Multi-model by tier — a frontier model plans and judges; a coding model executes.
• Verification-first — no completion claim ships without a verification step behind it.

The loop at a glance

Assess → Plan → Execute → Review → Iterate (5x max) → Learn
                            └─ Critic → Validate → Optimize → Fact-Check → Simplify → Auto-Resolve → Report

Review runs seven ordered sub-steps; Iterate loops back to Review on failure; Learn always emits an outcome.

Start here

• Installation — install for Claude Code, Codex, or all hosts.
• The Loop — what each phase does and what the agent owes you.
• Skills and Agents — the command, skill, and agent surface.
• Configuration — config keys, memory root, model tiering.
• FAQ — known issues and troubleshooting.

First run

npm install -g @tyroneross/build-loop@0.36.0
build-loop-install --host all

Then, inside a Claude Code session in your project:

/build-loop:run add billing settings with tests

You do not pick a mode. /build-loop:run auto-routes build, fix, refactor, optimize, research, and test requests to the right path. Completed, verified work is committed automatically; the only human-confirmation gates are production push, irreversible delete, and major user-impacting decisions.