mcpField
B
build-loop-claude-code

build-loop-claude-code

github.com/buildgreatproductsAgent workflows2331.7k installsUpdated 16w ago
Repository

About build-loop-claude-code

A Claude Code skill that builds features through a plan-driven loop of implementation, code review, and end-to-end testing. It is intended for development work where each task must pass verification before the next begins.

Key features

  1. 01Works from repository plans or prompts
  2. 02Implements tasks in order
  3. 03Runs `/review` and scoped security review
  4. 04Tests changes and user-facing flows
  5. 05Tracks progress and reports results

Use cases

  1. 01Implementing roadmap tasks sequentially
  2. 02Reviewing and testing a feature before marking it done
  3. 03Handling a request without an existing plan

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/buildgreatproducts/builder-os --skill build-loop-claude-code

After installing, type/build-loop-claude-codein Claude Code to confirm it loaded.

Details

From the project README

Claude Code Build Loop

Quality-gated feature work: nothing ships on "it compiles" — every increment is built, reviewed, tested end to end, and fixed before the user hears "done."

Source of work

  • A plan file exists (roadmap, refactor plan, or task list with - [ ] checkboxes — search the repo): work the first unchecked task. Tasks are ordered intentionally — never skip ahead. If the plan references spec docs, read only the sections relevant to the current task.
  • No plan (or the request is outside it): build from the user's prompt. Restate it as a verifiable goal with 2–4 success criteria and confirm scope in one message before building.

The loop

Run per task (or per prompted feature). Do not advance until every step passes.

  1. Build. Implement exactly what the task specifies. Simplest implementation that satisfies it, surgical changes, no speculative scope. Match existing project conventions.

  2. Review. Run /review on the changed code. If the change touches auth, payments, user input, or data access, also run /security-review. Fix all findings in scope — bugs, security issues, edge cases, performance, style in files you touched. If the project has a design system spec (design tokens file, DESIGN.md, theme config), check UI changes against it — no hardcoded colors, type, or spacing that bypass tokens. Note pre-existing issues in untouched code for the report instead of fixing silently. Re-run /review until clean. If a finding contradicts the task or spec, the spec wins — flag the disagreement.

  3. Test end to end. Run the task's verification step (or the success criteria). Run the full test suite — everything that passed before must still pass. Add tests for new logic. Then exercise the feature as a user would: run the app, walk the real flow including empty, loading, and error states.

  4. Fix. Anything testing finds goes back through the loop: fix → /review → re-test. Never mark a failing task complete; never start the next task with the app broken.

  5. Continue. Mark the task - [x], update any progress/status line in the plan, and loop to the next task until the requested scope is complete.

  6. Report. When done, tell the user: what was built and plan progress, review findings fixed and anything deferred, how it was verified (tests + flow walked), and what needs their attention next. Be honest about anything flaky or partially verified.

Rules

  • Skipped review or untested work = unfinished work.
  • Don't relitigate plan decisions; if a task seems wrong, ask one specific question rather than guessing.
  • Discovered work no task covers? Surface it and propose a task — never silently expand scope.

Comments

Markdown supported