Skip to content
Automation
Skill

/generator-build-integrator

Internal Auto-Harness generator skill for worktree-merge build integration. Use only inside the parallel Generator integrator during build mode.

From plugin
auto-harness
1420 skills26 agents8 commands5 hooks
+1
Install
$ npx -y skills add redker56/auto-harness --skill generator-build-integrator --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/generator-build-integrator

Context preview

The summary Claude sees to decide when to auto-load this skill.

Internal Auto-Harness generator skill for worktree-merge build integration. Use only inside the parallel Generator integrator during build mode.

SKILL.md

generator-build-integrator.SKILL.md
name: generator-build-integrator
description: Internal Auto-Harness generator skill for worktree-merge build integration. Use only inside the parallel Generator integrator during build mode.
user-invocable: false

Generator Build Integrator

This skill governs Generator **build integration mode**.

At the start of this action, read these harness artifacts from the project:

  • `.harness-parallel/status.md`
  • `.harness-parallel/intake.md`
  • `.harness-parallel/spec.md`
  • `.harness-parallel/design-direction.md`
  • `.harness-parallel/contracts/sprint-XX-contract.md`
  • `.harness-parallel/contracts/sprint-XX-review.md` when it exists for the current sprint.
  • `.harness-parallel/runtime.md` when revising an existing runtime contract.
  • `.harness-parallel/qa/sprint-XX-self-check.md` when revising an existing self-check.

Then inspect the current project implementation relevant to this action:

  • Read the source files, routes, components, services, tests, and config needed to integrate the approved sprint scope.
  • Treat the main worktree as the integration surface and the worker branches named by the Orchestrator as merge inputs.

Then read these skill references:

  • `references/protocols/file-ownership.md`
  • `references/templates/runtime-template.md`
  • `references/templates/self-check.md`

Follow these rules:

  • Merge only the worker branches the Orchestrator names for the current pass.
  • If not all graph nodes are merged yet, perform merge work only and return structured merge results without writing `.harness-parallel/runtime.md` or the sprint self-check.
  • Once all graph nodes are merged, finish any tightly related seam cleanup needed to satisfy the approved sprint scope.
  • Treat the current sprint review, when present, as implementation guidance even if the verdict is already `APPROVED`.
  • Treat the contract dependency graph as the source of truth for ownership and merge ordering.
  • Update `.harness-parallel/runtime.md` so Evaluator can start and verify the app.
  • Make `runtime.md` sufficient for Evaluator to install, start, and health-check the app without follow-up questions.
  • Produce the current sprint self-check before handoff.
  • Do not quietly violate locked architecture or stack choices; surface unavoidable deviations explicitly in runtime notes and the self-check.
  • Do not modify orchestrator- or evaluator-owned artifacts.
Read more
Ships withauto-harness

Auto-Harness is a Claude Code plugin for longer software tasks that need planning, implementation, QA, fixes, retests, and a final report. Give it a product brief.

Get the whole plugin

Other skills on auto-harness.