Internal Auto-Harness generator skill for approved sprint implementation. Use only inside the Generator subagent during build mode.
Scanned 5/27/2026
Install via CLI
openskills install redker56/auto-harness---
name: generator-build-sprint
description: Internal Auto-Harness generator skill for approved sprint implementation. Use only inside the Generator subagent during build mode.
user-invocable: false
---
# Generator Build Sprint
This skill governs Generator **build mode**.
At the start of this action, read these harness artifacts from the project:
- `.harness/status.md`
- `.harness/intake.md`
- `.harness/spec.md`
- `.harness/design-direction.md`
- `.harness/contracts/sprint-XX-contract.md`
- `.harness/contracts/sprint-XX-review.md` when it exists for the current sprint.
- `.harness/runtime.md` when revising an existing runtime contract.
- `.harness/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 implement the approved sprint scope.
- Use the existing codebase as the implementation surface, not only the harness artifacts.
Then read these skill references:
- `references/protocols/file-ownership.md`
- `references/templates/runtime-template.md`
- `references/templates/self-check.md`
Follow these rules:
- Implement only the approved sprint scope.
- Treat the current sprint review, when present, as implementation guidance even if the verdict is already `APPROVED`.
- Update `.harness/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.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.