harness-evolution

Generate approval-gated change proposals for workflow and harness maintenance.

2|Updated May 3, 2026
One-click install
npx skills add https://github.com/Rosetears520/aili-workflows --skill harness-evolution
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: harness-evolution
Source: https://github.com/Rosetears520/aili-workflows/tree/main/skills/harness-evolution
Command: npx skills add https://github.com/Rosetears520/aili-workflows --skill harness-evolution

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

It prevents workflow and harness changes from becoming uncontrolled by converting harness-related issues into approval-gated, verification-backed proposals rather than ad-hoc edits.

Core Features & Use Cases

  • Report-first harness proposals: Classifies the signal and produces a structured change report using the provided template when harness maintenance is needed.
  • Approval-gated core edits: Ensures core harness modifications (routing, rules, command/skill contracts, memory policy, install/setup scripts, and harness docs) are applied only with explicit human approval.
  • Verification and rollback planning: Requires a named verification trigger and a rollback plan for every proposed or applied change, recording verdict and evidence pointers after execution.

Quick Start

Ask the AI to generate an approval-gated harness change proposal after you identify repeated harness failures, using the existing harness-issue-triage evidence if available.

Frequently Asked Questions about harness-evolution

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I plan harness maintenance changes without uncontrolled workflow drift?

Harness maintenance changes require report-first proposals that enforce approval-gated core edits and mandate rollback planning to prevent uncontrolled workflow drift.

What is an approval-gated harness change proposal?

An approval-gated harness change proposal is a structured change report that ensures explicit human approval is recorded before modifying core harness routing, rules, or memory policies.

How do I create a verification and rollback plan for workflow drift?

Generate a structured change report specifying a named verification trigger and a rollback plan, then record the execution verdict and evidence pointers to address workflow drift.

Does this approach work for subagent dispatch boundary failures?

Yes, subagent dispatch boundary failures are addressed by producing structured change reports that require approval-gated edits, verification triggers, and rollback planning before applying fixes.

How do I fix command lifecycle bypass issues in my harness?

Command lifecycle bypass issues are fixed by classifying the signal and generating an approval-gated change report that mandates verification triggers and rollback planning before applying edits.

When should I not use ad-hoc edits for harness documentation inconsistencies?

Ad-hoc edits should be avoided for harness documentation inconsistencies because uncontrolled changes require approval-gated, verification-backed proposals to ensure evidence gaps are properly recorded.