A provider-agnostic scaffolding kit for running structured multi-agent workflows in your codebase.
This repository also configures its own agents. See what agent-harness-kit tells them →
Skill Claude Code
Ask a question about this codebase — where is X, does Y exist, how does Z work. Read-only. No tasks created, no harness tracking.
Skill Claude Code
Get technical advice or review on an approach, idea, or change. References available skills for best practices. No tasks created, no harness tracking.
Skill Claude Code
Preview a code review against ticket/objective alignment, with deep semantic (name-vs-behavior) analysis. No tasks created, no harness tracking.
Skill Claude Code
Triage a bug or unexpected behavior. Deep diagnostic analysis with structured report. No tasks created, no harness tracking.
Skill Claude Code
Design, write, and run behavior-focused tests for an objective or existing code. Writes test files only and reports evidence. No tasks created, no harness tracking.
Skill Claude CodeCodex
Turn an idea or Jira request into a reviewable, evidence-backed feature specification.
Skill Claude CodeCodex
Turn a reported defect or Jira issue into a reviewable, evidence-backed fix specification.
Skill Claude CodeCodex
Explain how to use and operate Agent Harness Kit= workflows, providers, MCP, health gates, and upgrades. Read-only; does not create harness state or change a project.
Skill Claude CodeCodex
Turn an approved spec, feature, or fix into a linked evidence-backed technical specification.
Skill Claude CodeCodex
Turn approved use cases or a product request into a linked functional specification.
Skill Claude CodeCodex
Define one user-centered use case through an iterative decision tree, then persist it as a reviewable draft.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: