mb-harness
CommunityDeterministic harness for safe agent runs
Authormrvladd-d
Version1.0.0
Installs0
System Documentation
What problem does it solve?
The mb-harness provides a deterministic, guardrailed environment to run autonomous agent tasks, ensuring repeatable results and auditable gates.
Core Features & Use Cases
- Defines entry points (AGENTS.md) and concrete quality gates
- Enables deterministic command execution with per-task worktrees
- Supports CI integration and memory-bank lint gating for safe operations
Quick Start
Boot the harness to bootstrap deterministic agent execution with guardrails and repeatable worktrees.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: mb-harness Download link: https://github.com/mrvladd-d/memobank/archive/main.zip#mb-harness Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.