jarvis-core

Community

10-stage governed orchestration for safe execution

Authorkmshihab7878
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Coordinate complex, multi-step objectives across agents while enforcing governance, safety, and accountability so that cross-system work proceeds without unauthorized side effects or policy violations.

Core Features & Use Cases

  • Ten-stage governed pipeline: Input sanitization, intent parsing, dual policy gates, DAG planning, delegation, governed execution, reflection, outcome tracking, and world-state updates.
  • Policy-first execution: Per-intent and per-step policy gates (ALLOW / REVIEW / ESCALATE / BLOCK) with least-privilege checks and approval batching for higher-risk actions.
  • Delegation and auditing: Automated agent selection, delegation contracts, sandboxed execution modes, side-effect recording, and an audit trail that feeds a closed-loop quality scoring system.
  • Use Case: Orchestrate a cross-team production deployment that requires DAG planning, staged approvals, parallel worker execution, and post-run compliance evidence.

Quick Start

Orchestrate a multi-step deployment across agents, enforce policy gates, and return a validated execution plan.

Dependency Matrix

Required Modules

None required

Components

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: jarvis-core
Download link: https://github.com/kmshihab7878/claude-code-setup/archive/main.zip#jarvis-core

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.