Multica Ultimate Workbench

A durable, Git-versioned operating-memory layer for coordinating Codex, Claude Code and other agents on top of the Multica live-collaboration platform, distributed as an installable skill pack.

Visit website github.com

Multica Ultimate Workbench preserves the operating rules for a multi-agent workbench in Git rather than only inside the live Multica platform, keeping owners, review gates, handoffs, skill lanes and source-of-truth boundaries versioned, diffed and auditable independently of the running system. Multica itself remains the live collaboration layer for agents, issues, comments, direct chat, runtimes, skills and autopilots.

The public workbench skill pack installs through an open skills ecosystem command, and the project recommends listing its 33 public-safe skills before installing only the slice of the workbench grammar a given runtime actually needs, rather than the full set at once.

More in Agent skills

See all 581

Provenance gate
github.com
A deterministic authorization gateway that sits between an AI agent and its tools, tracing where each parameter of a side-effect call came from, and blocking the call or asking a human when the source does not check out.
- Agent skills
- AI evals
Expected Harm Calculus (EHC-4): Asimov's Four Laws for Autonomous AI Agents
github.com
A markdown framework of system rules that restates Isaac Asimov's Four Laws of Robotics as a set of prioritized loss calculations for large-language-model agents to follow, published as a discovery file for agents and crawlers to read.
- Agent skills
Vitruvius
github.com
An engineering research agent that runs a discover, read, synthesize, verify and review loop over technical questions, reading sources directly rather than inferring from titles, and publishing its own scored verifier benchmark, weaknesses included.
- Agent skills
- AI evals

More in Agent skills

Provenance gate

Expected Harm Calculus (EHC-4): Asimov's Four Laws for Autonomous AI Agents

Vitruvius

Cookies