Hermes Atlas
Multi-agent & orchestration · works with Hermes Agent

Multica Ultimate Workbench

Fearvox/multica-ultimate-workbench

Skill pack for coordinating Codex, Claude Code and Hermes agents on Multica with review gates

In short

Multica Ultimate Workbench is a public skill pack and operating-memory repository for coordinating Codex, Claude Code and Hermes agents on top of Multica. It keeps roles, review gates and safety rules in Git.

What Multica Ultimate Workbench does

Multica Ultimate Workbench is a public skill pack and operating-memory repository for coordinating Codex, Claude Code and Hermes agents on top of Multica. Multica stays the live collaboration layer for agents, issues, comments, runtimes, skills and autopilots, while this repository keeps the surrounding operating model in Git: roles, decisions, templates, safety rules, verification scripts and review discipline.

The skills install through the open skills ecosystem with npx skills add, and the README says 33 public-safe skills can be listed first and installed selectively. Documented areas include a two-ring system, an SDD workflow, an algorithm advisory gate, goal mode, wake reports, and lanes for Capy process checks, Sanity unified context, agent install unification, the Flue agent harness and Mirage VFS tooling. It does not modify Multica's daemon, Desktop UI or core runtime.

Key features

  • 33 public-safe skills installable with npx skills add
  • Agent roster and role definitions for Codex, Claude Code and Hermes agents
  • Review gates, an SDD workflow and an algorithm advisory gate
  • Goal mode and wake reports for long-running coordination
  • Context lanes including Sanity unified context and Capy process checks
  • Verification scripts and templates kept in Git

When to use it

  • Give a Multica workspace documented owners, gates and handoff rules
  • Install only the workbench skills a given agent runtime needs
  • Audit multi-agent decisions and reviews through versioned files instead of chat history

Who it is for: Teams already using Multica who coordinate several coding agents and want shared operating rules.

How it fits with Hermes Agent

Hermes is one of three agent types, with Codex and Claude Code, that the workbench coordinates; the repository carries the hermes-agent topic.

How to install Multica Ultimate Workbench

These commands are copied from the project's README. Check the repository for the latest steps before you run them.

npx skills add Fearvox/multica-ultimate-workbench --list --full-depth
npx skills add Fearvox/multica-ultimate-workbench --skill workbench-self-awareness-infra workbench-sdd workbench-conductor
npx skills add Fearvox/multica-ultimate-workbench --all

FAQ

What is Multica Ultimate Workbench?

Multica Ultimate Workbench is a skill pack and operating-memory repository for a multi-agent workbench built on Multica. It stores roles, decisions, templates, safety rules and review discipline in Git.

Does Multica Ultimate Workbench work with Hermes Agent?

Yes, in a supporting role. The README describes it as a memory layer for coordinating Codex, Claude Code and Hermes agents on top of Multica.

Is Multica Ultimate Workbench free and open source?

The repository has no license file, so default copyright applies and you should check with the author before reuse. The source code is public on GitHub.

Similar multi-agent for Hermes Agent

All multi-agent

Related guides: Build agent teams with the Hermes kanban board · Run multiple Hermes agents with profiles · Connect Hermes agents on several machines with Hermes Desktop