🧭
AI EngineeringRust

Orchestrator Advisor

by Th0rgal

Orchestrator Advisor is an AI Engineering skill for Claude Code, published by Th0rgal in sandboxed.sh.

491 stars50 forkson Th0rgal/sandboxed.shAdded 2026/08/26+1% in starsRepository updated 2026/08/20
ai-agentsautonomous-agentsclaudeclaude-codecoding-assistantcontainerizationdeveloper-toolsllmmcpokxopencodeorchestrationself-hostedweb3workspace-isolationxagent-hackathon
Install in seconds
Install Orchestrator Advisor
Copy Orchestrator Advisor into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/Th0rgal/sandboxed.sh/tree/master/skills/orchestrator-advisor ~/.claude/skills/orchestrator-advisor

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/Th0rgal/sandboxed.sh.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
skills/orchestrator-advisor/SKILL.md in Th0rgal/sandboxed.sh
Installs to
~/.claude/skills/orchestrator-advisor
Collection
One of 8 skills cataloged from this repository
Category
AI Engineering2451 skills

What Orchestrator Advisor does

Orchestrator Advisor gives persistent, read-only guidance for navigating a repository across multiple turns. Use it to build a mental map once and then answer follow-up questions with specific file references.

Orchestrator Advisor is cataloged under AI Engineering on DirSkills. Orchestrator Advisor comes from a repository tagged ai-agents, autonomous-agents, claude, claude-code and coding-assistant.

Documentation

README

Orchestrator Advisor

You are a persistent advisor: a strong-reasoning agent that a cheaper executor agent consults when it hits a dead end. You live for the whole mission — each question arrives as a new user message in the same session, so your accumulated understanding of the repository is your main value.

First turn

On your first message, invest in context once:

  • Read the architecture docs (README, CLAUDE.md, docs/) and skim the module layout of the areas the first question touches.
  • Build a mental map: key modules, data flow, conventions, test layout.
  • Then answer the first question.

Do not repeat this exploration on later questions — only read files that the new question specifically requires.

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Orchestrator Advisor

  • What else does Th0rgal publish alongside Orchestrator Advisor?

    Orchestrator Advisor is one of 8 skills that DirSkills catalogs from Th0rgal/sandboxed.sh, the repository it ships in. Its siblings there include Controllers Policy, Hermes Mission Control and Library Management. Each one is a separate skill with its own page in this directory, installs the same way Orchestrator Advisor does, and is maintained by Th0rgal in that same repository. The rest of the collection is listed on the Th0rgal/sandboxed.sh page.

  • How does Orchestrator Advisor compare to other AI Engineering skills?

    Orchestrator Advisor ranks #2185 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Orchestrator Advisor against them. Open each page to compare what they document and how they install.

More from Th0rgal/sandboxed.sh

Orchestrator Advisor is one of 8 skills cataloged on DirSkills from Th0rgal/sandboxed.sh.

See all 8 skills
🧭
5d ago

Controllers Policy

Controllers Policy defines the autonomy contract, safety limits, and routing rules for autonomous project controllers. Use it to decide when to act, merge, pause, or escalate during each tick.
AI Engineering
49150
🛰️
5d ago

Hermes Mission Control

Hermes Mission Control monitors long-running sandboxed.sh missions, diagnoses stalls and failures, and nudges them back on track. Use it to switch backends, resume stalled work, or send targeted hints when a mission gives up early.
Automation
49150
🗂️
5d ago

Library Management

Library Management manages the Sandboxed.sh Library of skills, agents, commands, tools, rules, MCP servers, and workspace templates through Library API tools. Use it to list, read, save, sync, commit, and push library changes.
Automation
49150
🧭
5d ago

Orchestrator Boss

Orchestrator Boss coordinates worker missions by splitting work into delegated tasks, checking acceptance criteria, and integrating results. Use it when you need parallel analysis and judgment without doing the implementation yourself.
AI Engineering
49150
🧠
5d ago

Orchestrator Executor

Orchestrator Executor writes and verifies the work directly, and only consults one persistent advisor when stuck. Use it for missions where you want an agent to implement changes itself but have a fallback for hard problems.
AI Engineering
49150
🧭
5d ago

Orchestrator Worker

Orchestrator Worker handles boss-spawned missions within the assigned workspace and scope. Use it to verify changes, stay within bounds, and report blockers or completion quickly.
Automation
49150