alphaxiv/openresearch/orx-agent-delegation

Claude Code and agent skill by alphaxiv/openresearch

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

Create independent project chats with `orx agent spawn` using the user's New Chat settings. Covers standalone opening messages, project selection, worktrees, and compute authorization. Use before creating another chat.

Install

npx vskill@latest install alphaxiv/openresearch/orx-agent-delegation

SKILL.md

Create an independent chat

orx agent spawn creates an ordinary chat and submits its opening message, just like New Chat in OpenResearch. It uses the user's saved agent, model, reasoning, speed, permissions, and autonomy settings. It does not inherit this conversation or this chat's settings.

sh
orx agent spawn "<standalone opening message>"
orx agent spawn --title "<chat title>" --stdin
orx agent spawn "<message>" --project <project-id>

The project defaults to this OpenResearch chat's project; pass --project when that context is unavailable. The command requires the running local server. --harness, --model, and --no-wake are no longer supported.

The created chat is independent and appears in the sidebar without switching the user's view. It has its own transcript and normal session worktree. Its result will not be sent back here, and stopping this chat does not stop it. Use the harness's native subagents for subordinate work that needs to report back. Do not create a new chat as a substitute for a follow-up message.

Include the relevant project, experiment or commit, constraints, permitted compute, expected output, and definition of done in the opening message. Use --stdin for longer messages. Explicitly forbid compute launches when none are authorized. Changes stay in the new chat's worktree and never merge here automatically. Do not assign a branch already checked out by another session or edit a frozen experiment node.

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
6,315
Repository forks
404
7-day trend score
44

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/alphaxiv/openresearch/orx-agent-delegation/badge)](https://verified-skill.com/skills/alphaxiv/openresearch/orx-agent-delegation)

Something wrong with this skill or its page? Tell us.