Claude
Skill darshitpp/x-agent/claude
Cross-agent task runner — let any AI CLI (Codex, Cursor, Claude, Gemini, Junie) delegate tasks to or get second opinions from the others
npx -y skills add darshitpp/x-agent --skill claudeAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Delegate tasks or get a second opinion from Claude Code CLI. Infers mode (delegation vs validation) from prompt context. Detects available models at runtime via the CLI. Use when cross-validating code, plans, or architecture with Claude Code, or offloading work to it. Do not use when already running inside Claude Code or for tasks that do not benefit from cross-model input.
SKILL.md
1.1 KB, as published. Nobody here has run it
Cross-Agent Task Runner — Claude Code CLI
Procedures
Step 1: Self-Call Detection
- Check for
CLAUDE_CODEenvironment variable orclaudein process ancestry. - If detected, stop and inform the user: "Cannot invoke Claude from within Claude. Use a different target CLI."
Step 2: Execute Shared Procedure
- Read
references/shared-procedure.mdfor the core workflow (mode inference, context gathering, prompt construction, result presentation). - Read
references/cli-claude.mdfor Claude-specific flags, model selection heuristics, and version compatibility matrix. - Follow the shared procedure using the Claude-specific details.