| verified | true |
| lastVerifiedAt | 2026-02-28 |
| name | omega-claude-cli |
| description | Shell out to Claude Code CLI to invoke a second Claude session headlessly. Useful for cross-validation, second opinions, and isolated analysis without sharing current agent context. Requires Anthropic account. |
| version | 1.0.0 |
| model | sonnet |
| invoked_by | both |
| user_invocable | true |
| tools | ["Bash","Read"] |
| best_practices | ["Always run verify-setup.mjs before first invocation","Use for second-opinion validation where context isolation matters","Use --timeout-ms to prevent indefinite hangs","--dangerously-skip-permissions is required for headless mode (already in wrapper)","Use format-output.mjs to strip conversational text framing from JSON responses"] |
| error_handling | graceful |
| streaming | not_supported |
| source | builtin |
| trust_score | 100 |
| provenance_sha | 86c4c11e9df7f0cd |
Claude CLI Skill
Headless wrapper for Claude Code CLI. Invokes a separate Claude session via
claude -p "PROMPT" --dangerously-skip-permissions. Provides isolated second
opinions without sharing the current agent's context window.
When to Use
- Second-opinion validation (isolated Claude session without shared context)
- Cross-validation of current agent's reasoning
- Delegated deep analysis that should not consume current context window
- Multi-LLM consultation workflows (as one of the participating models)
- Chairman synthesis in llm-council workflows
Usage
Ask a question
node .claude/skills/omega-claude-cli/scripts/ask-claude.mjs "What are the security implications of this auth design?"
Specify model
node .claude/skills/omega-claude-cli/scripts/ask-claude.mjs "Review this code" --model sonnet
JSON output (with text stripping)
node .claude/skills/omega-claude-cli/scripts/ask-claude.mjs "Analyze dependencies" --json
With timeout
node .claude/skills/omega-claude-cli/scripts/ask-claude.mjs "Deep security review of auth.ts" --timeout-ms 300000
Availability Check
node .claude/skills/omega-claude-cli/scripts/verify-setup.mjs
Scripts
| Script | Purpose |
|---|
ask-claude.mjs | Core headless wrapper — prompt as positional arg to -p |
parse-args.mjs | Argument parser (--model, --json, --sandbox, --timeout-ms) |
verify-setup.mjs | Availability check with npx fallback |
format-output.mjs | Output normalization with extractJsonResponse() |
Flags
