Using Claude P | Agent Skills Atlas

About this skill

Use Claude Code non-interactive (-p/--print) mode for scripting, automation, and headless execution. Trigger: '''claude -p''', '''비대화형 claude''', '''headless claude''', '''스크립트에서 claude'''. Covers: CLI flag usage and gotchas (--output-format, --allowedTools, --resume, --dangerously-skip-permissions), JSON output parsing, session chaining, saving results to files, SSH remote execution of claude, harness self-testing (T1~T8), and known flag interaction bugs. Use when users want to run claude programmatically, pipe output, parse results, automate workflows, troubleshoot CLI flag behavior, or execute claude on remote machines. NOT for Codex CLI (use using-codex-exec). NOT for interactive TUI usage.

Quick start

Copy the install prompt. Use the green button above this README.
Send it to your agent. Paste it into your coding agent’s chat and send.
Review the setup. Your agent checks the skill’s instructions, requirements, and installation scope.

Installation guide →

Review, license & listing details

Review the source before using this skill

This is an imported listing. We haven’t certified its safety, license, or compatibility. Skills may include executable scripts.

Automated security scan: Partial

Only SKILL.md was scanned. Supporting files and scripts were not checked. No safety grade has been assigned.

0 potential findings · Scanned 11/4/2026 · Scanner 0.2.1

Content SHA-256: dd4823ba1b9dfa9f966a3e00ab31f0fc3852b161c7ac4a342522ad691ff84e0d

About scan coverage and limitations

Original listing metadata

Original name

using-claude-p

Original description

About this listing

Category: Automation & workflows
Reported license: Not specified
Listing language (estimated): English
Review status: Not individually reviewed
Agent compatibility: Atlas installation supports Claude Code, Codex, and Cursor. Skill-specific dependencies and features are checked during setup.