Prove It Works

Uni-pstack Runtime Adapter

This is a portable port of upstream Cursor pstack. Apply these overrides before following the original workflow:

• Cursor Task or subagent calls mean Codex delegation. In Codex, use native Codex subagents. In Claude Code, launch Codex CLI workers using the installed pstack skill spawn-codex-worker script or direct codex exec.
• Replace upstream Composer, Claude Opus, and other panel defaults with Codex gpt-5.6-sol and task-appropriate reasoning: medium for routine implementation and exploration; high for judgment, synthesis, and high-risk work. Use the supported fast or priority tier.
• Claude-only fallback model policy lives in the installed pstack delegation reference. Do not infer Claude model choices from this skill.
• Cursor-only commands such as loop, babysit, deslop, control-ui, and control-cli are conceptual cues. Use the host terminal, browser, review, subagent, and git tools directly.
• Cursor paths become host-appropriate project or user configuration paths. Preserve the workflow intent, not Cursor-specific storage.

Verify every task output by checking the real thing directly. Do not infer from proxies, self-reports, or "it compiles."

Why: Unverified work has unknown correctness. Indirect verification (file mtimes, output freshness, agent self-reports, cached screenshots) feels cheaper than direct observation. Acting on a wrong inference costs far more than checking the source.

Pattern: After completing any task, ask: "how do I prove this actually works?"