Sequence work into verifiable units

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.

Order work as a sequence of small units, each ending in a state you can check, and don't advance until the current one is green. The same discipline runs at two altitudes, how you execute and how you deliver.

Why: A break caught at the unit that caused it is cheap to localize. A break caught after a batch is buried, and you have already built further on a broken base. Sequencing those same units into a delivery a reviewer can replay turns "trust me" into "watch it go red, then green."

Execution. In a sweep, migration, or any run of similar edits, verify each change before starting the next. Never batch the edits and verify once at the end. Each unit is a before/after bracket: known-good state, one change, run the check, then proceed. Rebase onto clean trunk first so every check measures against the real baseline. When a lever does the edits, the per-unit check is nearly free; run it anyway.

Delivery. Stack commits and PRs in the order that proves the work. The canonical shape is the failing test first, then the fix on top. The first unit shows the bug is real (red), the next shows it resolved (green), so a reviewer sees both the problem and the proof. Other story orders are a subtraction before the reshape, a baseline capture before the treatment, the scaffold before the feature. Each commit lands on its own and the sequence reads as an argument.