principle-encode-lessons-in-structure

Generate a Codex project skill that drives an app the way a user does — any language, framework, or platform.

Your agent working mode for selective explanations, milestone updates, simple code, and Poteto-style writing.

Apply before you trust, report, or act on a number you measured: a speedup, a regression, a throughput, or a latency.

Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in.

Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which…

Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart".

Design an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a human reviews after stepping away.

Vet a perf measurement (limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened) before you report or act on it.

Spawn Comment Sicko, fix accepted findings, and offer encodings for claimed constraints.

Apply when two or more fixes that share one premise have failed the same gate.

Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it.

Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks.