Enforce intent engineering: a Claude Code plugin with 5 review lenses (predictability, convention, simplicity, experience, architecture) for planning, plan validation, code review, and codebase audit.
Skill Claude CodeCodex
Audit a whole codebase, subsystem, or feature against the intent-engineering lenses (predictability, convention, simplicity, experience, and architecture on supported frameworks) and produce a posture report — per-dimension 0-10 scores plus the top surprise/convention/complexity/UX/structural gaps. Use to assess an…
Skill Claude CodeCodex
Turn PR review comments, a triage markdown export, or open PR URLs into Intent Engineering config improvements — conventions.notes/sources, severityoverrides, optional pattern policy, and a short findings brief. Use when the user points at a PR, a PR stack triage doc, or wants to mine review learnings into .intense/.
Skill Claude CodeCodex
Setup and upgrade Intent Engineering project config in .intense/ — full wizard for greenfield monoliths and multi-repo workspaces (placement, conventions.auto roots, severityalign, pattern preference), plus upgrade that merges missing capabilities without clobbering notes. Optional calibrate measures repo…
Skill Claude CodeCodex
Inject intent-engineering principles into the planning phase — surface the least-astonishment, convention, simplicity, and UX considerations relevant to the work being planned, as a tailored advisory checklist. Lightweight and non-blocking; use while drafting a plan or thinking through an approach, before a full plan…
Skill Claude CodeCodex
Review code changes through the intent-engineering lenses (predictability, convention, simplicity, experience, and architecture on supported frameworks) — surfacing surprise, non-idiomatic patterns, needless complexity, UX gaps, and structural anti-patterns. Default (interactive) mode applies safe, verified fixes and…
Skill Claude CodeCodex
Validate a plan, spec, or requirements document against the four intent-engineering lenses before implementation — surfacing surprising designs, non-idiomatic or reinvented approaches, needless complexity/scope, and missing UX decisions (states, flows, IA, accessibility). Returns dimensional 0-10 ratings and the gaps…