ainative-build

ainative-build/skills

Plugin Claude Code

Plugin marketplace listing 1 plugin: aif.

ainative-build/skills

Plugin Claude Code

Portable coding-agent skills: aif-code-review (three-axis adversarial review), aif-recon (codebase reconnaissance), and aif-improve (architectural deepening opportunities).

ainative-build/skills

Agent

Single-axis code reviewer for the aif-code-review skill. Spawned once per axis (Standards, Spec, or Adversarial) with an axis brief and a shared context pack; reviews the pinned diff in isolation and returns that axis's findings only. Read-only — never edits code.

ainative-build/skills

Command

Three-axis adversarial code review (Standards / Spec / Adversarial). Auto-detects PR, commit, ref, --pending, or codebase.

ainative-build/skills

Command

Find architectural deepening opportunities in existing code — shallow modules to deepen, coupling to consolidate — ranked by evidence. Read-only until you pick one.

ainative-build/skills

Command

Codebase reconnaissance — find the relevant files, dependents, tests, and governing spec for a target.

ainative-build/skills

Skill Claude CodeCodex

Adversarial, axis-separated code review. Runs three isolated passes — Standards (code smells + structure/logic/types/perf), Spec (does it match the issue/PRD), and Adversarial (security + failure-mode red-team) — and never merges or re-ranks their findings. Auto-detects the review target: a PR, a commit, a fixed-point…

ainative-build/skills

Skill Claude CodeCodex

Find architectural deepening opportunities in existing code — shallow modules to make deep, tightly-coupled modules to consolidate, seams worth adding for testability and AI-navigability. Judges depth with the deletion test and reports evidence-backed candidates ranked by recommendation strength, never touching code…

ainative-build/skills

Skill Claude CodeCodex

Fast, token-efficient codebase reconnaissance. Given a task, a set of changed files, or a question, it finds the relevant files, their dependents/callers, related tests, and any governing spec/PRD/issue — and returns one concise context report. Divides the tree across parallel subagents when available, falls back to a…