Five blind-tested agent skills for Codex and Claude Code, plus two standing instructions.
Skill Codex
Audit a codebase or subsystem for architecture simplification - shallow or pass-through modules, scattered concepts, naming drift, sibling workflows that disagree, weak test seams. Use when the user asks what to simplify or restructure. Not for a narrow fix or for implementing an already chosen design.
Skill Codex
Judge performance or resource claims on real hardware, and design the test, replay, evaluation, benchmark, soak or watch before it runs: latency, throughput, memory or headroom numbers, and accept-or-reject decisions on optimizations. Not for refactors with no resource claim.
Skill Codex
Use when the deliverable is authored or edited prose whose wording matters (docs, READMEs, release notes, public copy) or when the user asks to tighten, de-AI, or review writing. Not for chat answers, code review, or explanations of current work.
Skill Claude CodeCodex
Use when creating, revising, or critiquing a chart, dashboard, or KPI display that makes a quantitative comparison someone will act on. Covers honest comparison and rendered checks; leave palette, marks, and library mechanics to the medium's own skill. Skip decorative graphics and diagrams with no data.
Skill Claude CodeCodex
Audit an existing agent skill or instruction file for lines that do not change behavior, routing overlap, and portability, or vet a third-party skill before installing it. To create or edit a skill, use the platform's skill-creator instead. Not for running a skill's own task.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: