Skill Claude CodeCodex
Standardize how Architecture Decision Records are written so every decision is captured the same way and stays auditable. Use when: When a real, consequential technical decision is being made or recognized — and only then.
Skill Claude CodeCodex
Standardize how a Knowledge Capsule is written/reviewed so external consumers get safe, useful context. Use when: When creating or refining a Knowledge Capsule for sharing with another project.
Skill Claude CodeCodex
Standardize how kaddo graph export hints become precise relationship front matter. Use when: When relationship quality is partial/sparse/empty, or when reviewing .kaddo/graph-hints.md.
Skill Claude CodeCodex
Standardize the plan produced before implementation starts. Use when: Before writing code for a ready Work Item.
Skill Claude CodeCodex
Standardize how a Work Item's learning is captured when it closes. Use when: When finishing a Work Item, after implementation and verification.
Skill Claude CodeCodex
Standardize how a multirepo module's context is refined without duplicating global knowledge. Use when: When refining knowledge/module/module-context.md in a multirepo module repository.
Skill Claude CodeCodex
Standardize how precise code: ownership globs are proposed so Guard can relate code changes to the right knowledge. Use when: When a Work Item or artifact is missing ownership, or its ownership is too broad/inaccurate.
Skill Claude CodeCodex
Standardize how a Work Item is sharpened from a rough idea into a ready, implementable item. Use when: When improving a draft Work Item, or turning a backlog idea / roadmap candidate into a ready item.
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: