Skill Codex
Audit and complete a repository's release path. Use for "ship it", unfinished releases, RC promotion, or missing merges, tags, changesets, artifacts, and registry publication.
Skill Claude CodeCodex
Sync vendored third-party skills against their upstream repositories, re-apply local patches, and flag new upstream skills. Invoke explicitly with /sync-skills.
Skill Claude CodeCodex
Prove substantial work complete with file-backed gates and runnable checks. Use for exhaustive completion, a Depth Tree, or a completion ledger.
Skill Claude CodeCodex
Operate exe.dev virtual machines. Use when the task mentions exe.dev, exe VMs, .exe.xyz hosts, or exe.dev infrastructure.
Skill Claude CodeCodex
Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.
Hook Claude Code
One of 3 in settings.json
Runs before the agent uses a tool for Bash and Bash tool calls, executing rtk-rewrite.sh and block-claude-attribution.sh (2 commands). From jkomyno/.dotfiles.
Hook Claude Code
One of 3 in settings.json
Runs when the agent asks permission for an action for Bash tool calls, executing approve-temp-cleanup.sh. From jkomyno/.dotfiles.
Agent Claude Code
Turns requirements and scout findings into a concrete, ordered implementation plan; makes no changes.
Agent Claude Code
Independent code review of a diff or a set of files for bugs, regressions, and security issues; makes no changes.
Agent Claude Code
Fast read-only codebase recon; returns compressed findings with exact file paths and line ranges.
Agent Claude Code
General-purpose agent with all tools; implements a well-specified task in an isolated context.
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: